Till sidans topp

Sidansvarig: Webbredaktion
Sidan uppdaterades: 2012-09-11 15:12

Tipsa en vän
Utskriftsversion

Readmission prediction us… - Göteborgs universitet Till startsida
Webbkarta
Till innehåll Läs mer om hur kakor används på gu.se

Readmission prediction using deep learning on electronic health records

Artikel i vetenskaplig tidskrift
Författare A. Ashfaq
A. Sant'Anna
Markus Lingman
S. Nowaczyk
Publicerad i Journal of Biomedical Informatics
Volym 97
ISSN 1532-0464
Publiceringsår 2019
Publicerad vid Institutionen för medicin, avdelningen för molekylär och klinisk medicin
Språk en
Länkar dx.doi.org/10.1016/j.jbi.2019.10325...
Ämnesord Contextual embeddings, Electronic health records, Long short-term memory networks, Readmission prediction, Brain, Cost reduction, E-learning, Embeddings, Forecasting, Health risks, Long short-term memory, Patient treatment, Records management, Risk assessment, Risk perception, Class imbalance problems, Congestive heart failures, Discrimination ability, Electronic health record, Intervention programs, Prediction performance, Sequential patterns, Short term memory, Deep learning
Ämneskategorier Molekylär medicin

Sammanfattning

Unscheduled 30-day readmissions are a hallmark of Congestive Heart Failure (CHF) patients that pose significant health risks and escalate care cost. In order to reduce readmissions and curb the cost of care, it is important to initiate targeted intervention programs for patients at risk of readmission. This requires identifying high-risk patients at the time of discharge from hospital. Here, using real data from over 7500 CHF patients hospitalized between 2012 and 2016 in Sweden, we built and tested a deep learning framework to predict 30-day unscheduled readmission. We present a cost-sensitive formulation of Long Short-Term Memory (LSTM) neural network using expert features and contextual embedding of clinical concepts. This study targets key elements of an Electronic Health Record (EHR) driven prediction model in a single framework: using both expert and machine derived features, incorporating sequential patterns and addressing the class imbalance problem. We evaluate the contribution of each element towards prediction performance (ROC-AUC, F1-measure) and cost-savings. We show that the model with all key elements achieves higher discrimination ability (AUC: 0.77; F1: 0.51; Cost: 22% of maximum possible savings) outperforming the reduced models in at least two evaluation metrics. Additionally, we present a simple financial analysis to estimate annual savings if targeted interventions are offered to high risk patients. © 2019 The Authors

Sidansvarig: Webbredaktion|Sidan uppdaterades: 2012-09-11
Dela:

På Göteborgs universitet använder vi kakor (cookies) för att webbplatsen ska fungera på ett bra sätt för dig. Genom att surfa vidare godkänner du att vi använder kakor.  Vad är kakor?