Chia-Cheng Lee
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
Research Subjects
Research Interests
Chia-Cheng Lee has a total of 54 co-authors. Here are the top co-authors by number of shared publications:
- Chin Lin
School of Medicine, National Defense Medical Center, Taipei, Taiwan
6 shared publications - Yu-Sheng Lou
Graduate Institutes of Life Sciences, National Defense Medical Center , No.161, Min-Chun E. Rd., Sec. 6, Neihu, Taipei 114, Taiwan , Republic of China
6 shared publications - Chia-Jung Hsu
Planning and Management Office, Tri-Service General Hospital, National Defense Medical Center, Taipei, Taiwan
5 shared publications - Wen-Hui Fang
Digital Medical Center, Tri-Service General Hospital, National Defense Medical University, Taipei, Taiwan, ROC
4 shared publications - Chao-Wen Chen
Division of Trauma and Surgical Critical Care, Department of Surgery, Kaohsiung Medical University Hospital, Kaohsiung Medical University, Kaohsiung City, Taiwan, ROC
3 shared publications - Chi-Ming Chu
College of Public Health National Defense Medical University Taipei City Taiwan
3 shared publications
Latest Publications
- Open Access
- 22 November 2022
- Published byĀ Oxford University Press (OUP)Ā inĀ European Heart Journal - Digital Health
- Vol.Ā 4 Ā (1) , 22-32
Development and validation of a dynamic deep learning algorithm using electrocardiogram to predict dyskalaemias in patients with multiple visits
Deep learning models (DLM) have shown superiority in electrocardiogram (ECG) analysis and have been applied to diagnose dyskalemias. However, no study has explored the performance of DLM-enabled ECG in continuous follow-up scenarios. Therefore, we proposed a dynamic revision of DLM-enabled ECG to use personal preannotated ECGs to enhance the accuracy in patients with multiple visits. We retrospectively collected 168,450 ECGs with corresponding serum potassium (K+) levels from 103,091 patients as development samples. In the internal/external validation sets, the numbers of ECGs with corresponding K+ were 37,246/47,604 from 13,555/20,058 patients. Our dynamic revision method showed better performance than the traditional direct prediction for diagnosing hypokalemia (AUC = 0.730/0.720 to 0.788/0.778) and hyperkalemia (AUC = 0.884/0.888 to 0.915/0.908) in patients with multiple visits. Our method has showed a distinguished improvement of DLM for diagnosing dyskalemias in patients with multiple visits, and we also proved its application in ejection fraction prediction, which could further improve daily clinical practice.
- 22 November 2022
- Published byĀ Oxford University Press (OUP)Ā inĀ European Heart Journal - Digital Health
- Vol.Ā 4 Ā (1) , 22-32
Open AccessDevelopment and validation of a dynamic deep learning algorithm using electrocardiogram to predict dyskalaemias in patients with multiple visits
Deep learning models (DLM) have shown superiority in electrocardiogram (ECG) analysis and have been applied to diagnose dyskalemias. However, no study has explored the performance of DLM-enabled ECG in continuous follow-up scenarios. Therefore, we proposed a dynamic revision of DLM-enabled ECG to use personal preannotated ECGs to enhance the accuracy in patients with multiple visits. We retrospectively collected 168,450 ECGs with corresponding serum potassium (K+) levels from 103,091 patients as development samples. In the internal/external validation sets, the numbers of ECGs with corresponding K+ were 37,246/47,604 from 13,555/20,058 patients. Our dynamic revision method showed better performance than the traditional direct prediction for diagnosing hypokalemia (AUC = 0.730/0.720 to 0.788/0.778) and hyperkalemia (AUC = 0.884/0.888 to 0.915/0.908) in patients with multiple visits. Our method has showed a distinguished improvement of DLM for diagnosing dyskalemias in patients with multiple visits, and we also proved its application in ejection fraction prediction, which could further improve daily clinical practice.
- Open Access
- 22 March 2022
- Published byĀ JMIR Publications Inc.Ā inĀ JMIR Serious Games
- Vol.Ā 10 Ā (1) , e35040
Effect of the Nintendo Ring Fit Adventure Exergame on Running Completion Time and Psychological Factors Among University Students Engaging in Distance Learning During the COVID-19 Pandemic: Randomized Controlled Trial
Background: The COVID-19 outbreak has not only changed the lifestyles of people globally but has also resulted in other challenges, such as the requirement of self-isolation and distance learning. Moreover, people are unable to venture out to exercise, leading to reduced movement, and therefore, the demand for exercise at home has increased. Objective: We intended to investigate the relationships between a Nintendo Ring Fit Adventure (RFA) intervention and improvements in running time, cardiac force index (CFI), sleep quality (Chinese version of the Pittsburgh Sleep Quality Index score), and mood disorders (5-item Brief Symptom Rating Scale score). Methods: This was a randomized prospective study and included 80 students who were required to complete a 1600-meter outdoor run before and after the intervention, the completion times of which were recorded in seconds. They were also required to fill out a lifestyle questionnaire. During the study, 40 participants (16 males and 24 females, with an average age of 23.75 years) were assigned to the RFA group and were required to exercise for 30 minutes 3 times per week (in the adventure mode) over 4 weeks. The exercise intensity was set according to the instructions given by the virtual coach during the first game. The remaining 40 participants (30 males and 10 females, with an average age of 22.65 years) were assigned to the control group and maintained their regular habits during the study period. Results: The study was completed by 80 participants aged 20 to 36 years (mean 23.20, SD 2.96 years). The results showed that the running time in the RFA group was significantly reduced. After 4 weeks of physical training, it took females in the RFA group 19.79 