Jeffrey M. Cochran
Research Subjects
Research Interests
Jeffrey M. Cochran has a total of 57 co-authors. Here are the top co-authors by number of shared publications:
- Jonathan Knights
Mindstrong Health, Menlo Park, CA, United States
5 shared publications - David Richard Busch
The Univ. of Texas Southwestern Medical Ctr. at Dallas
4 shared publications - Zahra Heidary
Otsuka Pharmaceutical Development & Commercialization, Inc, Princeton, NJ, United States
4 shared publications - Arjun G. Yodh
Department of Physics and Astronomy, University of Pennsylvania, Philadelphia, PA 19104, USA
3 shared publications - Christophe Le Gallo
Otsuka Pharmaceutical Development & Commercialization, Inc, Princeton, NJ, United States
3 shared publications - J Corey Reuteman-Fowler
Boehringer Ingelheim Pharmaceuticals, Inc., Ridgefield, USA
3 shared publications
Latest Publications
- Open Access
- 20 December 2024
- Published by JMIR Publications Inc. in JMIR Mental Health
- Vol. 11 (1) , e62959
Developing a Sleep Algxorithm to Support a Digital Medicine System: Noninterventional, Observational Sleep Study
Background: Sleep-wake patterns are important behavioral biomarkers for patients with serious mental illness (SMI), providing insight into their well-being. The gold standard for monitoring sleep is polysomnography (PSG), which requires a sleep lab facility; however, advances in wearable sensor technology allow for real-world sleep-wake monitoring. Objective: The goal of this study was to develop a PSG-validated sleep algorithm using accelerometer (ACC) and electrocardiogram (ECG) data from a wearable patch to accurately quantify sleep in a real-world setting. Methods: In this noninterventional, nonsignificant-risk, abbreviated investigational device exemption, single-site study, participants wore the reusable wearable sensor version 2 (RW2) patch. The RW2 patch is part of a digital medicine system (aripiprazole with sensor) designed to provide objective records of medication ingestion for patients with schizophrenia, bipolar I disorder, and major depressive disorder. This study developed a sleep algorithm from patch data and did not contain any study-related or digitized medication. Patch-acquired ACC and ECG data were compared against PSG data to build machine learning classification models to distinguish periods of wake from sleep. The PSG data provided sleep stage classifications at 30-second intervals, which were combined into 5-minute windows and labeled as sleep or wake based on the majority of sleep stages within the window. ACC and ECG features were derived for each 5-minute window. The algorithm that most accurately predicted sleep parameters against PSG data was compared to commercially available wearable devices to further benchmark model performance. Results: Of 80 participants enrolled, 60 had at least 1 night of analyzable ACC and ECG data (25 healthy volunteers and 35 participants with diagnosed SMI). Overall, 10,574 valid 5-minute windows were identified (5854 from participants with SMI), and 84% (n=8830) were classified as greater than half sleep. Of the 3 models tested, the conditional random field algorithm provided the most robust sleep-wake classification. Performance was comparable to the middle 50% of commercial devices evaluated in a recent publication, providing a sleep detection performance of 0.93 (sensitivity) and wake detection performance of 0.60 (specificity) at a prediction probability threshold of 0.75. The conditional random field algorithm retained this performance for individual sleep parameters, including total sleep time, sleep efficiency, and wake after sleep onset (within the middle 50% to top 25% of the assessed devices). The only parameter where the model performance was lower was sleep onset latency (within the bottom 25% of all comparator devices). Conclusions: Using industry-best practices, we developed a sleep algorithm for use with the RW2 patch that can accurately detect sleep and wake windows compared to PSG-labeled sleep data. This algorithm may be used for a more complete understanding of well-being for patients with SMI in a real-world setting, without the need for PSG and a sleep lab.
- 20 December 2024
- Published by JMIR Publications Inc. in JMIR Mental Health
- Vol. 11 (1) , e62959
Open AccessDeveloping a Sleep Algxorithm to Support a Digital Medicine System: Noninterventional, Observational Sleep Study
Background: Sleep-wake patterns are important behavioral biomarkers for patients with serious mental illness (SMI), providing insight into their well-being. The gold standard for monitoring sleep is polysomnography (PSG), which requires a sleep lab facility; however, advances in wearable sensor technology allow for real-world sleep-wake monitoring. Objective: The goal of this study was to develop a PSG-validated sleep algorithm using accelerometer (ACC) and electrocardiogram (ECG) data from a wearable patch to accurately quantify sleep in a real-world setting. Methods: In this noninterventional, nonsignificant-risk, abbreviated investigational device exemption, single-site study, participants wore the reusable wearable sensor version 2 (RW2) patch. The RW2 patch is part of a digital medicine system (aripiprazole with sensor) designed to provide objective records of medication ingestion for patients with schizophrenia, bipolar I disorder, and major depressive disorder. This study developed a sleep algorithm from patch data and did not contain any study-related or digitized medication. Patch-acquired ACC and ECG data were compared against PSG data to build machine learning classification models to distinguish periods of wake from sleep. The PSG data provided sleep stage classifications at 30-second intervals, which were combined into 5-minute windows and labeled as sleep or wake based on the majority of sleep stages within the window. ACC and ECG features were derived for each 5-minute window. The algorithm that most accurately predicted sleep parameters against PSG data was compared to commercially available wearable devices to further benchmark model performance. Results: Of 80 participants enrolled, 60 had at least 1 night of analyzable ACC and ECG data (25 healthy volunteers and 35 participants with diagnosed SMI). Overall, 10,574 valid 5-minute windows were identified (5854 from participants with SMI), and 84% (n=8830) were classified as greater than half sleep. Of the 3 models tested, the conditional random field algorithm provided the most robust sleep-wake classification. Performance was comparable to the middle 50% of commercial devices evaluated in a recent publication, providing a sleep detection performance of 0.93 (sensitivity) and wake detection performance of 0.60 (specificity) at a prediction probability threshold of 0.75. The conditional random field algorithm retained this performance for individual sleep parameters, including total sleep time, sleep efficiency, and wake after sleep onset (within the middle 50% to top 25% of the assessed devices). The only parameter where the model performance was lower was sleep onset latency (within the bottom 25% of all comparator devices). Conclusions: Using industry-best practices, we developed a sleep algorithm for use with the RW2 patch that can accurately detect sleep and wake windows compared to PSG-labeled sleep data. This algorithm may be used for a more complete understanding of well-being for patients with SMI in a real-world setting, without the need for PSG and a sleep lab.
