Jane Y. Zhao
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Jane Y. Zhao has a total of 61 co-authors. Here are the top co-authors by number of shared publications:
- Buer Song
Department of Biomedical Informatics University at Buffalo Buffalo, NY United States
2 shared publications Casey E. Senter
2 shared publications- Christopher Crowner
Department of Biomedical Informatics University at Buffalo Buffalo, NY United States
2 shared publications - Daniel Schlegel
Department of Biomedical Informatics University at Buffalo Buffalo, NY United States
2 shared publications - Edwin Anand
Department of Biomedical Informatics University at Buffalo Buffalo, NY United States
2 shared publications - Gary Brady
Pfizer, Inc. New York, NY United States
2 shared publications
Latest Publications
- 10 July 2024
- Published by Elsevier in Clinical Lung Cancer
- Vol. 25 (7) , 595-600
Prehabilitation for Older Adults Undergoing Lung Cancer Surgery: A Literature Review and Needs Assessment
- 10 July 2024
- Published by Elsevier in Clinical Lung Cancer
- Vol. 25 (7) , 595-600
Prehabilitation for Older Adults Undergoing Lung Cancer Surgery: A Literature Review and Needs Assessment
- Open Access
- 18 January 2023
- Published by Elsevier in JTCVS Techniques
- Vol. 18, 171-173
Management of donor partial anomalous pulmonary veins during lung transplantation
- 18 January 2023
- Published by Elsevier in JTCVS Techniques
- Vol. 18, 171-173
Open AccessManagement of donor partial anomalous pulmonary veins during lung transplantation
- Open Access
- 1 April 2022
- Published by Annals of Family Medicine in The Annals of Family Medicine
- Vol. 20 (Supplement) , 3106
Using chart reviews to evaluate a Continuing Medical Education (CME) program
Context Moore’s Expanded Outcomes Framework is a 7 level framework commonly used to assess the outcomes of continuing medical education (CME) programs. Levels 1 to 5 are provider-level outcomes (participation, satisfaction, knowledge, competence, and performance) while levels 6 and 7 are patient- and community-level outcomes. Chart reviews are one method to assess level 5 (performance). ECHO Ontario Chronic Pain and Opioid Stewardship (“ECHO”) is a CME telementoring program that aims to increase capacity and access for primary care providers (PCPs) who manage patients with chronic pain. Objective This study uses chart reviews to evaluate ECHO’s impact on PCP performance and to discuss the feasibility of performing chart reviews for evaluation purposes as per Moore’s framework. Study Design Retrospective chart review Setting The practices of 12 primary care providers across Ontario who attended ECHO between June 2014 to August 2018. The inclusion criteria for PCPs was 1) attended a minimum of four ECHO sessions, and 2) clinic site must be approving of a site visit for chart reviews. Population Studied 47 patient charts were included. For each patient chart reviewed, PCPs were asked to choose patients in their practice on whom they had used ECHO-taught knowledge. Inclusion criteria for patients was 1) have chronic pain and be managed by the ECHO-participating PCP, 2) was prescribed opioids during the time frame of the study, and 3) not presented during ECHO sessions. Informed consent was obtained prior to each site visit. 1) Increased use of ECHO-taught pain and opioid management strategies 2) Feasibility of using chart reviews to evaluate PCP performance following a CME activity Results 25 (53%) patients were male and the average age was 59 (± 14) years. 24 (51%) patients had two or more pain diagnoses at baseline, with musculoskeletal pain being the most prevalent at 81%. 26 (55%) patients had comorbid mental health conditions and 13 (28%) had sleep disorders. Trends in results showed marginal, but non-significant, improvements in PCP performance after ECHO as indicated by increased use of pain and opioid management strategies. Conclusions Conducting chart reviews was a challenging method to assess provider performance. Future work to assess provider performance should include a qualitative component (in-depth interviews or focus groups) in order to complement the quantitative data and provide context for care and management decisions.
