A5083358059- Genetics, Aging, and Longevity in Model Organisms
- Machine Learning in Healthcare
- Photoreceptor and optogenetics research
- COVID-19 diagnosis using AI
- Circadian rhythm and melatonin
- Electronic Health Records Systems
- Acute Myocardial Infarction Research
- Privacy-Preserving Technologies in Data
- Acute Ischemic Stroke Management
- Pharmaceutical Practices and Patient Outcomes
- Venous Thromboembolism Diagnosis and Management
- Chronic Disease Management Strategies
- Clinical Reasoning and Diagnostic Skills
- Geriatric Care and Nursing Homes
- Emergency and Acute Care Studies
- Advanced Thermodynamics and Statistical Mechanics
- Cannabis and Cannabinoid Research
- Healthcare Policy and Management
- AI in cancer detection
- Infant Health and Development
- Cardiovascular Function and Risk Factors
- Ecosystem dynamics and resilience
- Spaceflight effects on biology
- Rabbits: Nutrition, Reproduction, Health
- Medical Coding and Health Information
University of Pennsylvania
2017-2021
Icahn School of Medicine at Mount Sinai
2020-2021
Mount Sinai Health System
2021
Hasso Plattner Institute
2021
Philadelphia University
2019
Shell (United States)
2019
California University of Pennsylvania
2016
Machine learning models require large datasets that may be siloed across different health care institutions. studies focus on COVID-19 have been limited to single-hospital data, which limits model generalizability.
Coordinated rhythmic movements are ubiquitous in animal behavior. In many organisms, chains of neural oscillators underlie the generation these rhythms. C. elegans, locomotor wave has been poorly understood; particular, it is unclear where circuit rhythms generated, and whether there exists more than one such generator. We used optogenetic ablation experiments to probe nature rhythm circuit. found that multiple sections forward circuitry capable independently generating By perturbing...
ABSTRACT Machine learning (ML) models require large datasets which may be siloed across different healthcare institutions. Using federated learning, a ML technique that avoids locally aggregating raw clinical data multiple institutions, we predict mortality within seven days in hospitalized COVID-19 patients. Patient was collected from Electronic Health Records (EHRs) five hospitals the Mount Sinai System (MSHS). Logistic Regression with L1 regularization (LASSO) and Multilayer Perceptron...
Abstract Aims Clinical scoring systems for pulmonary embolism (PE) screening have low specificity and contribute to computed tomography angiogram (CTPA) overuse. We assessed whether deep learning models using an existing routinely collected data modality, electrocardiogram (ECG) waveforms, can increase PE detection. Methods results create a retrospective cohort of 21 183 patients at moderate- high suspicion associate 23 793 CTPAs (10.0% PE-positive) with 320 746 ECGs encounter-level clinical...
Although approximately one in five Medicare beneficiaries are discharged from hospital acute care to postacute at skilled nursing facilities (SNFs), little is known about access timely medical for these patients after they admitted a SNF. Our analysis of 2,392,753 such discharges hospitals under fee-for-service the period January 2012–October 2014 indicated that first visits by physician or advanced practitioner (a nurse assistant) initial assessment occurred within four days SNF admission...
Neural circuits coordinate with muscles and sensory feedback to generate motor behaviors appropriate an animal’s environment. In C. elegans, the mechanisms by which circuit generates undulations modulates them based on environment are largely unclear. We quantitatively analyzed elegans locomotion during free movement transient optogenetic muscle inhibition. Undulatory movements were highly asymmetrical respect duration of bending unbending each cycle. Phase response curves induced brief...
Abstract The roundworm Caenorhabditis elegans is widely used as a model for studying conserved pathways fat storage, aging, and metabolism. most broadly methods imaging in C. require fixing staining the animal. Here, we show that dark field images acquired through an ordinary light microscope can be to estimate levels worms. We define metric based on amount of scattered per area, this scattering strongly correlated with worm measured by Oil Red O (ORO) across wide variety genetic backgrounds...
Objective: To explore cognitive strategies clinicians apply while performing a medication reconciliation task, handling incomplete and conflicting information. Background: Medication is method to find resolve inconsistencies in patients’ medications medical conditions lists. The use during are unclear. Controlled lab experiments can how make sense of uncertain, missing, or information therefore support the development human performance model. We hypothesize that varied handle this task...
We report the results of a study which aims to improve our understanding how clinicians make sense medication and disease information (medical reconciliation), performed by in major US hospital. A card sorting simulation experiment running on an Android tablet was utilized record steps taken 130 reconcile better understand clinical they received about simulated patient. Evaluating order processed shows that most sorted medical condition before history. Clinicians use diverse strategies...
Our study aimed to examine psychiatric diagnoses and treatment preceding a schizophrenia diagnosis in adolescents, stratified by sex race/ethnicity. Using Medicaid physical behavioral health pharmacy claims data, we identified 1,459 adolescents who were aged 9-17 years diagnosed with between January 2006 through June 2009. Psychiatric diagnosis, mental service use including hospitalization, residential outpatient therapy psychotropic medication identified. Forty-five percent of the one or...
ABSTRACT Coordinated rhythmic movements are ubiquitous in animal behavior. In many organisms, chains of neural oscillators underlie the generation these rhythms. C. elegans , locomotor wave has been poorly understood; particular, it is unclear where circuit rhythms generated, and whether there exists more than one such generator. We used optogenetic ablation experiments to probe nature rhythm circuit. found that multiple sections forward circuitry capable independently generating By...
Classifying hospital admissions into various acute myocardial infarction phenotypes in electronic health records (EHRs) is a challenging task with strong research implications that remains unsolved. To our knowledge, this study the first to design and validate phenotyping algorithms using cardiac catheterizations identify not only patients ST-elevation (STEMI), but specific encounter when it occurred.We multi-modal phenotype STEMI on multicenter EHR containing 5.1 million 115 patient...
Abstract Neural circuits coordinate with muscles and sensory feedback to generate motor behaviors appropriate an animal’s environment. In C. elegans , the mechanisms by which circuit generates undulations modulates them based on environment are largely unclear. We quantitatively analyzed locomotion during free movement transient optogenetic muscle inhibition. Undulatory movements were highly asymmetrical respect duration of bending unbending each cycle. Phase response curves induced brief...
<sec> <title>BACKGROUND</title> Machine learning models require large datasets that may be siloed across different health care institutions. studies focus on COVID-19 have been limited to single-hospital data, which limits model generalizability. </sec> <title>OBJECTIVE</title> We aimed use federated learning, a machine technique avoids locally aggregating raw clinical data multiple institutions, predict mortality in hospitalized patients with within 7 days. <title>METHODS</title> Patient...
Background: Clinical scoring systems for pulmonary embolism (PE) screening have low specificity and contribute to CT angiogram (CTPA) overuse. We assessed whether deep learning models using an existing routinely collected data modality, electrocardiogram (ECG) waveforms, can increase PE detection.Methods: use clinical variables, annotated CTPAs, ECG waveform morphological parameter from five hospitals conduct a retrospective cohort study develop three predict likelihood: model only data, EHR...