Category: Digital Health
-
Predicting newborn health outcomes with electronic health records data
Researchers used electronic health records (EHRs) and advanced machine learning methodologies to predict neonatal outcomes from maternal conditions. The study used data from 32,354 mother-newborn dyads to train and validate the model and found it outperformed currently used EHR-based clinical risk scores. The study identified previously unreported associations between maternal conditions, such as anemia, certain…
-
Electronic patient-reported outcome (ePRO) systems reduce outpatient waiting lists
A review by the Centre for Patient-Reported Outcomes Research and the Institute of Applied Health Research at the University of Birmingham found that digital systems for patients to report symptoms remotely may reduce outpatient waiting lists. Electronic Patient-Reported Outcome (ePRO) systems allow patients to fill out questionnaires and have the results sent back to clinicians…
-
Machine learning model to predict heart injury post non-cardiac surgery
A prediction model for Myocardial injury after non-cardiac surgery (MINS) was developed by researchers from South Korea using machine learning techniques with the extreme gradient boosting algorithm. The study analyzed 6811 patients who underwent non-cardiac surgery between January 2010 and June 2019. The top 12 variables affecting MINS were preoperative cardiac troponin level, inotropic drug…
-
Deep learning model improves radiologist diagnostic performance in colon cancer screening
A study by the Technical University of Munich researchers evaluated the use of a deep learning algorithm to differentiate between colon cancer and acute diverticulitis on CT images and its impact on radiologists’ performance. The 3-D convolutional neural network reached a sensitivity of 83.3% and specificity of 86.6% compared to the average reader sensitivity of…
-
Sybil, a machine-learning model for lung cancer risk assessment
Researchers at MIT’s Abdul Latif Jameel Clinic for Machine Learning in Health, Mass General Cancer Center, and Chang Gung Memorial Hospital have developed an artificial intelligence tool named Sybil for lung cancer risk assessment. Sybil analyzes low-dose computed tomography (LDCT) image data without using clinical or demographic data to predict a patient’s risk of developing…
-
Machine learning model to predict drug side effects
Researchers developed a machine learning model to predict drug side effects that were discovered in post-marketing surveillance after clinical trials. Diego Galeano and Alberto Paccanaro utilized a geometric self-expressive model(GSEM) machine learning framework and post-marketing drug side effect data, drug chemical structure and protein targets data, and drug indications data. GSEM algorithm to predict drug…
-
Visible app – Activity monitoring for Illness
The Visible platform helps monitor health using manual data inputs about symptoms. It also utilizes smartphone cameras to analyze heart rate variation using a technique called photoplethysmography. In the future Visible hope to provide a monthly subscription service that includes a Polar Verity Sense heart-rate monitor (HRM), which is worn on the arm to collect…
-
A new computational approach to autism screening utilizing digital biomarkers shows promise
Researchers at the University of Chicago have developed a novel computational approach that can reliably predict an eventual diagnosis of autism spectrum disorder (ASD) in young children, without the need for additional blood work or procedures, using only diagnostic codes from past doctor’s visits. The new approach reportedly reduces the number of false-positive ASD diagnoses…
-
Virtual reality avatar to help physiotherapy at home
Researchers from the University of Warwick showed that virtual reality (VR) combined with 3D Motion capture could allow movements to be translated onto an avatar that the patient can follow. They accomplished this using consumer VR technologies currently available. Research showed that these consumer virtual reality technologies could be used for both providing guidance to…
-
Artificial Intelligence app to predict meningioma survival
Researchers recently published a study that shows proof of concept for how artificial intelligence can help doctors and brain tumor patients predicting survival and help make better treatment decisions. This study is published in Nature partner journal Digital Medicine. They also developed an open-source smartphone app meningioma.app to allow clinicians and other researchers to interactively…
Medical News Observer 
You must be logged in to post a comment.