Ofir Ben-Assuli | Ono Academic College (original) (raw)

Papers by Ofir Ben-Assuli

Future internet, Feb 26, 2024

International Journal of Medical Informatics, Jul 1, 2022

INTRODUCTION Diabetes is a chronic metabolic disease characterized by high levels of blood glucos... more INTRODUCTION Diabetes is a chronic metabolic disease characterized by high levels of blood glucose, which can lead over time to severe impairment to the heart, blood vessels, eyes, kidneys, nerves and premature death. Diabetes is prone to complications such as kidney failure, vision loss and nerve damage. The total assessed cost of diagnosed diabetes is growing rapidly; hence, harnessing telehealth for diabetes management may be cost-effective. A few previous publications have pointed to the effectiveness of telehealth but more numerous articles indicate that the results are inconsistent and economic models are lacking. This narrative review surveys the recent literature on the implementation of telehealth for diabetes management that incorporates cost-effectiveness analyses. MATERIALS AND METHODS This paper follows the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) [25]. RESULTS The vast majority of articles dealing with managing Type 2 diabetes have primarily used the telephone for telehealth monitoring (followed by teleophalmology and telemonitoring). Most publications report that the telehealth solution was cost effective. The leading cost-effectiveness method was the Markov model; however, only a small number of papers extend the Markov model to critical sensitivity analyses of their outcomes. The main goal of telehealth in general is diabetes management or monitoring, followed by ophthalmology, depression management, weight loss and other goals. CONCLUSION This work summarizes the literature on recent trends in telehealth options, and analyzes successes and failures in relation to both effectiveness and costs, which may be valuable to both scholars and practitioners.

Journal of Biomedical Informatics, 2022

Congestive Heart Failure (CHF) is among the most prevalent chronic diseases worldwide, and is com... more Congestive Heart Failure (CHF) is among the most prevalent chronic diseases worldwide, and is commonly associated with comorbidities and complex health conditions. Consequently, CHF patients are typically hospitalized frequently, and are at a high risk of premature death. Early detection of an envisaged patient disease trajectory is crucial for precision medicine. However, despite the abundance of patient-level data, cardiologists currently struggle to identify disease trajectories and track the evolution patterns of the disease over time, especially in small groups of patients with specific disease subtypes. The present study proposed a five-step method that allows clustering CHF patients, detecting cluster similarity, and identifying disease trajectories, and promises to overcome the existing difficulties. This work is based on a rich dataset of patients' records spanning ten years of hospital visits. The dataset contains all the health information documented in the hospital during each visit, including diagnoses, lab results, clinical data, and demographics. It utilizes an innovative Cluster Evolution Analysis (CEA) method to analyze the complex CHF population where each subject is potentially associated with numerous variables. We have defined sub-groups for mortality risk levels, which we used to characterize patients' disease evolution by refined data clustering in three points in time over ten years, and generating patients' migration patterns across periods. The results elicited 18, 23, and 25 clusters respective to the first, second, and third visits, uncovering clinically interesting small sub-groups of patients. In the following post-processing stage, we identified meaningful patterns. The analysis yielded fine-grained patient clusters divided into several finite risk levels, including several small-sized groups of high-risk patients. Significantly, the analysis also yielded longitudinal patterns where patients' risk levels changed over time. Four types of disease trajectories were identified: decline, preserved state, improvement, and mixed-progress. This stage is a unique contribution of the work. The resulting fine partitioning and longitudinal insights promise to significantly assist cardiologists in tailoring personalized interventions to improve care quality. Cardiologists could utilize these results to glean previously undetected relationships between symptoms and disease evolution that would allow a more informed clinical decision-making and effective interventions.