- Open Access
- 12 December 2023
- Published by JMIR Publications Inc. in JMIR Formative Research
- Vol. 7, e44768
Safety Evaluation in Iterative Development of Wearable Patches for Aripiprazole Tablets With Sensor: Pooled Analysis of Clinical Trials
Background: Wearable sensors in digital health may pose a risk for skin irritation through the use of wearable patches. Little is known about how patient- and product-related factors impact the risk of skin irritation. Aripiprazole tablets with sensor (AS, Abilify MyCite; Otsuka America Pharmaceutical, Inc) is a digital medicine system indicated for the treatment of patients with schizophrenia, bipolar I disorder, and major depressive disorder. AS includes aripiprazole tablets with an embedded ingestible event marker, a wearable sensor attached to the skin through a wearable patch, a smartphone app, and a web-based portal. To continuously improve the final product, successive iterations of wearable patches were developed, including raisin patch version 4 (RP4), followed by disposable wearable sensor version 5 (DW5), and then reusable wearable sensor version 2 (RW2). Objective: This analysis pooled safety data from clinical studies in adult participants using the RP4, DW5, and RW2 wearable patches of AS and evaluated adverse events related to the use of wearable patches. Methods: Safety data from 12 studies in adults aged 18-65 years from May 2010 to August 2020 were analyzed. All studies evaluated safety, with studies less than 2 weeks also specifically examining human factors associated with the use of the components of AS. Healthy volunteers or patients with schizophrenia, bipolar I disorder, or major depressive disorder were enrolled; those who were exposed to at least 1 wearable patch were included in the safety analysis. Adverse events related to the use of a wearable patch were evaluated. Abrasions, blisters, dermatitis, discoloration, erythema, irritation, pain, pruritus, rash, and skin reactions were grouped as skin irritation events (SIEs). All statistical analyses were descriptive. Results: The analysis included 763 participants (mean [SD] age 42.6 [12.9] years; White: n=359, 47.1%; and male: n=420, 55%). Participants were healthy volunteers (n=269, 35.3%) or patients with schizophrenia (n=402, 52.7%), bipolar I disorder (n=57, 7.5%), or major depressive disorder (n=35, 4.6%). Overall, 13.6% (104/763) of the participants reported at least 1 SIE, all of which were localized to the wearable patch site. Incidence of ≥1 patch-related SIEs was seen in 18.1% (28/155), 14.2% (55/387), and 9.2% (28/306) of participants who used RP4, DW5, and RW2, respectively. Incidence of SIE-related treatment discontinuation was low, which is reported by 1.9% (3/155), 3.1% (12/387), and 1.3% (4/306) of participants who used RP4, DW5, and RW2, respectively. Conclusions: The incidence rates of SIEs reported as the wearable patch versions evolved from RP4 through RW2 suggest that information derived from reported adverse events may have informed product design and development, which could have improved both tolerability and wearability of successive products. Trial Registration: Clinicaltrials.gov NCT02091882, https://clinicaltrials.gov/study/NCT02091882; Clinicaltrials.gov NCT02404532, https://clinicaltrials.gov/study/NCT02404532; Clinicaltrials.gov NCT02722967, https://clinicaltrials.gov/study/NCT02722967; Clinicaltrials.gov NCT02219009, https://clinicaltrials.gov/study/NCT02219009; Clinicaltrials.gov NCT03568500, https://clinicaltrials.gov/study/NCT03568500; Clinicaltrials.gov NCT03892889, https://clinicaltrials.gov/study/NCT03892889
- 12 December 2023
- Published by JMIR Publications Inc. in JMIR Formative Research
- Vol. 7, e44768
Open AccessSafety Evaluation in Iterative Development of Wearable Patches for Aripiprazole Tablets With Sensor: Pooled Analysis of Clinical Trials
Background: Wearable sensors in digital health may pose a risk for skin irritation through the use of wearable patches. Little is known about how patient- and product-related factors impact the risk of skin irritation. Aripiprazole tablets with sensor (AS, Abilify MyCite; Otsuka America Pharmaceutical, Inc) is a digital medicine system indicated for the treatment of patients with schizophrenia, bipolar I disorder, and major depressive disorder. AS includes aripiprazole tablets with an embedded ingestible event marker, a wearable sensor attached to the skin through a wearable patch, a smartphone app, and a web-based portal. To continuously improve the final product, successive iterations of wearable patches were developed, including raisin patch version 4 (RP4), followed by disposable wearable sensor version 5 (DW5), and then reusable wearable sensor version 2 (RW2). Objective: This analysis pooled safety data from clinical studies in adult participants using the RP4, DW5, and RW2 wearable patches of AS and evaluated adverse events related to the use of wearable patches. Methods: Safety data from 12 studies in adults aged 18-65 years from May 2010 to August 2020 were analyzed. All studies evaluated safety, with studies less than 2 weeks also specifically examining human factors associated with the use of the components of AS. Healthy volunteers or patients with schizophrenia, bipolar I disorder, or major depressive disorder were enrolled; those who were exposed to at least 1 wearable patch were included in the safety analysis. Adverse events related to the use of a wearable patch were evaluated. Abrasions, blisters, dermatitis, discoloration, erythema, irritation, pain, pruritus, rash, and skin reactions were grouped as skin irritation events (SIEs). All statistical analyses were descriptive. Results: The analysis included 763 participants (mean [SD] age 42.6 [12.9] years; White: n=359, 47.1%; and male: n=420, 55%). Participants were healthy volunteers (n=269, 35.3%) or patients with schizophrenia (n=402, 52.7%), bipolar I disorder (n=57, 7.5%), or major depressive disorder (n=35, 4.6%). Overall, 13.6% (104/763) of the participants reported at least 1 SIE, all of which were localized to the wearable patch site. Incidence of ≥1 patch-related SIEs was seen in 18.1% (28/155), 14.2% (55/387), and 9.2% (28/306) of participants who used RP4, DW5, and RW2, respectively. Incidence of SIE-related treatment discontinuation was low, which is reported by 1.9% (3/155), 3.1% (12/387), and 1.3% (4/306) of participants who used RP4, DW5, and RW2, respectively. Conclusions: The incidence rates of SIEs reported as the wearable patch versions evolved from RP4 through RW2 suggest that information derived from reported adverse events may have informed product design and development, which could have improved both tolerability and wearability of successive products. Trial Registration: Clinicaltrials.gov NCT02091882, https://clinicaltrials.gov/study/NCT02091882; Clinicaltrials.gov NCT02404532, https://clinicaltrials.gov/study/NCT02404532; Clinicaltrials.gov NCT02722967, https://clinicaltrials.gov/study/NCT02722967; Clinicaltrials.gov NCT02219009, https://clinicaltrials.gov/study/NCT02219009; Clinicaltrials.gov NCT03568500, https://clinicaltrials.gov/study/NCT03568500; Clinicaltrials.gov NCT03892889, https://clinicaltrials.gov/study/NCT03892889