seconds (P=.03) and males 22.56 seconds (P=.03) less than the baseline to complete the 1600-meter run. In contrast, there were no significant differences in the performance of the control group in the run before and after the fourth week of intervention. In terms of mood disorders, the average score of the RFA group increased from 1.81 to 3.31 for males (difference=1.50, P=.04) and from 3.17 to 4.54 for females (difference=1.38, P=.06). In addition, no significant differences between the RFA and control groups were observed for the CFI peak acceleration (CFIPA)_walk, CFIPA_run, or sleep quality. Conclusions: RFA could either maintain or improve an individualās physical fitness, thereby providing a good solution for people involved in distance learning or those who have not exercised for an extended period. Trial Registration: ClinicalTrials.gov NCT05227040; https://clinicaltrials.gov/ct2/show/NCT05227040
- 22 March 2022
- Published byĀ JMIR Publications Inc.Ā inĀ JMIR Serious Games
- Vol.Ā 10 Ā (1) , e35040
Open AccessEffect of the Nintendo Ring Fit Adventure Exergame on Running Completion Time and Psychological Factors Among University Students Engaging in Distance Learning During the COVID-19 Pandemic: Randomized Controlled Trial
Background: The COVID-19 outbreak has not only changed the lifestyles of people globally but has also resulted in other challenges, such as the requirement of self-isolation and distance learning. Moreover, people are unable to venture out to exercise, leading to reduced movement, and therefore, the demand for exercise at home has increased. Objective: We intended to investigate the relationships between a Nintendo Ring Fit Adventure (RFA) intervention and improvements in running time, cardiac force index (CFI), sleep quality (Chinese version of the Pittsburgh Sleep Quality Index score), and mood disorders (5-item Brief Symptom Rating Scale score). Methods: This was a randomized prospective study and included 80 students who were required to complete a 1600-meter outdoor run before and after the intervention, the completion times of which were recorded in seconds. They were also required to fill out a lifestyle questionnaire. During the study, 40 participants (16 males and 24 females, with an average age of 23.75 years) were assigned to the RFA group and were required to exercise for 30 minutes 3 times per week (in the adventure mode) over 4 weeks. The exercise intensity was set according to the instructions given by the virtual coach during the first game. The remaining 40 participants (30 males and 10 females, with an average age of 22.65 years) were assigned to the control group and maintained their regular habits during the study period. Results: The study was completed by 80 participants aged 20 to 36 years (mean 23.20, SD 2.96 years). The results showed that the running time in the RFA group was significantly reduced. After 4 weeks of physical training, it took females in the RFA group 19.79 seconds (P=.03) and males 22.56 seconds (P=.03) less than the baseline to complete the 1600-meter run. In contrast, there were no significant differences in the performance of the control group in the run before and after the fourth week of intervention. In terms of mood disorders, the average score of the RFA group increased from 1.81 to 3.31 for males (difference=1.50, P=.04) and from 3.17 to 4.54 for females (difference=1.38, P=.06). In addition, no significant differences between the RFA and control groups were observed for the CFI peak acceleration (CFIPA)_walk, CFIPA_run, or sleep quality. Conclusions: RFA could either maintain or improve an individualās physical fitness, thereby providing a good solution for people involved in distance learning or those who have not exercised for an extended period. Trial Registration: ClinicalTrials.gov NCT05227040; https://clinicaltrials.gov/ct2/show/NCT05227040
- 15 February 2022
- Published byĀ Springer NatureĀ inĀ European Journal of Trauma and Emergency Surgery
- Vol.Ā 48 Ā (4) , 3317-3326
A deep learning-based system capable of detecting pneumothorax via electrocardiogram
Purpose To determine if an electrocardiogram-based artificial intelligence system can identify pneumothorax prior to radiological examination. Methods This is a single-center, retrospective, electrocardiogram-based artificial intelligence (AI) system study that included 107 ECGs from 98 pneumothorax patients. Seven patients received needle decompression due to tension pneumothorax, and the others received thoracostomy due to instability (respiratory rate ā„ 24 breaths/min; heart rate, < 60 beats/min or > 120 beats/min; hypotension; room air O2 saturation, < 90%; and patient could not speak in whole sentences between breaths). Traumatic pneumothorax and bilateral pneumothorax were excluded. The ECGs of 132,127 patients presenting to the emergency department without pneumothorax were used as the control group. The development cohort included approximately 80% of the ECGs for training the deep learning model (DLM), and the other 20% of ECGs were used to validate the performance. A humanāmachine competition involving three physicians was conducted to assess the model performance. Results The areas under the receiver operating characteristic (ROC) curves (AUCs) of the DLM in the validation cohort and competition set were 0.947 and 0.957, respectively. The sensitivity and specificity of our DLM were 94.7% and 88.1% in the validation cohort, respectively, which were significantly higher than those of all physicians. Our DLM could also recognize the location of pneumothorax with 100% accuracy. Lead-specific analysis showed that lead I ECG made a major contribution, achieving an AUC of 0.930 (94.7% sensitivity, 86.0% specificity). The inclusion of the patient characteristics allowed our AI system to achieve an AUC of 0.994. Conclusion The present AI system may assist the medical system in the early identification of pneumothorax through 12-lead ECG, and it performs as well with lead I ECG alone as with 12-lead ECG.
