News

Yuzhen Liang awarded summer research assistantship by the IHSIP

The Boston University Institute for Health System Innovation & Policy (IHSIP) announced that DSLab researcher Yuzhen Liang has been awarded a 2021 summer research assistantship.   Yuzhen will work on a project titled “Application of Machine Learning to Real Time Nurse Dispatching.”  The project aims to apply machine learning methodologies to develop an algorithm that would set priorities among a group of patients with different needs that may change over time.  The results would be used to assign nurses to patients in real time in conjunction with an electronic health record system.  The project corresponds to two of the IHSIP domains: (a) Health System Design & Innovation, and (b) Digital Health.  It is motivated by the increased complexity of medical decision making that is brought about by technological advances, treatment sophistication, and new medication protocols.  These changes make it difficult for even experienced nurses to prioritize care tasks, which can lead to patients suffering from preventable conditions.  To compound the challenge, flexible scheduling systems assign nurses to hospital wards based on patient demand, compromising their ability to obtain expertise in each setting.

DSLab initiates City Innovate project with the MBTA

In January 2021, the DSLab started working on a project with the MBTA (Massachusetts Bay Transportation Authority) to create a decision support system to improve winter storm resource deployment processes. Click here to read more about the project.

Danrong Chen and John Maleyeff have a new publication in the Health Informatics Journal

Consumer health informatics approach for personalized cancer screening decisions using utility functions

Abstract

A consumer health informatics approach is used to investigate the development of a patient-centered decision support system (DSS) with individualized utility functions. It supports medical decisions that have uncertain benefits and potential harms. Its use for accepting or declining cancer screening is illustrated. The system’s underlying optimization model incorporates two user-specific utility functions—one that quantifies life-saving benefits and one that quantifies harms, such as unnecessary follow-up tests, surgeries, or treatments. The system requires sound decision making. Therefore, the decision making process was studied using a decision aid in the form of a color-coded matrix with the potential outcomes randomly placed in proportion to their likelihoods. Data were collected from 48 study participants, based on a central composite experimental design. The results show that the DSS can be effective, but health consumers may not be rational decision makers.

Keywords cancer screening, clinical decision making, consumer health informatics, e-health, health utility functions, medical decision modeling

Danqi Lu presented our research at the November 2020 Decision Sciences Institute (DSI) annual meeting. Click here to view the presentation.

2020 Annual Conference of the Decision Sciences Institute was hold on November 21st, 2020.

 

To see more information about the project: Meta-Analysis of How Call Centers Can Use Lean to Improve Customer Experience