International Conference on Information Systems, 2018

Electronic health records (EHR) and health information exchange (HIE), are key capabilities to ad... more Electronic health records (EHR) and health information exchange (HIE), are key capabilities to address challenges facing the health care system. We aimed to understand the role that EHR and HIE data can play in reducing the probabilities of a patients™ r

International Conference on Information Systems, 2019

This study addresses the call to harness big data analytics for more accurate clinical decision m... more This study addresses the call to harness big data analytics for more accurate clinical decision making, and is rooted in the context of Congestive Heart Failure (CHF) patients. We aim at identifying CHF patients’ risk levels and disease transitions over time, and present here the clusters that emerged in three consecutive visits. The clusters are classified into five risk levels, based on the mortality rate 30, 90, 180, 365 days post discharge. The primary method was Cluster Evolution Analysis that is able to identify patients’ risk classification, cluster evolution and patients transition over time. The clustering was based on lab results, and we added comorbidities to define the cluster characteristics. A senior cardiologist evaluated the results and stated that the fine clustering allows more accurate identification of patients’ risk groups, likely to result in an improved clinical decision. For example, three high-risk clusters, identified in visit 1, included between 42 to 53 patients out of ~10,000, which could probably be overlooked otherwise. In the next stage, we will identify disease evolution and patient transition between clusters over time

Informatics for Health & Social Care, Jun 9, 2021

ABSTRACT Objective The objective of this paper is to provide empirical guidance by comparing the ... more ABSTRACT Objective The objective of this paper is to provide empirical guidance by comparing the performance of six different area-level SDoH measurement approaches in predicting patient referral to a social worker and hospital admission after a primary care visit. Methods We compared the performance of six area-level SDoH measurement approaches in predicting patient referral to a social worker and hospital admission after a primary care visit using random forest classification algorithm. Data came from 209,605 patient encounters at a federally qualified health center. Models with each area-based measurement approach were compared against the patient-level data only model using area under the curve, sensitivity, specificity, and precision. Results Addition of area-level features to patient-level data improved the overall performance of models predicting need for a social worker referral. Entering area-level measures as individual features resulted in highest model performance. Conclusion Researchers seeking to include area-level SDoH measures in risk prediction may be able to forego more complex measurement approaches.

Blood Pressure, Apr 15, 2015

Pre-hypertension (pHT) is frequently diagnosed in the primary care setting, but its management by... more Pre-hypertension (pHT) is frequently diagnosed in the primary care setting, but its management by primary care physicians (PCPs) is not well characterized. All individuals aged 30-45 years who were insured by Clalit Health services in the Tel Aviv district and had their blood pressure (BP) measured from January 2006 to December 2010 were evaluated. Individuals were divided into three groups based on their initial BP value: optimal (< 120/80 mmHg), normal (systolic BP 120-129 or diastolic 80-84 mmHg) and borderline (130-139/85-89 mmHg). Groups were compared regarding clinical and laboratory follow-up performed by their PCP. Of the 20,214 individuals included in the study, 6576 (32.5%) had values in the pHT range. Of these, 2126 (32.3% of those with pHT) had BP values defined as "borderline" and 4450 (67.6% of those with pHT) had BP values defined as "normal". The number of follow-up visits by the PCP and repeat BP measurement were similar in those with "optimal" BP and pHT. A third and fourth BP measurement were recorded more frequently in those with pHT. In those with pHT, there were more recorded BP measurements than in those with borderline BP (3.35 ± 3 vs 3.23 ± 2.6), but the time from the initial to the second measurement and a record of a third and fourth measurement were the same in the two groups. Identification of pHT does not lead to a significant change in follow-up by PCPs, irrespective of BP values in the pHT range.

Metabolites

The objectives of the research were to analyze the association between Body Mass Index (BMI) and ... more The objectives of the research were to analyze the association between Body Mass Index (BMI) and dental caries using novel approaches of both statistical and machine learning (ML) models while adjusting for cardiovascular risk factors and metabolic syndrome (MetS) components, consequences, and related conditions. This research is a data-driven analysis of the Dental, Oral, Medical Epidemiological (DOME) big data repository, that integrates comprehensive socio-demographic, medical, and dental databases of a nationwide sample of dental attendees to military dental clinics for 1 year aged 18–50 years. Obesity categories were defined according to the World Health Organization (WHO): under-weight: BMI < 18.5 kg/m2, normal weight: BMI 18.5 to 24.9 kg/m2, overweight: BMI 25 to 29.9 kg/m2, and obesity: BMI ≥ 30 kg/m2. General linear models were used with the mean number of decayed teeth as the dependent variable across BMI categories, adjusted for (1) socio-demographics, (2) health-relat...