- Open Access
- 8 December 2022
- Published by JMIR Publications Inc. in JMIR Preprints
Safety Evaluation in Iterative Development of Wearable Patches for Aripiprazole Tablets With Sensor: Pooled Analysis of Clinical Trials (Preprint)
BACKGROUND Wearable sensors in digital health may pose a risk for skin irritation through the use of wearable patches. Little is known about how patient- and product-related factors impact the risk of skin irritation. Aripiprazole tablets with sensor (AS, Abilify MyCite; Otsuka America Pharmaceutical, Inc) is a digital medicine system indicated for the treatment of patients with schizophrenia, bipolar I disorder, and major depressive disorder. AS includes aripiprazole tablets with an embedded ingestible event marker, a wearable sensor attached to the skin through a wearable patch, a smartphone app, and a web-based portal. To continuously improve the final product, successive iterations of wearable patches were developed, including raisin patch version 4 (RP4), followed by disposable wearable sensor version 5 (DW5), and then reusable wearable sensor version 2 (RW2). OBJECTIVE This analysis pooled safety data from clinical studies in adult participants using the RP4, DW5, and RW2 wearable patches of AS and evaluated adverse events related to the use of wearable patches. METHODS Safety data from 12 studies in adults aged 18-65 years from May 2010 to August 2020 were analyzed. All studies evaluated safety, with studies less than 2 weeks also specifically examining human factors associated with the use of the components of AS. Healthy volunteers or patients with schizophrenia, bipolar I disorder, or major depressive disorder were enrolled; those who were exposed to at least 1 wearable patch were included in the safety analysis. Adverse events related to the use of a wearable patch were evaluated. Abrasions, blisters, dermatitis, discoloration, erythema, irritation, pain, pruritus, rash, and skin reactions were grouped as skin irritation events (SIEs). All statistical analyses were descriptive. RESULTS The analysis included 763 participants (mean [SD] age 42.6 [12.9] years; White: n=359, 47.1%; and male: n=420, 55%). Participants were healthy volunteers (n=269, 35.3%) or patients with schizophrenia (n=402, 52.7%), bipolar I disorder (n=57, 7.5%), or major depressive disorder (n=35, 4.6%). Overall, 13.6% (104/763) of the participants reported at least 1 SIE, all of which were localized to the wearable patch site. Incidence of ≥1 patch-related SIEs was seen in 18.1% (28/155), 14.2% (55/387), and 9.2% (28/306) of participants who used RP4, DW5, and RW2, respectively. Incidence of SIE-related treatment discontinuation was low, which is reported by 1.9% (3/155), 3.1% (12/387), and 1.3% (4/306) of participants who used RP4, DW5, and RW2, respectively. CONCLUSIONS The incidence rates of SIEs reported as the wearable patch versions evolved from RP4 through RW2 suggest that information derived from reported adverse events may have informed product design and development, which could have improved both tolerability and wearability of successive products. CLINICALTRIAL Clinicaltrials.gov NCT02091882, https://clinicaltrials.gov/study/NCT02091882; Clinicaltrials.gov NCT02404532, https://clinicaltrials.gov/study/NCT02404532; Clinicaltrials.gov NCT02722967, https://clinicaltrials.gov/study/NCT02722967; Clinicaltrials.gov NCT02219009, https://clinicaltrials.gov/study/NCT02219009; Clinicaltrials.gov NCT03568500, https://clinicaltrials.gov/study/NCT03568500; Clinicaltrials.gov NCT03892889, https://clinicaltrials.gov/study/NCT03892889
- 8 December 2022
- Published by JMIR Publications Inc. in JMIR Preprints
Open AccessSafety Evaluation in Iterative Development of Wearable Patches for Aripiprazole Tablets With Sensor: Pooled Analysis of Clinical Trials (Preprint)
BACKGROUND Wearable sensors in digital health may pose a risk for skin irritation through the use of wearable patches. Little is known about how patient- and product-related factors impact the risk of skin irritation. Aripiprazole tablets with sensor (AS, Abilify MyCite; Otsuka America Pharmaceutical, Inc) is a digital medicine system indicated for the treatment of patients with schizophrenia, bipolar I disorder, and major depressive disorder. AS includes aripiprazole tablets with an embedded ingestible event marker, a wearable sensor attached to the skin through a wearable patch, a smartphone app, and a web-based portal. To continuously improve the final product, successive iterations of wearable patches were developed, including raisin patch version 4 (RP4), followed by disposable wearable sensor version 5 (DW5), and then reusable wearable sensor version 2 (RW2). OBJECTIVE This analysis pooled safety data from clinical studies in adult participants using the RP4, DW5, and RW2 wearable patches of AS and evaluated adverse events related to the use of wearable patches. METHODS Safety data from 12 studies in adults aged 18-65 years from May 2010 to August 2020 were analyzed. All studies evaluated safety, with studies less than 2 weeks also specifically examining human factors associated with the use of the components of AS. Healthy volunteers or patients with schizophrenia, bipolar I disorder, or major depressive disorder were enrolled; those who were exposed to at least 1 wearable patch were included in the safety analysis. Adverse events related to the use of a wearable patch were evaluated. Abrasions, blisters, dermatitis, discoloration, erythema, irritation, pain, pruritus, rash, and skin reactions were grouped as skin irritation events (SIEs). All statistical analyses were