- 1 April 2022
- Published by Annals of Family Medicine in The Annals of Family Medicine
- Vol. 20 (Supplement) , 3106
Open AccessUsing chart reviews to evaluate a Continuing Medical Education (CME) program
Context Moore’s Expanded Outcomes Framework is a 7 level framework commonly used to assess the outcomes of continuing medical education (CME) programs. Levels 1 to 5 are provider-level outcomes (participation, satisfaction, knowledge, competence, and performance) while levels 6 and 7 are patient- and community-level outcomes. Chart reviews are one method to assess level 5 (performance). ECHO Ontario Chronic Pain and Opioid Stewardship (“ECHO”) is a CME telementoring program that aims to increase capacity and access for primary care providers (PCPs) who manage patients with chronic pain. Objective This study uses chart reviews to evaluate ECHO’s impact on PCP performance and to discuss the feasibility of performing chart reviews for evaluation purposes as per Moore’s framework. Study Design Retrospective chart review Setting The practices of 12 primary care providers across Ontario who attended ECHO between June 2014 to August 2018. The inclusion criteria for PCPs was 1) attended a minimum of four ECHO sessions, and 2) clinic site must be approving of a site visit for chart reviews. Population Studied 47 patient charts were included. For each patient chart reviewed, PCPs were asked to choose patients in their practice on whom they had used ECHO-taught knowledge. Inclusion criteria for patients was 1) have chronic pain and be managed by the ECHO-participating PCP, 2) was prescribed opioids during the time frame of the study, and 3) not presented during ECHO sessions. Informed consent was obtained prior to each site visit. 1) Increased use of ECHO-taught pain and opioid management strategies 2) Feasibility of using chart reviews to evaluate PCP performance following a CME activity Results 25 (53%) patients were male and the average age was 59 (± 14) years. 24 (51%) patients had two or more pain diagnoses at baseline, with musculoskeletal pain being the most prevalent at 81%. 26 (55%) patients had comorbid mental health conditions and 13 (28%) had sleep disorders. Trends in results showed marginal, but non-significant, improvements in PCP performance after ECHO as indicated by increased use of pain and opioid management strategies. Conclusions Conducting chart reviews was a challenging method to assess provider performance. Future work to assess provider performance should include a qualitative component (in-depth interviews or focus groups) in order to complement the quantitative data and provide context for care and management decisions.
- Open Access
- 1 April 2022
- Published by Annals of Family Medicine
- Vol. 20 (Supplement) , 3259
The complexity of rheumatology: Patient characteristics presented during a telemedicine education program, ECHO rheumatology
Context Rheumatoid Arthritis (RA) is a common, chronic, and complex disease that affects 1% of the population in Ontario, with a higher prevalence in First Nations populations at 3%. Timely and aggressive treatment of RA with disease-modifying antirheumatic drugs (DMARDs) can lead to effective management of symptoms. Left untreated, however, RA can lead to deformed joints, debilitating pain, and significantly reduced quality of life. ECHO Rheumatology (‘ECHO’) was a program developed to address the burden of RA and other rheumatic diseases in Ontario. ECHO began running weekly sessions in January 2017. Objective This study describes the patient characteristics and quality improvement (QI) initiatives in ECHO. Study Design A mixed methods study with a QI lens Setting ECHO (Extension for Community Healthcare Outcomes) is a collaborative model of medical education and care management, designed to increase capacity and access for care. In each weekly session, a healthcare provider (HCP) presents a patient case using a standardized patient case presentation form. Recommendations are then made from the interprofessional group and community. Population Studied Patient cases were summarized using the data extracted from HCPs’ weekly case presentation forms. QI opportunities were also identified from provider- and patient-level data. 1) Descriptive characteristics of patients presented and HCP participants 2) Differential diagnoses and recommendations following ECHO patient presentation Results From January 2017 to December 2019, ECHO provided 112 sessions with a total of 117 patient cases presented. 180 HCPs attended at least one session and 64 (36%) presented at least one case. At baseline, 63 (54%) of patients were female and mean age was 58 (range = 20-80). 24 (21%) patients had no diagnosis at baseline and 24 (21%) were on DMARDs. 27 (23%) were referred to a rheumatologist after presentation. Conclusions ECHO Ontario Rheumatology has gained uptake across Ontario. Patients presented at ECHO were complex, with multimorbidity, and reflected a mixture of classically inflammatory and mechanical pathologies mechanical pathologies, with relative prevalence reflecting the typical burden of rheumatologic and musculoskeletal diseases. Next steps in ECHO’s evaluation will address its impact on practice change through systematic follow up with participating health care providers, and on “real world” integration with preexisting models of care.
