Patient Outcome Predictions Improve Operations at a Large Hospital Network

• URL: http://arxiv.org/abs/2305.15629v1
• Date: Thu, 25 May 2023 00:49:27 GMT
• Title: Patient Outcome Predictions Improve Operations at a Large Hospital Network
• Authors: Liangyuan Na, Kimberly Villalobos Carballo, Jean Pauphilet, Ali Haddad-Sisakht, Daniel Kombert, Melissa Boisjoli-Langlois, Andrew Castiglione, Maram Khalifa, Pooja Hebbal, Barry Stein, Dimitris Bertsimas
• Abstract summary: A large hospital network in the US has been collaborating with academics and consultants to predict short-term and long-term outcomes for all inpatients. We develop machine learning models that predict the probabilities of next 24-hr/48-hr discharge and intensive care unit transfers, end-of-stay mortality and discharge dispositions. We implement an automated pipeline that extracts data and updates predictions every morning, as well as user-friendly software and a color-coded alert system to communicate these patient-level predictions.
• Score: 1.9399350450208843
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Problem definition: Access to accurate predictions of patients' outcomes can enhance medical staff's decision-making, which ultimately benefits all stakeholders in the hospitals. A large hospital network in the US has been collaborating with academics and consultants to predict short-term and long-term outcomes for all inpatients across their seven hospitals. Methodology/results: We develop machine learning models that predict the probabilities of next 24-hr/48-hr discharge and intensive care unit transfers, end-of-stay mortality and discharge dispositions. All models achieve high out-of-sample AUC (75.7%-92.5%) and are well calibrated. In addition, combining 48-hr discharge predictions with doctors' predictions simultaneously enables more patient discharges (10%-28.7%) and fewer 7-day/30-day readmissions ($p$-value $<0.001$). We implement an automated pipeline that extracts data and updates predictions every morning, as well as user-friendly software and a color-coded alert system to communicate these patient-level predictions (alongside explanations) to clinical teams. Managerial implications: Since we have been gradually deploying the tool, and training medical staff, over 200 doctors, nurses, and case managers across seven hospitals use it in their daily patient review process. We observe a significant reduction in the average length of stay (0.67 days per patient) following its adoption and anticipate substantial financial benefits (between \$55 and \$72 million annually) for the healthcare system.