descriptive. RESULTS The analysis included 763 participants (mean [SD] age 42.6 [12.9] years; White: n=359, 47.1%; and male: n=420, 55%). Participants were healthy volunteers (n=269, 35.3%) or patients with schizophrenia (n=402, 52.7%), bipolar I disorder (n=57, 7.5%), or major depressive disorder (n=35, 4.6%). Overall, 13.6% (104/763) of the participants reported at least 1 SIE, all of which were localized to the wearable patch site. Incidence of ≥1 patch-related SIEs was seen in 18.1% (28/155), 14.2% (55/387), and 9.2% (28/306) of participants who used RP4, DW5, and RW2, respectively. Incidence of SIE-related treatment discontinuation was low, which is reported by 1.9% (3/155), 3.1% (12/387), and 1.3% (4/306) of participants who used RP4, DW5, and RW2, respectively. CONCLUSIONS The incidence rates of SIEs reported as the wearable patch versions evolved from RP4 through RW2 suggest that information derived from reported adverse events may have informed product design and development, which could have improved both tolerability and wearability of successive products. CLINICALTRIAL Clinicaltrials.gov NCT02091882, https://clinicaltrials.gov/study/NCT02091882; Clinicaltrials.gov NCT02404532, https://clinicaltrials.gov/study/NCT02404532; Clinicaltrials.gov NCT02722967, https://clinicaltrials.gov/study/NCT02722967; Clinicaltrials.gov NCT02219009, https://clinicaltrials.gov/study/NCT02219009; Clinicaltrials.gov NCT03568500, https://clinicaltrials.gov/study/NCT03568500; Clinicaltrials.gov NCT03892889, https://clinicaltrials.gov/study/NCT03892889
- Open Access
- 28 July 2022
- Published by Taylor & Francis in Patient Preference and Adherence
- Vol. ume 16, 1805-1817
Participant Engagement and Symptom Improvement: Aripiprazole Tablets with Sensor for the Treatment of Schizophrenia
Purpose: A recent, phase 3b, mirror-image clinical trial of outpatients with schizophrenia found that use of aripiprazole tablets with sensor (AS; Abilify MyCite®, comprising an ingestible event-marker sensor embedded in aripiprazole tablets, wearable sensor patches, and a smartphone application) reduced the incidence of psychiatric hospitalizations relative to oral standard-of-care antipsychotics. This analysis explored the relationship between AS engagement by participants and changes in participant performance and symptom-severity measures assessed by clinical raters. Participants and Methods: This post hoc analysis used prospectively collected clinical data from a phase 3b clinical trial (NCT03892889). Outpatients had schizophrenia, were aged 18– 65 years, and had ≥ 1 psychiatric hospitalization in the previous 48 months. Participants were grouped by study completion status and a k-means clustering algorithm based on AS utilization, resulting in 3 groups: discontinued (discontinued AS before month 3 of the study); moderate engagement (completed 3 months, used AS intermittently); and high engagement (completed 3 months, used AS regularly). Baseline to end-of-study differences for the Clinical Global Impression Scale (Severity of Illness and Improvement of Illness scales), Personal and Social Performance Scale, and Positive and Negative Syndrome Scale were calculated. Results: A total of 277 outpatients were enrolled (discontinued, n = 164; moderate engagement, n = 63; high engagement, n = 50). All groups experienced symptom improvement from baseline to end-of-study, with significant changes in the more-engaged groups. Highly engaged participants showed significant improvement for all clinical scores and subscores (all P < 0.05) and demonstrated significantly more improvement in symptoms than participants with less engagement. Conclusion: Participants who completed 3 months of the study and had higher AS engagement experienced significantly greater improvement in their end-of-study clinical assessments versus participants who did not complete 3 months. Improvement may be related to more-consistent medication intake and better engagement with a digital health system.
- 28 July 2022
- Published by Taylor & Francis in Patient Preference and Adherence
- Vol. ume 16, 1805-1817
Open AccessParticipant Engagement and Symptom Improvement: Aripiprazole Tablets with Sensor for the Treatment of Schizophrenia
Purpose: A recent, phase 3b, mirror-image clinical trial of outpatients with schizophrenia found that use of aripiprazole tablets with sensor (AS; Abilify MyCite®, comprising an ingestible event-marker sensor embedded in aripiprazole tablets, wearable sensor patches, and a smartphone application) reduced the incidence of psychiatric hospitalizations relative to oral standard-of-care antipsychotics. This analysis explored the relationship between AS engagement by participants and changes in participant performance and symptom-severity measures assessed by clinical raters. Participants and Methods: This post hoc analysis used prospectively collected clinical data from a phase 3b clinical trial (NCT03892889). Outpatients had schizophrenia, were aged 18– 65 years, and had ≥ 1 psychiatric hospitalization in the previous 48 months. Participants were grouped by study completion status and a k-means clustering algorithm based on AS utilization, resulting in 3 groups: discontinued (discontinued AS before month 3 of the study); moderate engagement (completed 3 months, used AS intermittently); and high engagement (completed 3 months, used AS regularly). Baseline to end-of-study differences for the Clinical Global Impression Scale (Severity of Illness and Improvement of Illness scales), Personal and Social Performance Scale, and Positive and Negative Syndrome Scale were calculated. Results: A total of 277 outpatients were enrolled (discontinued, n = 164; moderate engagement, n = 63; high engagement, n = 50). All groups experienced symptom improvement from baseline to end-of-study, with significant changes in the more-engaged groups. Highly engaged participants showed significant improvement for all clinical scores and subscores (all P < 0.05) and demonstrated significantly more improvement in symptoms than participants with less engagement. Conclusion: Participants who completed 3 months of the study and had higher AS engagement experienced significantly greater improvement in their end-of-study clinical assessments versus participants who did not complete 3 months. Improvement may be related to more-consistent medication intake and better engagement with a digital health system.
