Healthcare Software: Digital Medical Support
Improving Patient Outcomes with Healthcare Support Software
Digital tools are transforming everyday clinical practice, giving healthcare professionals faster, smarter ways to support patients and streamline their workflow. This roundup of available Emory technologies highlights innovative software designed to boost efficiency, enhance accuracy, and improve patient outcomes across a variety of care settings.
Point-of-Care Support Solutions
Clinical Decision Support System for Dermatology
Approximately 18 million diagnostic errors occur each year, often due to time pressure, complex cases, or inefficient technology. To improve accuracy, many clinicians turn to second opinions, online databases, and clinical decision support systems (CDSS), which help guide diagnostic and therapeutic decisions – but they don’t assist with documentation. Emory researchers have developed a tool that uses smart phrases and auto‑texts to provide brief, evidence‑based explanations, differential diagnoses, work‑ups, and treatments for dermatologic conditions, reducing the clerical burden of creating thorough consult notes and supporting better patient care.
Emory Liver Transplant App
This app is designed for community gastroenterologists and other providers to easily submit referrals directly to the Emory Liver Transplant Program. In addition to submitting referrals, providers can read about the education and experience of all Emory Liver Transplant physicians, learn about the latest research and clinical trials, review liver transplant outcomes at Emory, read the latest liver transplant news, and calculate their patients' MELD-Na score. View it on the Apple App Store or Google Play.
“Ready for Tonsillectomy” Mobile App
A tonsillectomy—the surgical removal of the tonsils—is common in children under 15 and can be especially stressful for young patients. Emory inventors have developed an interactive mobile app to support support children and their caregivers by providing second‑grade–level text, animated illustrations, and active learning tools that explain the procedure, preparation, anesthesia, and post‑operative care. The app delivers timed notifications that address common questions before and after surgery, and its modular design allows customization for other pediatric procedures and translation into multiple languages, broadening its impact on pediatric surgical education.
System for Assessing Health Severity and Predicting Readmissions
Cardiovascular disease is the leading cause of death in the United States, causing over 600,000 deaths each year and driving significant healthcare costs, while hospital readmissions after severe cardiac events—especially heart failure—remain high. To address this, Emory researchers have developed a remote monitoring system that uses smartphone data to accurately predict a user’s risk for a severe cardiac event, using an algorithm based on the FDA‑recognized Kansas City Cardiomyopathy Questionnaire‑12 (KCCQ‑12). The team has also created a functional beta smartphone app that accurately predicts KCCQ‑12 scores for at‑risk patients.
Research, Data Processing & Advanced Analytics Tools
Autoencoding Neural Networks with Applications to Brain-Machine Interfaces
Brain‑machine interfaces have gained significant attention for their potential to link computers with human neural activity. Emerging as a powerful tool in understanding complex neural activities are autoencoders: unsupervised artificial neural networks that can learn efficient data coding while maintaining the ability to sort through the noise of highly complicated neural networks with better accuracy.
Emory inventors developed a Latent Factor Analysis via Dynamical System (LFADS), a sequential autoencoder for deep learning, to extract dynamic factors affecting the neural population in a time series neural data and use them to infer the motion correlated with firing rate or spiking data for the recorded neurons. The inventors also created a new autoencoder training method called "Coordinated Dropout (CD)," which further improves neural data processing of LFADS. CD also prevents “overfitting,” a problem in machine learning where the model cannot sort through the noise of the data, which is then incorrectly factored into the real-world predictions.
Study Management and Retention Toolkit (SMART)
A smart acronym with an even smarter function: The Study Management and Retention Toolkit, or SMART, is a centralized management tool designed specifically for tracking multiple aspects of human subject research studies of various designs. Data records and patient information can be input from multiple research sites at the same time and are organized within the system for easy retrieval and export. SMART also tracks subject enrollment in studies, and even automatically sends out reminders for upcoming appointments through text, email and calendar alerts. It's a one-stop shop for research personnel that keeps things easy, organized and simple.