Journal of Biomedical Informatics

Journal of Biomedical Informatics, 2022

Non-alcoholic fatty liver disease (NAFLD) affects 25% of the population worldwide, and its preval... more Non-alcoholic fatty liver disease (NAFLD) affects 25% of the population worldwide, and its prevalence is anticipated to increase globally. While most NAFLD patients are asymptomatic, NAFLD may progress to fibrosis, cirrhosis, cardiovascular disease, and diabetes. Research reports, with daunting results, show the challenge that NAFLD's burden causes to global population health. The current process for identifying fibrosis risk levels is inefficient, expensive, does not cover all potential populations, and does not identify the risk in time. Instead of invasive liver biopsies, we implemented a non-invasive fibrosis assessment process calculated from clinical data (accessed via EMRs/EHRs). We stratified patients' risks for fibrosis from 2007 to 2017 by modeling the risk in 5,579 individuals. The process involved time-series machine learning models (Hidden Markov Models and Group-Based Trajectory Models) profiled fibrosis risk by modeling patients' latent medical status resulted in three groups. The high-risk group had abnormal lab test values and a higher prevalence of chronic conditions. This study can help overcome the inefficient, traditional process of detecting fibrosis via biopsies (that are also medically unfeasible due to their invasive nature, the medical resources involved, and costs) at early stages. Thus longitudinal risk assessment may be used to make population-specific medical recommendations targeting early detection of high risk patients, to avoid the development of fibrosis disease and its complications as well as decrease healthcare costs.

Proceedings of the Annual Hawaii International Conference on System Sciences, 2022

Human-in-the-loop intelligence augmentation (IA) methods combined with visual analytics (VA) have... more Human-in-the-loop intelligence augmentation (IA) methods combined with visual analytics (VA) have the potential to provide additional functional capability and cognitively driven interpretability to Decision Support Systems (DSS) for health risk assessment and patient-clinician shared decision making. This paper presents some key ideas underlying the synthesis of IA with VA (IA/VA) and the challenges in the design, implementation, and use of IA/VA-enabled clinical decision support systems (CDSS) in the practice of medicine through data driven analytical models. An illustrative IA/VA solution provides a visualization of the distribution of health risk, and the impact of various parameters on the assessment, at the population and individual levels. It also allows the clinician to ask "what-if" questions using interactive visualizations that change actionable risk factors of the patient and visually assess their impact. This approach holds promise in enhancing decision support systems design, deployment and use outside the medical sphere as well.

Health Informatics Journal

Stratification modeling in health services is useful to identify differential patient risk groups... more Stratification modeling in health services is useful to identify differential patient risk groups, or latent classes. Given the frequency and costs, repeated emergency department (ED) may be an appropriate candidate for risk stratification modeling. We applied a method called group-based trajectory modeling (GBTM) to a sample of 37,416 patients who visited an urban, safety-net ED between 2006 and 2016. Patients had up to 10 ED visits during the study period. Data sources included the hospital’s electronic health record (EHR), the state-wide health information exchange system, and area-level social determinants of health factors. Results revealed three distinct trajectory groups. Trajectories with a higher risk of revisit were marked by more patients with behavioral diagnoses, injuries, alcohol & substance abuse, stroke, diabetes, and other factors. The application of advanced computational techniques, like GBTM, provides opportunities for health care organizations to better understa...

Information Systems Management

Health organizations are implementing health information technologies such as electronic health r... more Health organizations are implementing health information technologies such as electronic health records (EHR), information systems (IS), and health information exchange (HIE) networks to improve decision-making. However, over the years, the healthcare environment has demonstrated numerous unsuccessful implementations of such technologies. One of the reasons is that physicians tend not to make use of these technologies in the healthcare environment. The various explanations put forward typically refer to patient, physician, and/or work environment-related factors. This study evaluated the factors associated with the EHR use among physicians in the complex environment of emergency departments. We used log-files retrieved from an integrative and interoperable EHR that serves Israeli hospitals. We found that EHR was primarily consulted for patients presenting with internal diagnoses, patients of older age, and it was used more by internists than by surgical specialists. Furthermore, EHR usage was larger for admitted patients than for those discharged. The findings show factors associated with EHR use and suggest that it is mostly related to case-specific features and to physician specialty. The findings strongly suggest that when planning assimilation projects for EHR systems and HIE networks, attention should be paid to those factors associated with system usage. Specifically, in order to increase the efficiency of the system, and enhance its use in the ED environment, physicians' preferences and practice-related needs need to be taken into account. Furthermore, well-thought IT design and implementation are necessary to generate an increase in meaningful use of HIT, which can serve both physicians' and patients' needs.