- Open Access
- 28 July 2022
- Published by Taylor & Francis in Neuropsychiatric Disease and Treatment
- Vol. ume 18, 1521-1534
Healthcare Provider Engagement with a Novel Dashboard for Tracking Medication Ingestion: Impact on Treatment Decisions and Clinical Assessments for Adults with Schizophrenia
Purpose: Schizophrenia is a severe, chronic condition accounting for disproportionate healthcare utilization. Antipsychotics can reduce relapse rates, but the characteristics of schizophrenia may hinder medication adherence. A phase 3b open-label clinical trial used aripiprazole tablets with sensor (AS; includes pills with ingestible event-marker, wearable sensor patches and smartphone application) in adults with schizophrenia. This post hoc analysis explored how healthcare providers’ (HCPs) usage of a dashboard that provided medication ingestion information impacted treatment decisions and clinical assessments. Patients and Methods: Participants used AS for 3– 6 months. HCPs were instructed to check the dashboard regularly, identify features used, and report impact on treatment decisions. After stratifying HCPs by frequency of dashboard checks and resulting treatment decisions, changes from baseline were calculated for Positive and Negative Syndrome Scale (PANSS), Clinical Global Impression (CGI)–Severity of Illness and CGI-Improvement (CGI-I), and Personal and Social Performance (PSP), and compared using Mann–Whitney U-tests and rank-biserial correlation coefficient (r) effect sizes. Results: To ensure sufficient opportunity for AS engagement, 113 participants who completed ≥ 3 months on study were analyzed. HCPs most often accessed dashboard data regarding medication ingestion and missed doses. HCPs recommended adherence counseling and participant education most often. Participants whose HCPs used the dashboard more and recommended adherence counseling and participant education (n=61) improved significantly more than participants with less dashboard-active HCPs (n=49) in CGI-I mean score (2.9 versus 3.4 [p=0.004]), total PANSS (mean change: − 9.2 versus − 3.1 [p=0.0002]), PANSS positive subscale (− 3.2 versus − 1.5 [p=0.003]), PANSS general subscale (− 4.3 versus − 1.2 [p=0.02]), and Marder factor for negative symptoms (− 1.9 versus 0.0 [p=0.03]). Most HCPs found the dashboard easy to use (74%) and helpful for improving conversations with participants about their treatment plan and progress (78%). Conclusion: This provider dashboard may facilitate discussions with patients about regular medication-taking, which can improve patient outcomes.
- 28 July 2022
- Published by Taylor & Francis in Neuropsychiatric Disease and Treatment
- Vol. ume 18, 1521-1534
Open AccessHealthcare Provider Engagement with a Novel Dashboard for Tracking Medication Ingestion: Impact on Treatment Decisions and Clinical Assessments for Adults with Schizophrenia
Purpose: Schizophrenia is a severe, chronic condition accounting for disproportionate healthcare utilization. Antipsychotics can reduce relapse rates, but the characteristics of schizophrenia may hinder medication adherence. A phase 3b open-label clinical trial used aripiprazole tablets with sensor (AS; includes pills with ingestible event-marker, wearable sensor patches and smartphone application) in adults with schizophrenia. This post hoc analysis explored how healthcare providers’ (HCPs) usage of a dashboard that provided medication ingestion information impacted treatment decisions and clinical assessments. Patients and Methods: Participants used AS for 3– 6 months. HCPs were instructed to check the dashboard regularly, identify features used, and report impact on treatment decisions. After stratifying HCPs by frequency of dashboard checks and resulting treatment decisions, changes from baseline were calculated for Positive and Negative Syndrome Scale (PANSS), Clinical Global Impression (CGI)–Severity of Illness and CGI-Improvement (CGI-I), and Personal and Social Performance (PSP), and compared using Mann–Whitney U-tests and rank-biserial correlation coefficient (r) effect sizes. Results: To ensure sufficient opportunity for AS engagement, 113 participants who completed ≥ 3 months on study were analyzed. HCPs most often accessed dashboard data regarding medication ingestion and missed doses. HCPs recommended adherence counseling and participant education most often. Participants whose HCPs used the dashboard more and recommended adherence counseling and participant education (n=61) improved significantly more than participants with less dashboard-active HCPs (n=49) in CGI-I mean score (2.9 versus 3.4 [p=0.004]), total PANSS (mean change: − 9.2 versus − 3.1 [p=0.0002]), PANSS positive subscale (− 3.2 versus − 1.5 [p=0.003]), PANSS general subscale (− 4.3 versus − 1.2 [p=0.02]), and Marder factor for negative symptoms (− 1.9 versus 0.0 [p=0.03]). Most HCPs found the dashboard easy to use (74%) and helpful for improving conversations with participants about their treatment plan and progress (78%). Conclusion: This provider dashboard may facilitate discussions with patients about regular medication-taking, which can improve patient outcomes.
- Open Access
- 6 April 2021
- Published by Springer Nature in npj Digital Medicine
- Vol. 4 (1) , 1-7
Characterization of activity behavior using a digital medicine system and comparison to medication ingestion in patients with serious mental illness
Activity patterns can be important indicators in patients with serious mental illness. Here, we utilized an accelerometer and electrocardiogram incorporated within a digital medicine system, which also provides objective medication ingestion records, to explore markers of patient activity and investigate whether these markers of behavioral change are related to medication adherence. We developed an activity rhythm score to measure the consistency of step count patterns across the treatment regimen and explored the intensity of activity during active intervals. We then compared these activity features to ingestion behavior, both on a daily basis, using daily features and single-day ingestion behavior, and at the patient-level, using aggregate features and overall ingestion rates. Higher values of the single-day features for both the activity rhythm and activity intensity scores were associated with higher rates of ingestion on the following day. Patients with a mean activity rhythm score greater than the patient-level median were also shown to have higher overall ingestion rates than patients with lower activity rhythm scores (p = 0.004). These initial insights demonstrate the ability of digital medicine to enable the development of digital behavioral markers that can be compared to previously unavailable objective ingestion information to improve medication adherence.