- 1 April 2022
- Published by Annals of Family Medicine
- Vol. 20 (Supplement) , 3259
Open AccessThe complexity of rheumatology: Patient characteristics presented during a telemedicine education program, ECHO rheumatology
Context Rheumatoid Arthritis (RA) is a common, chronic, and complex disease that affects 1% of the population in Ontario, with a higher prevalence in First Nations populations at 3%. Timely and aggressive treatment of RA with disease-modifying antirheumatic drugs (DMARDs) can lead to effective management of symptoms. Left untreated, however, RA can lead to deformed joints, debilitating pain, and significantly reduced quality of life. ECHO Rheumatology (‘ECHO’) was a program developed to address the burden of RA and other rheumatic diseases in Ontario. ECHO began running weekly sessions in January 2017. Objective This study describes the patient characteristics and quality improvement (QI) initiatives in ECHO. Study Design A mixed methods study with a QI lens Setting ECHO (Extension for Community Healthcare Outcomes) is a collaborative model of medical education and care management, designed to increase capacity and access for care. In each weekly session, a healthcare provider (HCP) presents a patient case using a standardized patient case presentation form. Recommendations are then made from the interprofessional group and community. Population Studied Patient cases were summarized using the data extracted from HCPs’ weekly case presentation forms. QI opportunities were also identified from provider- and patient-level data. 1) Descriptive characteristics of patients presented and HCP participants 2) Differential diagnoses and recommendations following ECHO patient presentation Results From January 2017 to December 2019, ECHO provided 112 sessions with a total of 117 patient cases presented. 180 HCPs attended at least one session and 64 (36%) presented at least one case. At baseline, 63 (54%) of patients were female and mean age was 58 (range = 20-80). 24 (21%) patients had no diagnosis at baseline and 24 (21%) were on DMARDs. 27 (23%) were referred to a rheumatologist after presentation. Conclusions ECHO Ontario Rheumatology has gained uptake across Ontario. Patients presented at ECHO were complex, with multimorbidity, and reflected a mixture of classically inflammatory and mechanical pathologies mechanical pathologies, with relative prevalence reflecting the typical burden of rheumatologic and musculoskeletal diseases. Next steps in ECHO’s evaluation will address its impact on practice change through systematic follow up with participating health care providers, and on “real world” integration with preexisting models of care.
- Open Access
- 9 November 2021
- Published by JMIR Publications Inc. in Journal of Medical Internet Research
- Vol. 23 (11) , e28946
Using Artificial Intelligence With Natural Language Processing to Combine Electronic Health Record’s Structured and Free Text Data to Identify Nonvalvular Atrial Fibrillation to Decrease Strokes and Death: Evaluation and Case-Control Study
Background: Nonvalvular atrial fibrillation (NVAF) affects almost 6 million Americans and is a major contributor to stroke but is significantly undiagnosed and undertreated despite explicit guidelines for oral anticoagulation. Objective: The aim of this study is to investigate whether the use of semisupervised natural language processing (NLP) of electronic health record’s (EHR) free-text information combined with structured EHR data improves NVAF discovery and treatment and perhaps offers a method to prevent thousands of deaths and save billions of dollars. Methods: We abstracted 96,681 participants from the University of Buffalo faculty practice’s EHR. NLP was used to index the notes and compare the ability to identify NVAF, congestive heart failure, hypertension, age ≥75 years, diabetes mellitus, stroke or transient ischemic attack, vascular disease, age 65 to 74 years, sex category (CHA2DS2-VASc), and Hypertension, Abnormal liver/renal function, Stroke history, Bleeding history or predisposition, Labile INR, Elderly, Drug/alcohol usage (HAS-BLED) scores using unstructured data (International Classification of Diseases codes) versus structured and unstructured data from clinical notes. In addition, we analyzed data from 63,296,120 participants in the Optum and Truven databases to determine the NVAF frequency, rates of CHA2DS2‑VASc ≥2, and no contraindications to oral anticoagulants, rates of stroke and death in the untreated population, and first year’s costs after stroke. Results: The structured-plus-unstructured method would have identified 3,976,056 additional true NVAF cases (P<.001) and improved sensitivity for CHA2DS2-VASc and HAS-BLED scores compared with the structured data alone (P=.002 and P<.001, respectively), causing a 32.1% improvement. For the United States, this method would prevent an estimated 176,537 strokes, save 10,575 lives, and save >US $13.5 billion. Conclusions: Artificial intelligence–informed bio-surveillance combining NLP of free-text information with structured EHR data improves data completeness, prevents thousands of strokes, and saves lives and funds. This method is applicable to many disorders with profound public health consequences.
