The Malone Center for Engineering in Healthcare (MCEH) recently awarded grants through the center’s Seed Grant Program. The new grants will fund engineering innovations that aim to:

  • identify pediatric patients at high risk of developing COVID-19 complications
  • understand and reduce bias in deep learning algorithms for radiology
  • uncover mechanisms responsible for inequitable health outcomes for COVID-19

With the funding for this round of projects, the center will have awarded a total of 13 Seed Grants since the program’s inception in 2018. To learn about the past projects, visit the Malone Seed Grant page.

The Malone Center will fund the following projects:

Identifying Pediatric Patients at Risk of Developing Severe Complications from SARS-CoV-2 Infection – Harnessing the Power of Artificial Intelligence-Driven Predictive Models

Research Team: Oluwakemi Badaki-Makun (Pediatric Emergency Medicine); Scott Levin and Jeremiah Hinson (Emergency Medicine/MCEH)

Despite indications that SARS-CoV-2 infection appears to cause less severe disease in children than in adults, severe complications – including prolonged hospitalizations, invasive ventilation, and death – do occur in this population. Early identification, isolation and treatment of pediatric patients at risk for these severe complications will improve outcomes.

Led by Oluwakemi Badaki-Makun, associate director of research of pediatric emergency medicine, and Malone researchers Scott Levin and Jeremiah Hinson, the project will develop predictive models with two objectives: identify pediatric patients (ages 0 to 21 years) admitted to emergency departments at Johns Hopkins who are at high risk for SARS-CoV-2 complications; and determine the probability that asymptomatic pediatric patients undergoing routine screening for elective procedures are positive for SARS-CoV-2. The research team will use the Super Learner approach, a technique in which multiple machine learning algorithms and regression models can be combined into an ensemble algorithm to produce a predictive model.

Evaluating and Solving Performance Biases Against Underrepresented Populations in Deep
Learning-Based Diagnosis of Disease on Chest Radiographs

Research Team: Paul Yi (Radiology/MCEH), Jeremias Sulam (Biomedical Engineering), Ilya Shpitser (Computer Science/MCEH), and Cheng Ting Lin (Radiology)

Deep learning (DL) models have demonstrated their potential to diagnose disease on medical imaging with performance approaching or even exceeding that of a human radiologist. But deep learning models suffer from a fundamental problem: they often adopt unwanted biases found within the data on which they’re trained. Ultimately, these biases can lead to problems such as discrimination and underserving or underperforming on underrepresented populations. 

To make these models more equitable, the research team will quantify the impact of chest x-ray datasets with imbalances in demographics, such as sex and race/ethnicity, on the development of biased DL models for medical imaging diagnosis. Based on these findings,  the team will develop and validate methods to train DL models resistant to demographic imbalances. Ultimately, this work will set the foundation for unbiased DL algorithms which can be safely deployed in diverse patient populations. 

Identifying Mechanisms Responsible for Inequitable Health Outcomes for COVID-19

Research Team: Ilya Shpitser  and Mathias Unberath (Computer Science/MCEH); Jeremiah Hinson and Scott Levin (Emergency Medicine/MCEH) 

The COVID-19 pandemic has exposed longstanding health inequities in United States; evidence is mounting that some ethnic groups are suffering far worse outcomes, including mortality, compared to others. Precise mechanisms driving these disparities are not currently well understood, and may include socioeconomic factors, prevalence of important comorbidities, or even other mechanisms such as differential adherence to government interventions. 

In this proposed study, the team will leverage modern causal inference methodology to investigate mechanisms behind observed disparities associated with causal pathways mediated by by socioeconomic factors, biological factors, or differences in care. Their findings will be made available to the scientific and legislative communities as soon as possible to help guide continued research and political intervention to mitigate the causes of inequitable health outcomes in COVID-19.

This project is a continuation of work started at the center’s fall symposium “Disparities and COVID-19: A Two Day Virtual Workshop on Data Science for Social Good.” 

*The Malone Center Seed Grant Program aims to assist faculty and research staff with development of innovative, collaborative proposals that will advance the Malone Center mission. New partnerships and research directions are often achieved, opening up opportunities that may otherwise not come to fruition.