- 6 April 2021
- Published by Springer Nature in npj Digital Medicine
- Vol. 4 (1) , 1-7
Open AccessCharacterization of activity behavior using a digital medicine system and comparison to medication ingestion in patients with serious mental illness
Activity patterns can be important indicators in patients with serious mental illness. Here, we utilized an accelerometer and electrocardiogram incorporated within a digital medicine system, which also provides objective medication ingestion records, to explore markers of patient activity and investigate whether these markers of behavioral change are related to medication adherence. We developed an activity rhythm score to measure the consistency of step count patterns across the treatment regimen and explored the intensity of activity during active intervals. We then compared these activity features to ingestion behavior, both on a daily basis, using daily features and single-day ingestion behavior, and at the patient-level, using aggregate features and overall ingestion rates. Higher values of the single-day features for both the activity rhythm and activity intensity scores were associated with higher rates of ingestion on the following day. Patients with a mean activity rhythm score greater than the patient-level median were also shown to have higher overall ingestion rates than patients with lower activity rhythm scores (p = 0.004). These initial insights demonstrate the ability of digital medicine to enable the development of digital behavioral markers that can be compared to previously unavailable objective ingestion information to improve medication adherence.
- Open Access
- 2 March 2021
- Published by JMIR Publications Inc. in JMIR Formative Research
- Vol. 5 (3) , e17993
A Rest Quality Metric Using a Cluster-Based Analysis of Accelerometer Data and Correlation With Digital Medicine Ingestion Data: Algorithm Development
Background: Adherence to medication regimens and patient rest are two important factors in the well-being of patients with serious mental illness. Both of these behaviors are traditionally difficult to record objectively in unsupervised populations. Objective: A digital medicine system that provides objective time-stamped medication ingestion records was used by patients with serious mental illness. Accelerometer data from the digital medicine system was used to assess rest quality and thus allow for investigation into correlations between rest and medication ingestion. Methods: Longest daily rest periods were identified and then evaluated using a k-means clustering algorithm and distance metric to quantify the relative quality of patient rest during these periods. This accelerometer-derived quality-of-rest metric, along with other accepted metrics of rest quality, such as duration and start time of the longest rest periods, was compared to the objective medication ingestion records. Overall medication adherence classification based on rest features was not performed due to a lack of patients with poor adherence in the sample population. Results: Explorations of the relationship between these rest metrics and ingestion did seem to indicate that patients with poor adherence experienced relatively low quality of rest; however, patients with better adherence did not necessarily exhibit consistent rest quality. This sample did not contain sufficient patients with poor adherence to draw more robust correlations between rest quality and ingestion behavior. The correlation of temporal outliers in these rest metrics with daily outliers in ingestion time was also explored. Conclusions: This result demonstrates the ability of digital medicine systems to quantify patient rest quality, providing a framework for further work to expand the participant population, compare these rest metrics to gold-standard sleep measurements, and correlate these digital medicine biomarkers with objective medication ingestion data.
- 2 March 2021
- Published by JMIR Publications Inc. in JMIR Formative Research
- Vol. 5 (3) , e17993
Open AccessA Rest Quality Metric Using a Cluster-Based Analysis of Accelerometer Data and Correlation With Digital Medicine Ingestion Data: Algorithm Development
Background: Adherence to medication regimens and patient rest are two important factors in the well-being of patients with serious mental illness. Both of these behaviors are traditionally difficult to record objectively in unsupervised populations. Objective: A digital medicine system that provides objective time-stamped medication ingestion records was used by patients with serious mental illness. Accelerometer data from the digital medicine system was used to assess rest quality and thus allow for investigation into correlations between rest and medication ingestion. Methods: Longest daily rest periods were identified and then evaluated using a k-means clustering algorithm and distance metric to quantify the relative quality of patient rest during these periods. This accelerometer-derived quality-of-rest metric, along with other accepted metrics of rest quality, such as duration and start time of the longest rest periods, was compared to the objective medication ingestion records. Overall medication adherence classification based on rest features was not performed due to a lack of patients with poor adherence in the sample population. Results: Explorations of the relationship between these rest metrics and ingestion did seem to indicate that patients with poor adherence experienced relatively low quality of rest; however, patients with better adherence did not necessarily exhibit consistent rest quality. This sample did not contain sufficient patients with poor adherence to draw more robust correlations between rest quality and ingestion behavior. The correlation of temporal outliers in these rest metrics with daily outliers in ingestion time was also explored. Conclusions: This result demonstrates the ability of digital medicine systems to quantify patient rest quality, providing a framework for further work to expand the participant population, compare these rest metrics to gold-standard sleep measurements, and correlate these digital medicine biomarkers with objective medication ingestion data.