This paper evaluates the contribution of an electronic health records (EHR) system to efficient d... more This paper evaluates the contribution of an electronic health records (EHR) system to efficient decision-making by physicians, and investigates whether these systems lead to more efficient medical care in emergency departments (ED). Log-files of patient visits and admissions were retrieved from an integrative EHR system that serves seven main hospitals owned by a large health maintenance organization (HMO). This study focused on readmissions within seven days and single-day admissions, problems that concern hospitals around the world. The findings indicate that using an EHR system in the EDs correlates with a decreased number of readmissions within seven days as well as with a reduced number of single-day admissions. The results provide evidence that using EHR system may contribute to efficiency in an ED by assisting decision-making. We believe this is the first data set that investigates the impact of an EHR on hospital efficiency at the scale of HMO.

Information Systems Management, 2020

Reducing costly hospital readmissions of patients with Congestive Heart Failure (CHF) is importan... more Reducing costly hospital readmissions of patients with Congestive Heart Failure (CHF) is important. We analyzed 4,661 CHF patients (from 2007 to 2017) using Hidden Markov Models in order to profile CHF readmission risk over time. This method proved practical in identifying three patient groups with distinctive characteristics, which might guide physicians in tailoring personalized care to prevent hospital readmission. We thus demonstrate how applying appropriate AI analytics can save costs and improve the quality of care.

The Journal of Alternative and Complementary Medicine, 2021

Future internet, Feb 26, 2024

International Journal of Medical Informatics, Jul 1, 2022

INTRODUCTION Diabetes is a chronic metabolic disease characterized by high levels of blood glucos... more INTRODUCTION Diabetes is a chronic metabolic disease characterized by high levels of blood glucose, which can lead over time to severe impairment to the heart, blood vessels, eyes, kidneys, nerves and premature death. Diabetes is prone to complications such as kidney failure, vision loss and nerve damage. The total assessed cost of diagnosed diabetes is growing rapidly; hence, harnessing telehealth for diabetes management may be cost-effective. A few previous publications have pointed to the effectiveness of telehealth but more numerous articles indicate that the results are inconsistent and economic models are lacking. This narrative review surveys the recent literature on the implementation of telehealth for diabetes management that incorporates cost-effectiveness analyses. MATERIALS AND METHODS This paper follows the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) [25]. RESULTS The vast majority of articles dealing with managing Type 2 diabetes have primarily used the telephone for telehealth monitoring (followed by teleophalmology and telemonitoring). Most publications report that the telehealth solution was cost effective. The leading cost-effectiveness method was the Markov model; however, only a small number of papers extend the Markov model to critical sensitivity analyses of their outcomes. The main goal of telehealth in general is diabetes management or monitoring, followed by ophthalmology, depression management, weight loss and other goals. CONCLUSION This work summarizes the literature on recent trends in telehealth options, and analyzes successes and failures in relation to both effectiveness and costs, which may be valuable to both scholars and practitioners.