- 15 February 2022
- Published byĀ Springer NatureĀ inĀ European Journal of Trauma and Emergency Surgery
- Vol.Ā 48 Ā (4) , 3317-3326
A deep learning-based system capable of detecting pneumothorax via electrocardiogram
Purpose To determine if an electrocardiogram-based artificial intelligence system can identify pneumothorax prior to radiological examination. Methods This is a single-center, retrospective, electrocardiogram-based artificial intelligence (AI) system study that included 107 ECGs from 98 pneumothorax patients. Seven patients received needle decompression due to tension pneumothorax, and the others received thoracostomy due to instability (respiratory rate ā„ 24 breaths/min; heart rate, < 60 beats/min or > 120 beats/min; hypotension; room air O2 saturation, < 90%; and patient could not speak in whole sentences between breaths). Traumatic pneumothorax and bilateral pneumothorax were excluded. The ECGs of 132,127 patients presenting to the emergency department without pneumothorax were used as the control group. The development cohort included approximately 80% of the ECGs for training the deep learning model (DLM), and the other 20% of ECGs were used to validate the performance. A humanāmachine competition involving three physicians was conducted to assess the model performance. Results The areas under the receiver operating characteristic (ROC) curves (AUCs) of the DLM in the validation cohort and competition set were 0.947 and 0.957, respectively. The sensitivity and specificity of our DLM were 94.7% and 88.1% in the validation cohort, respectively, which were significantly higher than those of all physicians. Our DLM could also recognize the location of pneumothorax with 100% accuracy. Lead-specific analysis showed that lead I ECG made a major contribution, achieving an AUC of 0.930 (94.7% sensitivity, 86.0% specificity). The inclusion of the patient characteristics allowed our AI system to achieve an AUC of 0.994. Conclusion The present AI system may assist the medical system in the early identification of pneumothorax through 12-lead ECG, and it performs as well with lead I ECG alone as with 12-lead ECG.
- Open Access
- 29 June 2021
- Published byĀ The Endocrine SocietyĀ inĀ Journal of the Endocrine Society
- Vol.Ā 5 Ā (9) , bvab120
Artificial IntelligenceāAssisted Electrocardiography for Early Diagnosis of Thyrotoxic Periodic Paralysis
Context Thyrotoxic periodic paralysis (TPP) characterized by acute weakness, hypokalemia, and hyperthyroidism is a medical emergency with a great challenge in early diagnosis since most TPP patients do not have overt symptoms. Objective This work aims to assess artificial intelligence (AI)-assisted electrocardiography (ECG) combined with routine laboratory data in the early diagnosis of TPP. Methods A deep learning model (DLM) based on ECG12Net, an 82-layer convolutional neural network, was constructed to detect hypokalemia and hyperthyroidism. The development cohort consisted of 39 ECGs from patients with TPP and 502 ECGs of hypokalemic controls; the validation cohort consisted of 11 ECGs of TPP patients and 36 ECGs of non-TPP individuals with weakness. The AI-ECGābased TPP diagnostic process was then consecutively evaluated in 22 male patients with TTP-like features. Results In the validation cohort, the DLM-based ECG system detected all cases of hypokalemia in TPP patients with a mean absolute error of 0.26 mEq/L and diagnosed TPP with an area under curve (AUC) of approximately 80%, surpassing the best standard ECG parameter (AUC = 0.7285 for the QR interval). Combining the AI predictions with the estimated glomerular filtration rate and serum chloride boosted the diagnostic accuracy of the algorithm to AUC 0.986. In the prospective study, the integrated AI and routine laboratory diagnostic system had a PPV of 100% and F-measure of 87.5%. Conclusion An AI-ECG system reliably identifies hypokalemia in patients with paralysis, and integration with routine blood chemistries provides valuable decision support for the early diagnosis of TPP.
- 29 June 2021
- Published byĀ The Endocrine SocietyĀ inĀ Journal of the Endocrine Society
- Vol.Ā 5 Ā (9) , bvab120
Open AccessArtificial IntelligenceāAssisted Electrocardiography for Early Diagnosis of Thyrotoxic Periodic Paralysis
Context Thyrotoxic periodic paralysis (TPP) characterized by acute weakness, hypokalemia, and hyperthyroidism is a medical emergency with a great challenge in early diagnosis since most TPP patients do not have overt symptoms. Objective This work aims to assess artificial intelligence (AI)-assisted electrocardiography (ECG) combined with routine laboratory data in the early diagnosis of TPP. Methods A deep learning model (DLM) based on ECG12Net, an 82-layer convolutional neural network, was constructed to detect hypokalemia and hyperthyroidism. The development cohort consisted of 39 ECGs from patients with TPP and 502 ECGs of hypokalemic controls; the validation cohort consisted of 11 ECGs of TPP patients and 36 ECGs of non-TPP individuals with weakness. The AI-ECGābased TPP diagnostic process was then consecutively evaluated in 22 male patients with TTP-like features. Results In the validation cohort, the DLM-based ECG system detected all cases of hypokalemia in TPP patients with a mean absolute error of 0.26 mEq/L and diagnosed TPP with an area under curve (AUC) of approximately 80%, surpassing the best standard ECG parameter (AUC = 0.7285 for the QR interval). Combining the AI predictions with the estimated glomerular filtration rate and serum chloride boosted the diagnostic accuracy of the algorithm to AUC 0.986. In the prospective study, the integrated AI and routine laboratory diagnostic system had a PPV of 100% and F-measure of 87.5%. Conclusion An AI-ECG system reliably identifies hypokalemia in patients with paralysis, and integration with routine blood chemistries provides valuable decision support for the early diagnosis of TPP.
