Washington People: Chenyang Lu - The Source

Chenyang Lu is not a civil engineer.

For a computer scientist, however, he builds many bridges. Especially between the fields of IT and healthcare.

Lu is Full Graph Professor in the Washington University Department of Computer Science & Engineering at McKelvey School of Engineering in St. Louis. His research focuses on the Internet of Things (IoT), cyber-physical systems and artificial intelligence, and he is particularly interested in how these technologies can improve healthcare.

As part of several teams of surgeons and doctors, Lu has tested Fitbit activity trackers in studies that have shown that these relatively inexpensive wearable devices can play a valuable role in improving patient health.

"We can collect data like step count, heart rate and sleep cycles that we use with our machine learning models to predict a deterioration or improvement in a patient's health," said Lu. "These efforts show tremendous potential for wearable and machine learning to improve healthcare."

A graphic from a pilot study published in 2020 in which researchers monitored outpatients with wearable devices and developed machine learning models to predict the readmission of patients with congestive heart failure who were recently discharged from Barnes-Jewish Hospital. The results showed that continuous monitoring of outpatients with wristbands is feasible. Machine learning models based on multimodal data (step, sleep and heart rate) clearly outperformed the traditional clinical approach. A similar approach is used in one study to predict postoperative complications and readmission of patients undergoing pancreatic surgery. (Image: Chenyang Lu)

For example, using data from Fitbits, Lu and his coworkers have shown that they can predict the surgical outcomes of pancreatic cancer patients with greater success than the current risk assessment tool.

The goal is improved health care, but where some of the toughest problems arise, Lu finds technical solutions. Obstacles may contain sub-par data or simply not enough data to obtain useful information from portable devices.

"You have to extract features using engineering techniques," said Lu. "How do we take this noisy, lousy data from wearables and extract robust and predictive characteristics to generate something clinically meaningful and informative so that we can actually predict something?"

Getting useful information out of cluttered data is one of the reasons his colleagues at the School of Medicine value his partnership.

“Chenyang has established itself as an expert in interpreting and linking the points of this high-dimensional data. That's why I think he's so productive, "said Philip Payne, Janet and Bernard Becker Professor and Director of the Institute of Computer Science, Assistant Dean of Health Information and Data Science, and Senior Data Scientist at the School of Medicine.

He may be productive, but Lu is eager to do more.

"We can scale this to perfect the technology and expand the scope so that it can be used with larger groups of different types of patients," said Lu. "I look forward to working with even more doctors and surgeons to expand this work."

Read more on the engineering website.

continue reading http://dailytechnonewsllc.com/washington-people-chenyang-lu-the-source/?feed_id=3492&_unique_id=61bb36be9acbe