Journal of Biomedical Informatics, 2022

Congestive Heart Failure (CHF) is among the most prevalent chronic diseases worldwide, and is com... more Congestive Heart Failure (CHF) is among the most prevalent chronic diseases worldwide, and is commonly associated with comorbidities and complex health conditions. Consequently, CHF patients are typically hospitalized frequently, and are at a high risk of premature death. Early detection of an envisaged patient disease trajectory is crucial for precision medicine. However, despite the abundance of patient-level data, cardiologists currently struggle to identify disease trajectories and track the evolution patterns of the disease over time, especially in small groups of patients with specific disease subtypes. The present study proposed a five-step method that allows clustering CHF patients, detecting cluster similarity, and identifying disease trajectories, and promises to overcome the existing difficulties. This work is based on a rich dataset of patients' records spanning ten years of hospital visits. The dataset contains all the health information documented in the hospital during each visit, including diagnoses, lab results, clinical data, and demographics. It utilizes an innovative Cluster Evolution Analysis (CEA) method to analyze the complex CHF population where each subject is potentially associated with numerous variables. We have defined sub-groups for mortality risk levels, which we used to characterize patients' disease evolution by refined data clustering in three points in time over ten years, and generating patients' migration patterns across periods. The results elicited 18, 23, and 25 clusters respective to the first, second, and third visits, uncovering clinically interesting small sub-groups of patients. In the following post-processing stage, we identified meaningful patterns. The analysis yielded fine-grained patient clusters divided into several finite risk levels, including several small-sized groups of high-risk patients. Significantly, the analysis also yielded longitudinal patterns where patients' risk levels changed over time. Four types of disease trajectories were identified: decline, preserved state, improvement, and mixed-progress. This stage is a unique contribution of the work. The resulting fine partitioning and longitudinal insights promise to significantly assist cardiologists in tailoring personalized interventions to improve care quality. Cardiologists could utilize these results to glean previously undetected relationships between symptoms and disease evolution that would allow a more informed clinical decision-making and effective interventions.

International Conference on Information Systems, 2018

Electronic health records (EHR) and health information exchange (HIE), are key capabilities to ad... more Electronic health records (EHR) and health information exchange (HIE), are key capabilities to address challenges facing the health care system. We aimed to understand the role that EHR and HIE data can play in reducing the probabilities of a patients™ r

International Conference on Information Systems, 2019

This study addresses the call to harness big data analytics for more accurate clinical decision m... more This study addresses the call to harness big data analytics for more accurate clinical decision making, and is rooted in the context of Congestive Heart Failure (CHF) patients. We aim at identifying CHF patients’ risk levels and disease transitions over time, and present here the clusters that emerged in three consecutive visits. The clusters are classified into five risk levels, based on the mortality rate 30, 90, 180, 365 days post discharge. The primary method was Cluster Evolution Analysis that is able to identify patients’ risk classification, cluster evolution and patients transition over time. The clustering was based on lab results, and we added comorbidities to define the cluster characteristics. A senior cardiologist evaluated the results and stated that the fine clustering allows more accurate identification of patients’ risk groups, likely to result in an improved clinical decision. For example, three high-risk clusters, identified in visit 1, included between 42 to 53 patients out of ~10,000, which could probably be overlooked otherwise. In the next stage, we will identify disease evolution and patient transition between clusters over time

Informatics for Health & Social Care, Jun 9, 2021

ABSTRACT Objective The objective of this paper is to provide empirical guidance by comparing the ... more ABSTRACT Objective The objective of this paper is to provide empirical guidance by comparing the performance of six different area-level SDoH measurement approaches in predicting patient referral to a social worker and hospital admission after a primary care visit. Methods We compared the performance of six area-level SDoH measurement approaches in predicting patient referral to a social worker and hospital admission after a primary care visit using random forest classification algorithm. Data came from 209,605 patient encounters at a federally qualified health center. Models with each area-based measurement approach were compared against the patient-level data only model using area under the curve, sensitivity, specificity, and precision. Results Addition of area-level features to patient-level data improved the overall performance of models predicting need for a social worker referral. Entering area-level measures as individual features resulted in highest model performance. Conclusion Researchers seeking to include area-level SDoH measures in risk prediction may be able to forego more complex measurement approaches.