- Open Access
- 21 April 2021
- Published byĀ JMIR Publications Inc.Ā inĀ Journal of Medical Internet Research
- Vol.Ā 23 Ā (4) , e27069
A Technology Acceptance Model for Deploying Masks to Combat the COVID-19 Pandemic in Taiwan (My Health Bank): Web-Based Cross-sectional Survey Study
Background: The successful completion of medical practices often relies on information collection and analysis. Government agencies and medical institutions have encouraged people to use medical information technology (MIT) to manage their conditions and promote personal health. In 2014, Taiwan established the first electronic personal health record (PHR) platform, My Health Bank (MHB), which allows people to access and manage their PHRs at any time. In the face of the COVID-19 pandemic in 2020, Taiwan has used MIT to effectively prevent the spread of COVID-19 and undertaken various prevention measures before the onset of the outbreak. Using MHB to purchase masks in an efficient and orderly way and thoroughly implementing personal protection efforts is highly important to contain disease spread. Objective: This study aims to understand peopleās intention to use the electronic PHR platform MHB and to investigate the factors affecting their intention to use this platform. Methods: From March 31 to April 9, 2014, in a promotion via email and Facebook, participants were asked to fill out a structured questionnaire after watching an introductory video about MHB on YouTube. The questionnaire included seven dimensions: perceived usefulness, perceived ease of use, health literacy, privacy and security, computer self-efficacy, attitude toward use, and behavioral intention to use. Each question was measured on a 5-point Likert scale ranging from āstrongly disagreeā (1 point) to āstrongly agreeā (5 points). Descriptive statistics and structural equation analysis were performed using SPSS 21 and AMOS 21 software. Results: A total of 350 valid questionnaire responses were collected (female: 219/350, 62.6%; age: 21-30 years: 238/350, 68.0%; university-level education: 228/350, 65.1%; occupation as student: 195/350, 56.6%; average monthly income <NT $30,000 [<US $1054.89]: 230/350, 65.7%; residence in northern Taiwan: 236/350, 67.4%; and health status perceived as āgoodā: 171/350, 48.9%). Five indicators, including chi-square test (X2310=2.63), goodness-of-fit index (0.85), adjusted goodness-of-fit index (0.81), comparative fit index (0.91), and root mean square error of approximation (0.07), were calculated. The results indicated a good fit. Further analysis indicated that the most important factor affecting respondentsā behavioral intention to use MHB was their attitude toward use (0.78), followed by perceived ease of use (0.65), perceived usefulness (0.41), health literacy (0.10), and privacy and security (0.07). Conclusions: From the perspective of the populace, this study explored the factors affecting the use of MHB and constructed an interpretation model with a strong goodness of fit. The results of our analysis are consistent with the technology acceptance model. Through the diverse value-added services of MHB, Taiwan's experience in pandemic prevention with smart technology can facilitate future responses to unknown, emerging infectious diseases.
- 21 April 2021
- Published byĀ JMIR Publications Inc.Ā inĀ Journal of Medical Internet Research
- Vol.Ā 23 Ā (4) , e27069
Open AccessA Technology Acceptance Model for Deploying Masks to Combat the COVID-19 Pandemic in Taiwan (My Health Bank): Web-Based Cross-sectional Survey Study
Background: The successful completion of medical practices often relies on information collection and analysis. Government agencies and medical institutions have encouraged people to use medical information technology (MIT) to manage their conditions and promote personal health. In 2014, Taiwan established the first electronic personal health record (PHR) platform, My Health Bank (MHB), which allows people to access and manage their PHRs at any time. In the face of the COVID-19 pandemic in 2020, Taiwan has used MIT to effectively prevent the spread of COVID-19 and undertaken various prevention measures before the onset of the outbreak. Using MHB to purchase masks in an efficient and orderly way and thoroughly implementing personal protection efforts is highly important to contain disease spread. Objective: This study aims to understand peopleās intention to use the electronic PHR platform MHB and to investigate the factors affecting their intention to use this platform. Methods: From March 31 to April 9, 2014, in a promotion via email and Facebook, participants were asked to fill out a structured questionnaire after watching an introductory video about MHB on YouTube. The questionnaire included seven dimensions: perceived usefulness, perceived ease of use, health literacy, privacy and security, computer self-efficacy, attitude toward use, and behavioral intention to use. Each question was measured on a 5-point Likert scale ranging from āstrongly disagreeā (1 point) to āstrongly agreeā (5 points). Descriptive statistics and structural equation analysis were performed using SPSS 21 and AMOS 21 software. Results: A total of 350 valid questionnaire responses were collected (female: 219/350, 62.6%; age: 21-30 years: 238/350, 68.0%; university-level education: 228/350, 65.1%; occupation as student: 195/350, 56.6%; average monthly income <NT $30,000 [<US $1054.89]: 230/350, 65.7%; residence in northern Taiwan: 236/350, 67.4%; and health status perceived as āgoodā: 171/350, 48.9%). Five indicators, including chi-square test (X2310=2.63), goodness-of-fit index (0.85), adjusted goodness-of-fit index (0.81), comparative fit index (0.91), and root mean square error of approximation (0.07), were calculated. The results indicated a good fit. Further analysis indicated that the most important factor affecting respondentsā behavioral intention to use MHB was their attitude toward use (0.78), followed by perceived ease of use (0.65), perceived usefulness (0.41), health literacy (0.10), and privacy and security (0.07). Conclusions: From the perspective of the populace, this study explored the factors affecting the use of MHB and constructed an interpretation model with a strong goodness of fit. The results of our analysis are consistent with the technology acceptance model. Through the diverse value-added services of MHB, Taiwan's experience in pandemic prevention with smart technology can facilitate future responses to unknown, emerging infectious diseases.