- Open Access
- 23 February 2021
- Published by SPIE-Intl Soc Optical Eng in Journal of Biomedical Optics
- Vol. 26 (02) , 026004-15
Breast cancer differential diagnosis using diffuse optical spectroscopic imaging and regression with z-score normalized data
In standard clinical practice, breast lesions are imaged using x-ray mammography and ultrasound;1 this requires the differentiation of suspicious lesions from surrounding healthy tissue. Additional diagnostic imaging and/or invasive biopsies are then performed to determine whether the suspicious lesion is malignant or benign.1 Thereafter, treatment plans for patients with malignant carcinomas are developed. Unfortunately, although x-ray mammography has very high sensitivity to breast tumors, it has relatively low specificity,2 which produces a high false positive rate, i.e., across all ages,3 with higher rates in younger patients.4 Moreover, ultrasound imaging is also susceptible to this high false positive rate,5 which prompts more than 500,000 unnecessary negative biopsies per year5,6 and can lead to excessive cost3,7 and stress for patients.8 Additionally, women with radiographically dense breasts, who may be at increased risk for breast cancer,9,10 are more difficult to image with mammography, leading to even higher false positive rates.11 Functional information can help distinguish benign lesions from the more metabolically active malignant tumors. Indeed, more functional information about the lesions could improve the high false positive rate of x-ray mammography. Thus, other imaging modalities such as positron emission tomography (PET) or magnetic resonance imaging (MRI) can augment the diagnostic ability of mammography, albeit with logistical constraints such as ionizing radiation, cost, and low throughput.- 23 February 2021
- Published by SPIE-Intl Soc Optical Eng in Journal of Biomedical Optics
- Vol. 26 (02) , 026004-15
Open AccessBreast cancer differential diagnosis using diffuse optical spectroscopic imaging and regression with z-score normalized data
In standard clinical practice, breast lesions are imaged using x-ray mammography and ultrasound;1 this requires the differentiation of suspicious lesions from surrounding healthy tissue. Additional diagnostic imaging and/or invasive biopsies are then performed to determine whether the suspicious lesion is malignant or benign.1 Thereafter, treatment plans for patients with malignant carcinomas are developed. Unfortunately, although x-ray mammography has very high sensitivity to breast tumors, it has relatively low specificity,2 which produces a high false positive rate, i.e., across all ages,3 with higher rates in younger patients.4 Moreover, ultrasound imaging is also susceptible to this high false positive rate,5 which prompts more than 500,000 unnecessary negative biopsies per year5,6 and can lead to excessive cost3,7 and stress for patients.8 Additionally, women with radiographically dense breasts, who may be at increased risk for breast cancer,9,10 are more difficult to image with mammography, leading to even higher false positive rates.11 Functional information can help distinguish benign lesions from the more metabolically active malignant tumors. Indeed, more functional information about the lesions could improve the high false positive rate of x-ray mammography. Thus, other imaging modalities such as positron emission tomography (PET) or magnetic resonance imaging (MRI) can augment the diagnostic ability of mammography, albeit with logistical constraints such as ionizing radiation, cost, and low throughput. - Open Access
- 10 September 2020
- Published by JMIR Publications Inc. in JMIR Mental Health
- Vol. 7 (9) , e21378
Detection of Behavioral Anomalies in Medication Adherence Patterns Among Patients With Serious Mental Illness Engaged With a Digital Medicine System
Background: Adherence to medication is often represented in the form of a success percentage over a period of time. Although noticeable changes to aggregate adherence levels may be indicative of unstable medication behavior, a lack of noticeable changes in aggregate levels over time does not necessarily indicate stability. The ability to detect developing changes in medication-taking behavior under such conditions in real time would allow patients and care teams to make more timely and informed decisions. Objective: This study aims to develop a method capable of identifying shifts in behavioral (medication) patterns at the individual level and subsequently assess the presence of such shifts in retrospective clinical trial data from patients with serious mental illness. Methods: We defined the term adherence volatility as “the degree to which medication ingestion behavior fits expected behavior based on historically observed data” and defined a contextual anomaly system around this concept, leveraging the empirical entropy rate of a stochastic process as the basis for formulating anomaly detection. For the presented methodology, each patient’s evolving behavior is used to dynamically construct the expectation bounds for each future interval, eliminating the need to rely on model training or a static reference sequence. Results: Simulations demonstrated that the presented methodology identifies anomalous behavior patterns even when aggregate adherence levels remain constant and highlight the temporal dependence inherent in these anomalies. Although a given sequence of events may present as anomalous during one period, that sequence should subsequently contribute to future expectations and may not be considered anomalous at a later period—this feature was demonstrated in retrospective clinical trial data. In the same clinical trial data, anomalous behavioral shifts were identified at both high- and low-adherence levels and were spread across the whole treatment regimen, with 77.1% (81/105) of the population demonstrating at least one behavioral anomaly at some point in their treatment. Conclusions: Digital medicine systems offer new opportunities to inform treatment decisions and provide complementary information about medication adherence. This paper introduces the concept of adherence volatility and develops a new type of contextual anomaly detection, which does not require an a priori definition of normal and allows expectations to evolve with shifting behavior, removing the need to rely on training data or static reference sequences. Retrospective analysis from clinical trial data highlights that such an approach could provide new opportunities to meaningfully engage patients about potential shifts in their ingestion behavior; however, this framework is not intended to replace clinical judgment, rather to highlight elements of data that warrant attention. The evidence provided here identifies new areas for research and seems to justify additional explorations in this area.
- 10 September 2020
- Published by JMIR Publications Inc. in JMIR Mental Health
- Vol. 7 (9) , e21378
Open AccessDetection of Behavioral Anomalies in Medication Adherence Patterns Among Patients With Serious Mental Illness Engaged With a Digital Medicine System
Background: Adherence to medication is often represented in the form of a success percentage over a period of time. Although noticeable changes to aggregate adherence levels may be indicative of unstable medication behavior, a lack of noticeable changes in aggregate levels over time does not necessarily indicate stability. The ability to detect developing changes in medication-taking behavior under such conditions in real time would allow patients and care teams to make more timely and informed decisions. Objective: This study aims to develop a method capable of identifying shifts in behavioral (medication) patterns at the individual level and subsequently assess the presence of such shifts in retrospective clinical trial data from patients with serious mental illness. Methods: We defined the term adherence volatility as “the degree to which medication ingestion behavior fits expected behavior based on historically observed data” and defined a contextual anomaly system around this concept, leveraging the empirical entropy rate of a stochastic process as the basis for formulating anomaly detection. For the presented methodology, each patient’s evolving behavior is used to dynamically construct the expectation bounds for each future interval, eliminating the need to rely on model training or a static reference sequence. Results: Simulations demonstrated that the presented methodology identifies anomalous behavior patterns even when aggregate adherence levels remain constant and highlight the temporal dependence inherent in these anomalies. Although a given sequence of events may present as anomalous during one period, that sequence should subsequently contribute to future expectations and may not be considered anomalous at a later period—this feature was demonstrated in retrospective clinical trial data. In the same clinical trial data, anomalous behavioral shifts were identified at both high- and low-adherence levels and were spread across the whole treatment regimen, with 77.1% (81/105) of the population demonstrating at least one behavioral anomaly at some point in their treatment. Conclusions: Digital medicine systems offer new opportunities to inform treatment decisions and provide complementary information about medication adherence. This paper introduces the concept of adherence volatility and develops a new type of contextual anomaly detection, which does not require an a priori definition of normal and allows expectations to evolve with shifting behavior, removing the need to rely on training data or static reference sequences. Retrospective analysis from clinical trial data highlights that such an approach could provide new opportunities to meaningfully engage patients about potential shifts in their ingestion behavior; however, this framework is not intended to replace clinical judgment, rather to highlight elements of data that warrant attention. The evidence provided here identifies new areas for research and seems to justify additional explorations in this area.
