Three stories that show how AI is assisting the medical profession.

Olive: Urine Analysis on an Apple Watch

Olive KG, a non-invasive, toilet-mounted, AI-based optical device by Olive Diagnostics automatically sends its results for display on an Apple Watch via an app called Olive WatchOS.

The AI in the sensor measures molecules, biomarkers in urine that are relevant to more than 600 conditions, and analyzes protein, ketone, creatinine, as well as red blood cells, and other urine characteristics such as volume, pressure, color, and frequency.

As soon as a person approaches a toilet the sensor connects to the Apple Watch via Bluetooth, displays the urine analysis and also provides a health score.

“Olive Diagnostics enables quick and early detection of conditions and diseases that could negatively impact the health of a person and place an unnecessary load on healthcare professionals,” said Guy Goldman, CEO of Olive Diagnostics. “We are now taking this a step further and simplifying how the how users interact with the toilet mounted sensor, and receive data relevant to them, as well as their care givers.” (ISRAEL HAYOM)

John Hopkins: Predicting cardiac arrest

A new artificial-intelligence-based technique developed by Johns Hopkins University researchers may accurately predict if and when a patient could die of cardiac arrest.

“There are patients who may be at low risk of sudden cardiac death getting defibrillators that they might not need and then there are high-risk patients that aren’t getting the treatment they need and could die in the prime of their life,” said Natalia Trayanova, senior author of the paper, in a university press statement. “What our algorithm can do is determine who is at risk for cardiac death and when it will occur, allowing doctors to decide exactly what needs to be done.” (Indian Express)

Hernia surgery outcomes

Surgeons at the University of Texas MD Anderson Cancer Center in Houston have developed machine learning models that predict with high accuracy the type of patients that are most likely to have a hernia recurrence or other complications.

Recurrence of hernias after surgery happens in about a third of the patients even though repair of ventral hernias (hernias that occur when a bulge emerges through the abdominal muscles) is a common operation. Even post-surgery complications are fairly frequent.

“We found that the machine learning algorithm, trained using our own data, could accurately predict occurrence of complications after complex abdominal wall repair,” said lead study author Abbas M Hassan, post doctoral fellow and PhD candidate, department of plastic surgery, MD Anderson. (Medical Dialogues)

Related Story: MIT Researcher Develops Mirai – An AI To Accurately Predict Breast Cancer