- Open Access
- 18 January 2021
- Published byĀ JMIR Publications Inc.Ā inĀ JMIR Preprints
A Technology Acceptance Model for Deploying Masks to Combat the COVID-19 Pandemic in Taiwan (My Health Bank): Web-Based Cross-sectional Survey Study (Preprint)
BACKGROUND The successful completion of medical practices often relies on information collection and analysis. Government agencies and medical institutions have encouraged people to use medical information technology (MIT) to manage their conditions and promote personal health. In 2014, Taiwan established the first electronic personal health record (PHR) platform, My Health Bank (MHB), which allows people to access and manage their PHRs at any time. In the face of the COVID-19 pandemic in 2020, Taiwan has used MIT to effectively prevent the spread of COVID-19 and undertaken various prevention measures before the onset of the outbreak. Using MHB to purchase masks in an efficient and orderly way and thoroughly implementing personal protection efforts is highly important to contain disease spread. OBJECTIVE This study aims to understand peopleās intention to use the electronic PHR platform MHB and to investigate the factors affecting their intention to use this platform. METHODS From March 31 to April 9, 2014, in a promotion via email and Facebook, participants were asked to fill out a structured questionnaire after watching an introductory video about MHB on YouTube. The questionnaire included seven dimensions: perceived usefulness, perceived ease of use, health literacy, privacy and security, computer self-efficacy, attitude toward use, and behavioral intention to use. Each question was measured on a 5-point Likert scale ranging from āstrongly disagreeā (1 point) to āstrongly agreeā (5 points). Descriptive statistics and structural equation analysis were performed using SPSS 21 and AMOS 21 software. RESULTS A total of 350 valid questionnaire responses were collected (female: 219/350, 62.6%; age: 21-30 years: 238/350, 68.0%; university-level education: 228/350, 65.1%; occupation as student: 195/350, 56.6%; average monthly income <NT $30,000 [<US $1054.89]: 230/350, 65.7%; residence in northern Taiwan: 236/350, 67.4%; and health status perceived as āgoodā: 171/350, 48.9%). Five indicators, including chi-square test (X2310=2.63), goodness-of-fit index (0.85), adjusted goodness-of-fit index (0.81), comparative fit index (0.91), and root mean square error of approximation (0.07), were calculated. The results indicated a good fit. Further analysis indicated that the most important factor affecting respondentsā behavioral intention to use MHB was their attitude toward use (0.78), followed by perceived ease of use (0.65), perceived usefulness (0.41), health literacy (0.10), and privacy and security (0.07). CONCLUSIONS From the perspective of the populace, this study explored the factors affecting the use of MHB and constructed an interpretation model with a strong goodness of fit. The results of our analysis are consistent with the technology acceptance model. Through the diverse value-added services of MHB, Taiwan's experience in pandemic prevention with smart technology can facilitate future responses to unknown, emerging infectious diseases.
- 18 January 2021
- Published byĀ JMIR Publications Inc.Ā inĀ JMIR Preprints
Open AccessA Technology Acceptance Model for Deploying Masks to Combat the COVID-19 Pandemic in Taiwan (My Health Bank): Web-Based Cross-sectional Survey Study (Preprint)
BACKGROUND The successful completion of medical practices often relies on information collection and analysis. Government agencies and medical institutions have encouraged people to use medical information technology (MIT) to manage their conditions and promote personal health. In 2014, Taiwan established the first electronic personal health record (PHR) platform, My Health Bank (MHB), which allows people to access and manage their PHRs at any time. In the face of the COVID-19 pandemic in 2020, Taiwan has used MIT to effectively prevent the spread of COVID-19 and undertaken various prevention measures before the onset of the outbreak. Using MHB to purchase masks in an efficient and orderly way and thoroughly implementing personal protection efforts is highly important to contain disease spread. OBJECTIVE This study aims to understand peopleās intention to use the electronic PHR platform MHB and to investigate the factors affecting their intention to use this platform. METHODS From March 31 to April 9, 2014, in a promotion via email and Facebook, participants were asked to fill out a structured questionnaire after watching an introductory video about MHB on YouTube. The questionnaire included seven dimensions: perceived usefulness, perceived ease of use, health literacy, privacy and security, computer self-efficacy, attitude toward use, and behavioral intention to use. Each question was measured on a 5-point Likert scale ranging from āstrongly disagreeā (1 point) to āstrongly agreeā (5 points). Descriptive statistics and structural equation analysis were performed using SPSS 21 and AMOS 21 software. RESULTS A total of 350 valid questionnaire responses were collected (female: 219/350, 62.6%; age: 21-30 years: 238/350, 68.0%; university-level education: 228/350, 65.1%; occupation as student: 195/350, 56.6%; average monthly income <NT $30,000 [<US $1054.89]: 230/350, 65.7%; residence in northern Taiwan: 236/350, 67.4%; and health status perceived as āgoodā: 171/350, 48.9%). Five indicators, including chi-square test (X2310=2.63), goodness-of-fit index (0.85), adjusted goodness-of-fit index (0.81), comparative fit index (0.91), and root mean square error of approximation (0.07), were calculated. The results indicated a good fit. Further analysis indicated that the most important factor affecting respondentsā behavioral intention to use MHB was their attitude toward use (0.78), followed by perceived ease of use (0.65), perceived usefulness (0.41), health literacy (0.10), and privacy and security (0.07). CONCLUSIONS From the perspective of the populace, this study explored the factors affecting the use of MHB and constructed an interpretation model with a strong goodness of fit. The results of our analysis are consistent with the technology acceptance model. Through the diverse value-added services of MHB, Taiwan's experience in pandemic prevention with smart technology can facilitate future responses to unknown, emerging infectious diseases.