- Open Access
- 12 June 2020
- Published by JMIR Publications Inc. in JMIR Preprints
Detection of Behavioral Anomalies in Medication Adherence Patterns Among Patients With Serious Mental Illness Engaged With a Digital Medicine System (Preprint)
BACKGROUND Adherence to medication is often represented in the form of a success percentage over a period of time. Although noticeable changes to aggregate adherence levels may be indicative of unstable medication behavior, a lack of noticeable changes in aggregate levels over time does not necessarily indicate stability. The ability to detect developing changes in medication-taking behavior under such conditions in real time would allow patients and care teams to make more timely and informed decisions. OBJECTIVE This study aims to develop a method capable of identifying shifts in behavioral (medication) patterns at the individual level and subsequently assess the presence of such shifts in retrospective clinical trial data from patients with serious mental illness. METHODS We defined the term adherence volatility as “the degree to which medication ingestion behavior fits expected behavior based on historically observed data” and defined a contextual anomaly system around this concept, leveraging the empirical entropy rate of a stochastic process as the basis for formulating anomaly detection. For the presented methodology, each patient’s evolving behavior is used to dynamically construct the expectation bounds for each future interval, eliminating the need to rely on model training or a static reference sequence. RESULTS Simulations demonstrated that the presented methodology identifies anomalous behavior patterns even when aggregate adherence levels remain constant and highlight the temporal dependence inherent in these anomalies. Although a given sequence of events may present as anomalous during one period, that sequence should subsequently contribute to future expectations and may not be considered anomalous at a later period—this feature was demonstrated in retrospective clinical trial data. In the same clinical trial data, anomalous behavioral shifts were identified at both high- and low-adherence levels and were spread across the whole treatment regimen, with 77.1% (81/105) of the population demonstrating at least one behavioral anomaly at some point in their treatment. CONCLUSIONS Digital medicine systems offer new opportunities to inform treatment decisions and provide complementary information about medication adherence. This paper introduces the concept of adherence volatility and develops a new type of contextual anomaly detection, which does not require an a priori definition of normal and allows expectations to evolve with shifting behavior, removing the need to rely on training data or static reference sequences. Retrospective analysis from clinical trial data highlights that such an approach could provide new opportunities to meaningfully engage patients about potential shifts in their ingestion behavior; however, this framework is not intended to replace clinical judgment, rather to highlight elements of data that warrant attention. The evidence provided here identifies new areas for research and seems to justify additional explorations in this area.
- 12 June 2020
- Published by JMIR Publications Inc. in JMIR Preprints
Open AccessDetection of Behavioral Anomalies in Medication Adherence Patterns Among Patients With Serious Mental Illness Engaged With a Digital Medicine System (Preprint)
BACKGROUND Adherence to medication is often represented in the form of a success percentage over a period of time. Although noticeable changes to aggregate adherence levels may be indicative of unstable medication behavior, a lack of noticeable changes in aggregate levels over time does not necessarily indicate stability. The ability to detect developing changes in medication-taking behavior under such conditions in real time would allow patients and care teams to make more timely and informed decisions. OBJECTIVE This study aims to develop a method capable of identifying shifts in behavioral (medication) patterns at the individual level and subsequently assess the presence of such shifts in retrospective clinical trial data from patients with serious mental illness. METHODS We defined the term adherence volatility as “the degree to which medication ingestion behavior fits expected behavior based on historically observed data” and defined a contextual anomaly system around this concept, leveraging the empirical entropy rate of a stochastic process as the basis for formulating anomaly detection. For the presented methodology, each patient’s evolving behavior is used to dynamically construct the expectation bounds for each future interval, eliminating the need to rely on model training or a static reference sequence. RESULTS Simulations demonstrated that the presented methodology identifies anomalous behavior patterns even when aggregate adherence levels remain constant and highlight the temporal dependence inherent in these anomalies. Although a given sequence of events may present as anomalous during one period, that sequence should subsequently contribute to future expectations and may not be considered anomalous at a later period—this feature was demonstrated in retrospective clinical trial data. In the same clinical trial data, anomalous behavioral shifts were identified at both high- and low-adherence levels and were spread across the whole treatment regimen, with 77.1% (81/105) of the population demonstrating at least one behavioral anomaly at some point in their treatment. CONCLUSIONS Digital medicine systems offer new opportunities to inform treatment decisions and provide complementary information about medication adherence. This paper introduces the concept of adherence volatility and develops a new type of contextual anomaly detection, which does not require an a priori definition of normal and allows expectations to evolve with shifting behavior, removing the need to rely on training data or static reference sequences. Retrospective analysis from clinical trial data highlights that such an approach could provide new opportunities to meaningfully engage patients about potential shifts in their ingestion behavior; however, this framework is not intended to replace clinical judgment, rather to highlight elements of data that warrant attention. The evidence provided here identifies new areas for research and seems to justify additional explorations in this area.