A5101879267- Machine Learning in Healthcare
- Radiology practices and education
- Topic Modeling
- Innovations in Medical Education
- Natural Language Processing Techniques
- Patient-Provider Communication in Healthcare
- Diabetic Foot Ulcer Assessment and Management
- Chronic Obstructive Pulmonary Disease (COPD) Research
- Electronic Health Records Systems
- Diabetes Management and Education
- Peripheral Nerve Disorders
- Psychosomatic Disorders and Their Treatments
- Software Reliability and Analysis Research
- Emergency and Acute Care Studies
- Clinical practice guidelines implementation
- Pharmaceutical Practices and Patient Outcomes
- Orthopedic Surgery and Rehabilitation
- Pressure Ulcer Prevention and Management
- Psychopathy, Forensic Psychiatry, Sexual Offending
- Software System Performance and Reliability
- Asthma and respiratory diseases
- Healthcare Systems and Technology
- Multimodal Machine Learning Applications
- Health Policy Implementation Science
- Chronic Disease Management Strategies
Reading Hospital
2023-2024
Yale University
2017-2023
Background: The Canadian Computed Tomography (CT) Head Rule, a clinical decision rule designed to safely reduce imaging in minor head injury, has been rigorously validated and implemented, yet expected decreases CT were unsuccessful. Recent work identified empathic care as key component decreasing overuse. Health information technology can hinder the clinician-patient relationship. Patient-centered tools support relationship are needed promote evidence-based decisions.
Physician turnover places a heavy burden on the healthcare industry, patients, physicians, and their families. Having mechanism in place to identify physicians at risk for departure could help target appropriate interventions that prevent departure. We have collected physician characteristics, electronic health record (EHR) use patterns, clinical productivity data from large ambulatory based practice of non-teaching build predictive model. several techniques possible intervenable variables....
Abstract Question Severe asthma and COPD exacerbations requiring hospitalization are linked to increased disease morbidity healthcare costs. We sought identify Electronic Health Record (EHR) features of severe evaluate the performance four machine learning (ML) one deep (DL) model in predicting readmissions using EHR data. Study design methods Observational study between September 30, 2012, December 31, 2017, patients hospitalized with exacerbations. Results This included 5,794 patients,...
Current information-rich electronic health record (EHR) interfaces require large, high-resolution screens running on desktop computers. This interface compromises the provider's already limited time at bedside by physically separating patient from doctor. The case study presented here describes a patient-centered clinical decision support (CDS) design process that aims to bring physician back integrating aid with CDS for shared use and provider touchscreen tablet computer deciding whether or...
Choosing an optimal data fusion technique is essential when performing machine learning with multimodal data. In this study, we examined deep learning-based techniques for the combined classification of radiological images and associated text reports. our analysis, (1) compared performance three prototypical techniques: Early, Late, Model fusion, (2) assessed to unimodal learning; finally (3) investigated amount labeled needed by versus models yield comparable performance. Our experiments...
We aimed to discover computationally-derived phenotypes of opioid-related patient presentations the ED via clinical notes and structured electronic health record (EHR) data.
Introduction Nerve conduction study (NCS) and electromyography (EMG) are electrodiagnostic studies that highly tolerated by patients despite their nature of causing pain discomfort. However, few have focused on the true tolerability these procedures in patients. This aimed to determine tolerance rate NCS EMG patient populations factors might be associated with them. Methods Participants scheduled for were prospectively recruited between March 2023 September 2023. After completion study,...
Abstract Introduction Amputation is a major condition that requires inpatient rehabilitation. Some research has been conducted to explore the risk factors for readmission of patients from rehabilitation facilities acute care hospitals. However, few studies have included with amputation in study population. Objective To identify hospitals an facility. Design Retrospective cohort study. Setting An hospital associated community‐based tertiary medical center. Patients A retrospective review 156...
Abstract Objective We aimed to discover computationally-derived phenotypes of opioid-related patient presentations the emergency department (ED) via clinical notes and structured electronic health record (EHR) data. Methods This was a retrospective study ED visits from 2013-2020 across ten sites within regional healthcare network. derived for patients 18 years age with at least one prior or current documentation an diagnosis. Natural language processing used extract entities notes, which...