- Open Access
- 23 July 2019
- Published byĀ JMIR Publications Inc.Ā inĀ JMIR Medical Informatics
- Vol.Ā 7 Ā (3) , e14499
Projection Word Embedding Model With Hybrid Sampling Training for Classifying ICD-10-CM Codes: Longitudinal Observational Study
Journal of Medical Internet Research - International Scientific Journal for Medical Research, Information and Communication on the Internet #Preprint #PeerReviewMe: Warning: This is a unreviewed preprint. Readers are warned that the document has not been peer-reviewed by expert/patient reviewers or an academic editor, may contain misleading claims, and is likely to undergo changes before final publication, if accepted, or may have been rejected/withdrawn. Readers with interest and expertise are encouraged to sign up as peer-reviewer, if the paper is within an open peer-review period. Please cite this preprint only for review purposes or for grant applications and CVs (if you are the author). Background: Most current state-of-the-art algorithms for searching International Classification of Diseases, Tenth Revision, Clinical Modification (ICD-10-CM) codes use word embedding technology to capture useful semantic properties. However, they are limited by the quality of initial word embeddings. Word embedding trained by electronic health records (EHRs) is considered to be the best, but the vocabulary diversity is limited by previous medical records. Thus, we require a word embedding model that maintains the vocabulary diversity of open Internet databases and the medical terminology understanding of EHRs. Moreover, we need to consider the particularity of the disease classification that discharge notes present only positive disease descriptions. Objective: We propose a projection word2vec model and a hybrid sampling method and conduct a series of experiments to validate their effectiveness. Methods: We compared the projection word2vec model and traditional word2vec model using two corpora sources: English Wikipedia and PubMed journal abstracts. We used seven published datasets to measure the medical semantic understanding of the above word2vec models, and used them to identify the three-chapter-level ICD-10-CM diagnostic codes in a set of discharge notes. On the basis of embedding technology improvement, we also tried to apply the hybrid sampling method to improve accuracy. The 94,483 labeled discharge notes from the Tri-Service General Hospital of Taipei, Taiwan from June 1, 2015 to June 30, 2017 were used. To evaluate the model performance, 24,762 discharge notes from July 1, 2017 to December 31, 2017 from the same hospital were used. Moreover, 74,324 additional discharge notes collected from seven other hospitals were tested. The F-measure, which is the major global measure of effectiveness, was adopted. Results: In medical semantic understanding, the original EHR embeddings and PubMed embeddings exhibited superior performance to the original Wikipedia embeddings. After projection training technology was applied, the projection Wikipedia embeddings exhibited an obvious improvement but did not reach the level of original EHR embeddings or PubMed embeddings. In the subsequent ICD-10-CM coding experiment, the model that used both projection PubMed and Wikipedia embeddings had the highest testing mean F-measure (0.7362 and 0.6693 in Tri-Service General Hospital and the seven other hospitals, respectively). Moreover, the hybrid sampling method was found to improve the model performance (F-measure = 0.7371/0.6698). Conclusions: The word embeddings trained using EHR and PubMed could understand medical semantics better, and the proposed projection word2vec model improved the ability of medical semantics extraction in Wikipedia embeddings. Although the improvement from the projection word2vec model in the real ICD-10-CM coding task was not substantial, the algorithms can effectively handle emerging diseases. The proposed hybrid sampling method enables the algorithm to behave more like a human expert.
- 23 July 2019
- Published byĀ JMIR Publications Inc.Ā inĀ JMIR Medical Informatics
- Vol.Ā 7 Ā (3) , e14499
Open AccessProjection Word Embedding Model With Hybrid Sampling Training for Classifying ICD-10-CM Codes: Longitudinal Observational Study
Journal of Medical Internet Research - International Scientific Journal for Medical Research, Information and Communication on the Internet #Preprint #PeerReviewMe: Warning: This is a unreviewed preprint. Readers are warned that the document has not been peer-reviewed by expert/patient reviewers or an academic editor, may contain misleading claims, and is likely to undergo changes before final publication, if accepted, or may have been rejected/withdrawn. Readers with interest and expertise are encouraged to sign up as peer-reviewer, if the paper is within an open peer-review period. Please cite this preprint only for review purposes or for grant applications and CVs (if you are the author). Background: Most current state-of-the-art algorithms for searching International Classification of Diseases, Tenth Revision, Clinical Modification (ICD-10-CM) codes use word embedding technology to capture useful semantic properties. However, they are limited by the quality of initial word embeddings. Word embedding trained by electronic health records (EHRs) is considered to be the best, but the vocabulary diversity is limited by previous medical records. Thus, we require a word embedding model that maintains the vocabulary diversity of open Internet databases and the medical terminology understanding of EHRs. Moreover, we need to consider the particularity of the disease classification that discharge notes present only positive disease descriptions. Objective: We propose a projection word2vec model and a hybrid sampling method and conduct a series of experiments to validate their effectiveness. Methods: We compared the projection word2vec model and traditional word2vec model using two corpora sources: English Wikipedia and PubMed journal abstracts. We used seven published datasets to measure the medical semantic understanding of the above word2vec models, and used them to identify the three-chapter-level ICD-10-CM diagnostic codes in a set of discharge notes. On the basis of embedding technology improvement, we also tried to apply the hybrid sampling method to improve accuracy. The 94,483 labeled discharge notes from the Tri-Service General Hospital of Taipei, Taiwan from June 1, 2015 to June 30, 2017 were used. To evaluate the model performance, 24,762 discharge notes from July 1, 2017 to December 31, 2017 from the same hospital were used. Moreover, 74,324 additional discharge notes collected from seven other hospitals were tested. The F-measure, which is the major global measure of effectiveness, was adopted. Results: In medical semantic understanding, the original EHR embeddings and PubMed embeddings exhibited superior performance to the original Wikipedia embeddings. After projection training technology was applied, the projection Wikipedia embeddings exhibited an obvious improvement but did not reach the level of original EHR embeddings or PubMed embeddings. In the subsequent ICD-10-CM coding experiment, the model that used both projection PubMed and Wikipedia embeddings had the highest testing mean F-measure (0.7362 and 0.6693 in Tri-Service General Hospital and the seven other hospitals, respectively). Moreover, the hybrid sampling method was found to improve the model performance (F-measure = 0.7371/0.6698). Conclusions: The word embeddings trained using EHR and PubMed could understand medical semantics better, and the proposed projection word2vec model improved the ability of medical semantics extraction in Wikipedia embeddings. Although the improvement from the projection word2vec model in the real ICD-10-CM coding task was not substantial, the algorithms can effectively handle emerging diseases. The proposed hybrid sampling method enables the algorithm to behave more like a human expert.