Blood Pressure, Apr 15, 2015

Pre-hypertension (pHT) is frequently diagnosed in the primary care setting, but its management by... more Pre-hypertension (pHT) is frequently diagnosed in the primary care setting, but its management by primary care physicians (PCPs) is not well characterized. All individuals aged 30-45 years who were insured by Clalit Health services in the Tel Aviv district and had their blood pressure (BP) measured from January 2006 to December 2010 were evaluated. Individuals were divided into three groups based on their initial BP value: optimal (&amp;amp;amp;amp;lt; 120/80 mmHg), normal (systolic BP 120-129 or diastolic 80-84 mmHg) and borderline (130-139/85-89 mmHg). Groups were compared regarding clinical and laboratory follow-up performed by their PCP. Of the 20,214 individuals included in the study, 6576 (32.5%) had values in the pHT range. Of these, 2126 (32.3% of those with pHT) had BP values defined as &amp;amp;amp;amp;quot;borderline&amp;amp;amp;amp;quot; and 4450 (67.6% of those with pHT) had BP values defined as &amp;amp;amp;amp;quot;normal&amp;amp;amp;amp;quot;. The number of follow-up visits by the PCP and repeat BP measurement were similar in those with &amp;amp;amp;amp;quot;optimal&amp;amp;amp;amp;quot; BP and pHT. A third and fourth BP measurement were recorded more frequently in those with pHT. In those with pHT, there were more recorded BP measurements than in those with borderline BP (3.35 ± 3 vs 3.23 ± 2.6), but the time from the initial to the second measurement and a record of a third and fourth measurement were the same in the two groups. Identification of pHT does not lead to a significant change in follow-up by PCPs, irrespective of BP values in the pHT range.

Metabolites

The objectives of the research were to analyze the association between Body Mass Index (BMI) and ... more The objectives of the research were to analyze the association between Body Mass Index (BMI) and dental caries using novel approaches of both statistical and machine learning (ML) models while adjusting for cardiovascular risk factors and metabolic syndrome (MetS) components, consequences, and related conditions. This research is a data-driven analysis of the Dental, Oral, Medical Epidemiological (DOME) big data repository, that integrates comprehensive socio-demographic, medical, and dental databases of a nationwide sample of dental attendees to military dental clinics for 1 year aged 18–50 years. Obesity categories were defined according to the World Health Organization (WHO): under-weight: BMI < 18.5 kg/m2, normal weight: BMI 18.5 to 24.9 kg/m2, overweight: BMI 25 to 29.9 kg/m2, and obesity: BMI ≥ 30 kg/m2. General linear models were used with the mean number of decayed teeth as the dependent variable across BMI categories, adjusted for (1) socio-demographics, (2) health-relat...

Journal of Biomedical Informatics

Journal of Biomedical Informatics, 2022

Non-alcoholic fatty liver disease (NAFLD) affects 25% of the population worldwide, and its preval... more Non-alcoholic fatty liver disease (NAFLD) affects 25% of the population worldwide, and its prevalence is anticipated to increase globally. While most NAFLD patients are asymptomatic, NAFLD may progress to fibrosis, cirrhosis, cardiovascular disease, and diabetes. Research reports, with daunting results, show the challenge that NAFLD's burden causes to global population health. The current process for identifying fibrosis risk levels is inefficient, expensive, does not cover all potential populations, and does not identify the risk in time. Instead of invasive liver biopsies, we implemented a non-invasive fibrosis assessment process calculated from clinical data (accessed via EMRs/EHRs). We stratified patients' risks for fibrosis from 2007 to 2017 by modeling the risk in 5,579 individuals. The process involved time-series machine learning models (Hidden Markov Models and Group-Based Trajectory Models) profiled fibrosis risk by modeling patients' latent medical status resulted in three groups. The high-risk group had abnormal lab test values and a higher prevalence of chronic conditions. This study can help overcome the inefficient, traditional process of detecting fibrosis via biopsies (that are also medically unfeasible due to their invasive nature, the medical resources involved, and costs) at early stages. Thus longitudinal risk assessment may be used to make population-specific medical recommendations targeting early detection of high risk patients, to avoid the development of fibrosis disease and its complications as well as decrease healthcare costs.

