This project focuses on developing machine learning models to predict the likelihood of patients being readmitted to the Intensive Care Unit (ICU). ICUs manage critically ill patients, and while clinicians make discharge decisions based on expertise, there's no formal method to predict readmission success. Current readmission rates range from 2% to 20%, with readmitted patients facing significantly higher mortality risks. Existing predictive models often rely on static data and don't fully utilize the complex, time-varying information available in Electronic Health Records (EHRs). The goal is to create an algorithm that leverages comprehensive EHR data to accurately predict ICU readmissions. By improving the prediction of patient recovery and reducing premature discharges, this work aims to decrease morbidity and mortality, lower healthcare costs, and optimize resource allocation. The insights gained from analyzing predictive features could also inform future healthcare modeling.
This project focuses on a specific research and design outcome within Biomedical Engineering. Career paths stemming from such work involve applying advanced data analysis and machine learning techniques to healthcare challenges.
The Committee on Finance reviews and approves the university's budget, including tuition levels. For detailed financial information, prospective students should consult the main Johns Hopkins University Admissions and Aid sections.
Accreditation information for the Biomedical Engineering program is available via a link on the BME department page, indicating a focus on program objectives and outcomes.
This project focuses on developing machine learning models using comprehensive Electronic Health Records (EHR) data to predict the likelihood of patients being readmitted to the Intensive Care Unit (ICU). The goal is to improve patient outcomes and reduce healthcare costs by optimizing discharge decisions.
This project can lead to roles such as a Clinical Data Scientist, Healthcare AI Researcher, Biomedical Data Analyst, or Predictive Health Modeler, focusing on applying advanced data analysis and machine learning to healthcare challenges.
Prospective students should follow the general graduate application procedures for Johns Hopkins University. This includes identifying the program, reviewing specific requirements, preparing application materials like transcripts and letters of recommendation, submitting the online application, and paying the fee.
The application period typically opens in the fall for admission the following academic year, with deadlines varying by program. Admission decisions are often released in late winter or early spring.
Specific tuition figures and estimated living costs are not provided. Prospective students should consult the main Johns Hopkins University Admissions and Aid sections and refer to the Committee on Finance for detailed financial information.
Detailed information on specific program entry requirements, including academic prerequisites and English language proficiency, is not provided. Prospective students should refer to the general graduate admissions information for Johns Hopkins University.