- Open Access
- 26 April 2019
- Published byĀ JMIR Publications Inc.Ā inĀ JMIR Preprints
Projection Word Embedding Model With Hybrid Sampling Training for Classifying ICD-10-CM Codes: Longitudinal Observational Study (Preprint)
BACKGROUND Most current state-of-the-art models for searching the International Classification of Diseases, Tenth Revision Clinical Modification (ICD-10-CM) codes use word embedding technology to capture useful semantic properties. However, they are limited by the quality of initial word embeddings. Word embedding trained by electronic health records (EHRs) is considered the best, but the vocabulary diversity is limited by previous medical records. Thus, we require a word embedding model that maintains the vocabulary diversity of open internet databases and the medical terminology understanding of EHRs. Moreover, we need to consider the particularity of the disease classification, wherein discharge notes present only positive disease descriptions. OBJECTIVE We aimed to propose a projection word2vec model and a hybrid sampling method. In addition, we aimed to conduct a series of experiments to validate the effectiveness of these methods. METHODS We compared the projection word2vec model and traditional word2vec model using two corpora sources: English Wikipedia and PubMed journal abstracts. We used seven published datasets to measure the medical semantic understanding of the word2vec models and used these embeddings to identify the threeācharacter-level ICD-10-CM diagnostic codes in a set of discharge notes. On the basis of embedding technology improvement, we also tried to apply the hybrid sampling method to improve accuracy. The 94,483 labeled discharge notes from the Tri-Service General Hospital of Taipei, Taiwan, from June 1, 2015, to June 30, 2017, were used. To evaluate the model performance, 24,762 discharge notes from July 1, 2017, to December 31, 2017, from the same hospital were used. Moreover, 74,324 additional discharge notes collected from seven other hospitals were tested. The F-measure, which is the major global measure of effectiveness, was adopted. RESULTS In medical semantic understanding, the original EHR embeddings and PubMed embeddings exhibited superior performance to the original Wikipedia embeddings. After projection training technology was applied, the projection Wikipedia embeddings exhibited an obvious improvement but did not reach the level of original EHR embeddings or PubMed embeddings. In the subsequent ICD-10-CM coding experiment, the model that used both projection PubMed and Wikipedia embeddings had the highest testing mean F-measure (0.7362 and 0.6693 in Tri-Service General Hospital and the seven other hospitals, respectively). Moreover, the hybrid sampling method was found to improve the model performance (F-measure=0.7371/0.6698). CONCLUSIONS The word embeddings trained using EHR and PubMed could understand medical semantics better, and the proposed projection word2vec model improved the ability of medical semantics extraction in Wikipedia embeddings. Although the improvement from the projection word2vec model in the real ICD-10-CM coding task was not substantial, the models could effectively handle emerging diseases. The proposed hybrid sampling method enables the model to behave like a human expert.
- 26 April 2019
- Published byĀ JMIR Publications Inc.Ā inĀ JMIR Preprints
Open AccessProjection Word Embedding Model With Hybrid Sampling Training for Classifying ICD-10-CM Codes: Longitudinal Observational Study (Preprint)
BACKGROUND Most current state-of-the-art models for searching the International Classification of Diseases, Tenth Revision Clinical Modification (ICD-10-CM) codes use word embedding technology to capture useful semantic properties. However, they are limited by the quality of initial word embeddings. Word embedding trained by electronic health records (EHRs) is considered the best, but the vocabulary diversity is limited by previous medical records. Thus, we require a word embedding model that maintains the vocabulary diversity of open internet databases and the medical terminology understanding of EHRs. Moreover, we need to consider the particularity of the disease classification, wherein discharge notes present only positive disease descriptions. OBJECTIVE We aimed to propose a projection word2vec model and a hybrid sampling method. In addition, we aimed to conduct a series of experiments to validate the effectiveness of these methods. METHODS We compared the projection word2vec model and traditional word2vec model using two corpora sources: English Wikipedia and PubMed journal abstracts. We used seven published datasets to measure the medical semantic understanding of the word2vec models and used these embeddings to identify the threeācharacter-level ICD-10-CM diagnostic codes in a set of discharge notes. On the basis of embedding technology improvement, we also tried to apply the hybrid sampling method to improve accuracy. The 94,483 labeled discharge notes from the Tri-Service General Hospital of Taipei, Taiwan, from June 1, 2015, to June 30, 2017, were used. To evaluate the model performance, 24,762 discharge notes from July 1, 2017, to December 31, 2017, from the same hospital were used. Moreover, 74,324 additional discharge notes collected from seven other hospitals were tested. The F-measure, which is the major global measure of effectiveness, was adopted. RESULTS In medical semantic understanding, the original EHR embeddings and PubMed embeddings exhibited superior performance to the original Wikipedia embeddings. After projection training technology was applied, the projection Wikipedia embeddings exhibited an obvious improvement but did not reach the level of original EHR embeddings or PubMed embeddings. In the subsequent ICD-10-CM coding experiment, the model that used both projection PubMed and Wikipedia embeddings had the highest testing mean F-measure (0.7362 and 0.6693 in Tri-Service General Hospital and the seven other hospitals, respectively). Moreover, the hybrid sampling method was found to improve the model performance (F-measure=0.7371/0.6698). CONCLUSIONS The word embeddings trained using EHR and PubMed could understand medical semantics better, and the proposed projection word2vec model improved the ability of medical semantics extraction in Wikipedia embeddings. Although the improvement from the projection word2vec model in the real ICD-10-CM coding task was not substantial, the models could effectively handle emerging diseases. The proposed hybrid sampling method enables the model to behave like a human expert.