Related papers

• SepsisLab: Early Sepsis Prediction with Uncertainty Quantification and Active Sensing [67.8991481023825]
  Sepsis is the leading cause of in-hospital mortality in the USA. Existing predictive models are usually trained on high-quality data with few missing information. For the potential high-risk patients with low confidence due to limited observations, we propose a robust active sensing algorithm.
  arXiv  Detail & Related papers  (2024-07-24T04:47:36Z)
• A machine learning framework for interpretable predictions in patient pathways: The case of predicting ICU admission for patients with symptoms of sepsis [3.5280004326441365]
  PatWay-Net is an ML framework designed for interpretable predictions of admission to the intensive care unit for patients with sepsis. We propose a novel type of recurrent neural network and combine it with multi-layer perceptrons to process the patient pathways. We demonstrate its utility through a comprehensive dashboard that visualizes patient health trajectories, predictive outcomes, and associated risks.
  arXiv  Detail & Related papers  (2024-05-21T20:31:42Z)
• An Interpretable Deep-Learning Framework for Predicting Hospital Readmissions From Electronic Health Records [2.156208381257605]
  We propose a novel, interpretable deep-learning framework for predicting unplanned hospital readmissions. We validate our system on the two predictive tasks of hospital readmission within 30 and 180 days, using real-world data.
  arXiv  Detail & Related papers  (2023-10-16T08:48:52Z)
• Dynamic Healthcare Embeddings for Improving Patient Care [0.0]
  We propose DECENT, an auto-encoding heterogeneous co-evolving dynamic neural network, for learning dynamic embeddings of patients, doctors, rooms, and medications. The results of using the learned patient embeddings in predictive modeling show that DECENT has a gain of up to 48.1% on the mortality risk prediction task. Case studies on the learned doctor, medication, and room embeddings show that our approach learns meaningful and interpretable embeddings.
  arXiv  Detail & Related papers  (2023-03-21T03:14:15Z)
• Predicting Patient Readmission Risk from Medical Text via Knowledge Graph Enhanced Multiview Graph Convolution [67.72545656557858]
  We propose a new method that uses medical text of Electronic Health Records for prediction. We represent discharge summaries of patients with multiview graphs enhanced by an external knowledge graph. Experimental results prove the effectiveness of our method, yielding state-of-the-art performance.
  arXiv  Detail & Related papers  (2021-12-19T01:45:57Z)
• Optimal discharge of patients from intensive care via a data-driven policy learning framework [58.720142291102135]
  It is important that the patient discharge task addresses the nuanced trade-off between decreasing a patient's length of stay and the risk of readmission or even death following the discharge decision. This work introduces an end-to-end general framework for capturing this trade-off to recommend optimal discharge timing decisions. A data-driven approach is used to derive a parsimonious, discrete state space representation that captures a patient's physiological condition.
  arXiv  Detail & Related papers  (2021-12-17T04:39:33Z)
• Forecasting COVID-19 Counts At A Single Hospital: A Hierarchical Bayesian Approach [59.318136981032]
  We consider the problem of forecasting the daily number of hospitalized COVID-19 patients at a single hospital site. We develop several candidate hierarchical Bayesian models which directly capture the count nature of data. We demonstrate our approach on public datasets for 8 hospitals in Massachusetts, U.S.A. and 10 hospitals in the United Kingdom.
  arXiv  Detail & Related papers  (2021-04-14T11:58:54Z)
• Clinical Outcome Prediction from Admission Notes using Self-Supervised Knowledge Integration [55.88616573143478]
  Outcome prediction from clinical text can prevent doctors from overlooking possible risks. Diagnoses at discharge, procedures performed, in-hospital mortality and length-of-stay prediction are four common outcome prediction targets. We propose clinical outcome pre-training to integrate knowledge about patient outcomes from multiple public sources.
  arXiv  Detail & Related papers  (2021-02-08T10:26:44Z)
• Forecasting Emergency Department Capacity Constraints for COVID Isolation Beds [9.358404775024109]
  New COVID-related capacity constraints placed on our pediatric hospital's emergency department prompted us to develop an hourly forecasting tool. We obtain strong performance for both point predictions and classification accuracy when predicting the ordinal tiers of our hospital's capacity. We are currently working on moving our tool to a real-time setting with the goal of augmenting the capabilities of our healthcare workers.
  arXiv  Detail & Related papers  (2020-11-09T19:35:41Z)
• BiteNet: Bidirectional Temporal Encoder Network to Predict Medical Outcomes [53.163089893876645]
  We propose a novel self-attention mechanism that captures the contextual dependency and temporal relationships within a patient's healthcare journey. An end-to-end bidirectional temporal encoder network (BiteNet) then learns representations of the patient's journeys. We have evaluated the effectiveness of our methods on two supervised prediction and two unsupervised clustering tasks with a real-world EHR dataset.
  arXiv  Detail & Related papers  (2020-09-24T00:42:36Z)
• A unified machine learning approach to time series forecasting applied to demand at emergency departments [1.7119367122421556]
  There were 25.6 million attendances at Emergency Departments (EDs) in England in 2019 corresponding to an increase of 12 million attendances over the past ten years. We develop a novel ensemble methodology that combines the outcomes of the best performing time series and machine learning approaches. Our approach is able to predict attendances one day in advance up to a mean absolute error of +/- 14 and +/- 10 patients corresponding to a mean absolute percentage error of 6.8% and 8.6% respectively.
  arXiv  Detail & Related papers  (2020-07-13T07:59:24Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.