Proceedings of the Annual Hawaii International Conference on System Sciences, 2022

Human-in-the-loop intelligence augmentation (IA) methods combined with visual analytics (VA) have... more Human-in-the-loop intelligence augmentation (IA) methods combined with visual analytics (VA) have the potential to provide additional functional capability and cognitively driven interpretability to Decision Support Systems (DSS) for health risk assessment and patient-clinician shared decision making. This paper presents some key ideas underlying the synthesis of IA with VA (IA/VA) and the challenges in the design, implementation, and use of IA/VA-enabled clinical decision support systems (CDSS) in the practice of medicine through data driven analytical models. An illustrative IA/VA solution provides a visualization of the distribution of health risk, and the impact of various parameters on the assessment, at the population and individual levels. It also allows the clinician to ask "what-if" questions using interactive visualizations that change actionable risk factors of the patient and visually assess their impact. This approach holds promise in enhancing decision support systems design, deployment and use outside the medical sphere as well.

Health Informatics Journal

Stratification modeling in health services is useful to identify differential patient risk groups... more Stratification modeling in health services is useful to identify differential patient risk groups, or latent classes. Given the frequency and costs, repeated emergency department (ED) may be an appropriate candidate for risk stratification modeling. We applied a method called group-based trajectory modeling (GBTM) to a sample of 37,416 patients who visited an urban, safety-net ED between 2006 and 2016. Patients had up to 10 ED visits during the study period. Data sources included the hospital’s electronic health record (EHR), the state-wide health information exchange system, and area-level social determinants of health factors. Results revealed three distinct trajectory groups. Trajectories with a higher risk of revisit were marked by more patients with behavioral diagnoses, injuries, alcohol & substance abuse, stroke, diabetes, and other factors. The application of advanced computational techniques, like GBTM, provides opportunities for health care organizations to better understa...

Information Systems Management

Health organizations are implementing health information technologies such as electronic health r... more Health organizations are implementing health information technologies such as electronic health records (EHR), information systems (IS), and health information exchange (HIE) networks to improve decision-making. However, over the years, the healthcare environment has demonstrated numerous unsuccessful implementations of such technologies. One of the reasons is that physicians tend not to make use of these technologies in the healthcare environment. The various explanations put forward typically refer to patient, physician, and/or work environment-related factors. This study evaluated the factors associated with the EHR use among physicians in the complex environment of emergency departments. We used log-files retrieved from an integrative and interoperable EHR that serves Israeli hospitals. We found that EHR was primarily consulted for patients presenting with internal diagnoses, patients of older age, and it was used more by internists than by surgical specialists. Furthermore, EHR usage was larger for admitted patients than for those discharged. The findings show factors associated with EHR use and suggest that it is mostly related to case-specific features and to physician specialty. The findings strongly suggest that when planning assimilation projects for EHR systems and HIE networks, attention should be paid to those factors associated with system usage. Specifically, in order to increase the efficiency of the system, and enhance its use in the ED environment, physicians' preferences and practice-related needs need to be taken into account. Furthermore, well-thought IT design and implementation are necessary to generate an increase in meaningful use of HIT, which can serve both physicians' and patients' needs.

This paper evaluates the contribution of an electronic health records (EHR) system to efficient d... more This paper evaluates the contribution of an electronic health records (EHR) system to efficient decision-making by physicians, and investigates whether these systems lead to more efficient medical care in emergency departments (ED). Log-files of patient visits and admissions were retrieved from an integrative EHR system that serves seven main hospitals owned by a large health maintenance organization (HMO). This study focused on readmissions within seven days and single-day admissions, problems that concern hospitals around the world. The findings indicate that using an EHR system in the EDs correlates with a decreased number of readmissions within seven days as well as with a reduced number of single-day admissions. The results provide evidence that using EHR system may contribute to efficiency in an ED by assisting decision-making. We believe this is the first data set that investigates the impact of an EHR on hospital efficiency at the scale of HMO.

Information Systems Management, 2020

Reducing costly hospital readmissions of patients with Congestive Heart Failure (CHF) is importan... more Reducing costly hospital readmissions of patients with Congestive Heart Failure (CHF) is important. We analyzed 4,661 CHF patients (from 2007 to 2017) using Hidden Markov Models in order to profile CHF readmission risk over time. This method proved practical in identifying three patient groups with distinctive characteristics, which might guide physicians in tailoring personalized care to prevent hospital readmission. We thus demonstrate how applying appropriate AI analytics can save costs and improve the quality of care.

The Journal of Alternative and Complementary Medicine, 2021