- Open Access
- 11 February 2019
- Published byĀ JMIR Publications Inc.Ā inĀ JMIR Preprints
ICD10Net: An Artificial Intelligence Algorithm with Medical Background Conducts ICD-10-CM Coding Task with Outstanding Performance (Preprint)
BACKGROUND An artificial intelligence-based algorithm has shown a powerful ability for coding the International Classification of Diseases, Tenth Revision, Clinical Modification (ICD-10-CM) in discharge notes. However, its performance still requires improvement compared with human experts. The major disadvantage of the previous algorithm is its lack of understanding medical terminologies. OBJECTIVE We propose some methods based on human-learning process and conduct a series of experiments to validate their improvements. METHODS We compared two data sources for training the word-embedding model: English Wikipedia and PubMed journal abstracts. Moreover, the fixed, changeable, and double-channel embedding tables were used to test their performance. Some additional tricks were also applied to improve accuracy. We used these methods to identify the three-chapter-level ICD-10-CM diagnosis codes in a set of discharge notes. Subsequently, 94,483-labeled discharge notes from June 1, 2015 to June 30, 2017 were used from the Tri-Service General Hospital in Taipei, Taiwan. To evaluate performance, 24,762 discharge notes from July 1, 2017 to December 31, 2017, from the same hospital were used. Moreover, 74,324 additional discharge notes collected from other seven hospitals were also tested. The F-measure is the major global measure of effectiveness. RESULTS In understanding medical terminologies, the PubMed-embedding model (Pearson correlation = 0.60/0.57) shows a better performance compared with the Wikipedia-embedding model (Pearson correlation = 0.35/0.31). In the accuracy of ICD-10-CM coding, the changeable model both used the PubMed- and Wikipedia-embedding model has the highest testing mean F-measure (0.7311 and 0.6639 in Tri-Service General Hospital and other seven hospitals, respectively). Moreover, a proposed method called a hybrid sampling method, an augmentation trick to avoid algorithms identifying negative terms, was found to additionally improve the model performance. CONCLUSIONS The proposed model architecture and training method is named as ICD10Net, which is the first expert level model practically applied to daily work. This model can also be applied in unstructured information extraction from free-text medical writing. We have developed a web app to demonstrate our work (https://linchin.ndmctsgh.edu.tw/app/ICD10/).
- 11 February 2019
- Published byĀ JMIR Publications Inc.Ā inĀ JMIR Preprints
Open AccessICD10Net: An Artificial Intelligence Algorithm with Medical Background Conducts ICD-10-CM Coding Task with Outstanding Performance (Preprint)
BACKGROUND An artificial intelligence-based algorithm has shown a powerful ability for coding the International Classification of Diseases, Tenth Revision, Clinical Modification (ICD-10-CM) in discharge notes. However, its performance still requires improvement compared with human experts. The major disadvantage of the previous algorithm is its lack of understanding medical terminologies. OBJECTIVE We propose some methods based on human-learning process and conduct a series of experiments to validate their improvements. METHODS We compared two data sources for training the word-embedding model: English Wikipedia and PubMed journal abstracts. Moreover, the fixed, changeable, and double-channel embedding tables were used to test their performance. Some additional tricks were also applied to improve accuracy. We used these methods to identify the three-chapter-level ICD-10-CM diagnosis codes in a set of discharge notes. Subsequently, 94,483-labeled discharge notes from June 1, 2015 to June 30, 2017 were used from the Tri-Service General Hospital in Taipei, Taiwan. To evaluate performance, 24,762 discharge notes from July 1, 2017 to December 31, 2017, from the same hospital were used. Moreover, 74,324 additional discharge notes collected from other seven hospitals were also tested. The F-measure is the major global measure of effectiveness. RESULTS In understanding medical terminologies, the PubMed-embedding model (Pearson correlation = 0.60/0.57) shows a better performance compared with the Wikipedia-embedding model (Pearson correlation = 0.35/0.31). In the accuracy of ICD-10-CM coding, the changeable model both used the PubMed- and Wikipedia-embedding model has the highest testing mean F-measure (0.7311 and 0.6639 in Tri-Service General Hospital and other seven hospitals, respectively). Moreover, a proposed method called a hybrid sampling method, an augmentation trick to avoid algorithms identifying negative terms, was found to additionally improve the model performance. CONCLUSIONS The proposed model architecture and training method is named as ICD10Net, which is the first expert level model practically applied to daily work. This model can also be applied in unstructured information extraction from free-text medical writing. We have developed a web app to demonstrate our work (https://linchin.ndmctsgh.edu.tw/app/ICD10/).
- Open Access
- 6 November 2017
- Published byĀ JMIR Publications Inc.Ā inĀ Journal of Medical Internet Research
- Vol.Ā 19 Ā (11) , e380
Artificial Intelligence Learning Semantics via External Resources for Classifying Diagnosis Codes in Discharge Notes
Journal of Medical Internet Research - International Scientific Journal for Medical Research, Information and Communication on the Internet
- 6 November 2017
- Published byĀ JMIR Publications Inc.Ā inĀ Journal of Medical Internet Research
- Vol.Ā 19 Ā (11) , e380
Open AccessArtificial Intelligence Learning Semantics via External Resources for Classifying Diagnosis Codes in Discharge Notes
Journal of Medical Internet Research - International Scientific Journal for Medical Research, Information and Communication on the Internet