- 9 November 2021
- Published by JMIR Publications Inc. in Journal of Medical Internet Research
- Vol. 23 (11) , e28946
Open AccessUsing Artificial Intelligence With Natural Language Processing to Combine Electronic Health Record’s Structured and Free Text Data to Identify Nonvalvular Atrial Fibrillation to Decrease Strokes and Death: Evaluation and Case-Control Study
Background: Nonvalvular atrial fibrillation (NVAF) affects almost 6 million Americans and is a major contributor to stroke but is significantly undiagnosed and undertreated despite explicit guidelines for oral anticoagulation. Objective: The aim of this study is to investigate whether the use of semisupervised natural language processing (NLP) of electronic health record’s (EHR) free-text information combined with structured EHR data improves NVAF discovery and treatment and perhaps offers a method to prevent thousands of deaths and save billions of dollars. Methods: We abstracted 96,681 participants from the University of Buffalo faculty practice’s EHR. NLP was used to index the notes and compare the ability to identify NVAF, congestive heart failure, hypertension, age ≥75 years, diabetes mellitus, stroke or transient ischemic attack, vascular disease, age 65 to 74 years, sex category (CHA2DS2-VASc), and Hypertension, Abnormal liver/renal function, Stroke history, Bleeding history or predisposition, Labile INR, Elderly, Drug/alcohol usage (HAS-BLED) scores using unstructured data (International Classification of Diseases codes) versus structured and unstructured data from clinical notes. In addition, we analyzed data from 63,296,120 participants in the Optum and Truven databases to determine the NVAF frequency, rates of CHA2DS2‑VASc ≥2, and no contraindications to oral anticoagulants, rates of stroke and death in the untreated population, and first year’s costs after stroke. Results: The structured-plus-unstructured method would have identified 3,976,056 additional true NVAF cases (P<.001) and improved sensitivity for CHA2DS2-VASc and HAS-BLED scores compared with the structured data alone (P=.002 and P<.001, respectively), causing a 32.1% improvement. For the United States, this method would prevent an estimated 176,537 strokes, save 10,575 lives, and save >US $13.5 billion. Conclusions: Artificial intelligence–informed bio-surveillance combining NLP of free-text information with structured EHR data improves data completeness, prevents thousands of strokes, and saves lives and funds. This method is applicable to many disorders with profound public health consequences.
- Open Access
- 19 March 2021
- Published by JMIR Publications Inc. in JMIR Preprints
Using Artificial Intelligence With Natural Language Processing to Combine Electronic Health Record’s Structured and Free Text Data to Identify Nonvalvular Atrial Fibrillation to Decrease Strokes and Death: Evaluation and Case-Control Study (Preprint)
BACKGROUND Nonvalvular atrial fibrillation (NVAF) affects almost 6 million Americans and is a major contributor to stroke but is significantly undiagnosed and undertreated despite explicit guidelines for oral anticoagulation. OBJECTIVE The aim of this study is to investigate whether the use of semisupervised natural language processing (NLP) of electronic health record’s (EHR) free-text information combined with structured EHR data improves NVAF discovery and treatment and perhaps offers a method to prevent thousands of deaths and save billions of dollars. METHODS We abstracted 96,681 participants from the University of Buffalo faculty practice’s EHR. NLP was used to index the notes and compare the ability to identify NVAF, congestive heart failure, hypertension, age ≥75 years, diabetes mellitus, stroke or transient ischemic attack, vascular disease, age 65 to 74 years, sex category (CHA2DS2-VASc), and Hypertension, Abnormal liver/renal function, Stroke history, Bleeding history or predisposition, Labile INR, Elderly, Drug/alcohol usage (HAS-BLED) scores using unstructured data (International Classification of Diseases codes) versus structured and unstructured data from clinical notes. In addition, we analyzed data from 63,296,120 participants in the Optum and Truven databases to determine the NVAF frequency, rates of CHA2DS2‑VASc ≥2, and no contraindications to oral anticoagulants, rates of stroke and death in the untreated population, and first year’s costs after stroke. RESULTS The structured-plus-unstructured method would have identified 3,976,056 additional true NVAF cases (P<.001) and improved sensitivity for CHA2DS2-VASc and HAS-BLED scores compared with the structured data alone (P=.002 and P<.001, respectively), causing a 32.1% improvement. For the United States, this method would prevent an estimated 176,537 strokes, save 10,575 lives, and save >US $13.5 billion. CONCLUSIONS Artificial intelligence–informed bio-surveillance combining NLP of free-text information with structured EHR data improves data completeness, prevents thousands of strokes, and saves lives and funds. This method is applicable to many disorders with profound public health consequences.
- 19 March 2021
- Published by JMIR Publications Inc. in JMIR Preprints
Open AccessUsing Artificial Intelligence With Natural Language Processing to Combine Electronic Health Record’s Structured and Free Text Data to Identify Nonvalvular Atrial Fibrillation to Decrease Strokes and Death: Evaluation and Case-Control Study (Preprint)
BACKGROUND Nonvalvular atrial fibrillation (NVAF) affects almost 6 million Americans and is a major contributor to stroke but is significantly undiagnosed and undertreated despite explicit guidelines for oral anticoagulation. OBJECTIVE The aim of this study is to investigate whether the use of semisupervised natural language processing (NLP) of electronic health record’s (EHR) free-text information combined with structured EHR data improves NVAF discovery and treatment and perhaps offers a method to prevent thousands of deaths and save billions of dollars. METHODS We abstracted 96,681 participants from the University of Buffalo faculty practice’s EHR. NLP was used to index the notes and compare the ability to identify NVAF, congestive heart failure, hypertension, age ≥75 years, diabetes mellitus, stroke or transient ischemic attack, vascular disease, age 65 to 74 years, sex category (CHA2DS2-VASc), and Hypertension, Abnormal liver/renal function, Stroke history, Bleeding history or predisposition, Labile INR, Elderly, Drug/alcohol usage (HAS-BLED) scores using unstructured data (International Classification of Diseases codes) versus structured and unstructured data from clinical notes. In addition, we analyzed data from 63,296,120 participants in the Optum and Truven databases to determine the NVAF frequency, rates of CHA2DS2‑VASc ≥2, and no contraindications to oral anticoagulants, rates of stroke and death in the untreated population, and first year’s costs after stroke. RESULTS The structured-plus-unstructured method would have identified 3,976,056 additional true NVAF cases (P<.001) and improved sensitivity for CHA2DS2-VASc and HAS-BLED scores compared with the structured data alone (P=.002 and P<.001, respectively), causing a 32.1% improvement. For the United States, this method would prevent an estimated 176,537 strokes, save 10,575 lives, and save >US $13.5 billion. CONCLUSIONS Artificial intelligence–informed bio-surveillance combining NLP of free-text information with structured EHR data improves data completeness, prevents thousands of strokes, and saves lives and funds. This method is applicable to many disorders with profound public health consequences.
- 1 August 2020
- Published by Elsevier in Journal of Surgical Research
- Vol. 252, 264-271
The Value of the Surgeon Informatician
- 1 August 2020
- Published by Elsevier in Journal of Surgical Research
- Vol. 252, 264-271
The Value of the Surgeon Informatician
- 1 October 2019
- Published by Elsevier in The American Journal of Surgery
- Vol. 218 (4) , 792-797
The surgical blog: An important supplement to traditional scientific literature
- 1 October 2019
- Published by Elsevier in The American Journal of Surgery
- Vol. 218 (4) , 792-797
The surgical blog: An important supplement to traditional scientific literature
- 1 March 2019
- Published by Elsevier in Journal of Surgical Education
- Vol. 76 (2) , 512-518
Interprofessional Communication Goes Up When the Electronic Health Record Goes Down
- 1 March 2019
- Published by Elsevier in Journal of Surgical Education
- Vol. 76 (2) , 512-518
Interprofessional Communication Goes Up When the Electronic Health Record Goes Down