SBME Research Seminar - Dr. Hannah Carter
Immune Checkpoint Blockade (ICB) has revolutionized cancer treatment, however mechanisms determining patient response remain poorly understood. We used machine learning to predict ICB response from germline and somatic biomarkers and studied feature usage by the learned model to uncover putative mechanisms driving superior outcomes. Patients with higher T follicular helper infiltrates were robust to defects in the class-I Major Histocompatibility Complex (MHC-I). Further investigation uncovered different ICB responses in MHC-I versus MHC-II neoantigen reliant tumors across patients. Despite similar response rates, MHC-II reliant responses were associated with significantly longer durable clinical benefit (Discovery: Median OS=63.6 vs. 34.5 months P=0.0074; Validation: Median OS=37.5 vs. 33.1 months, P=0.040). Characteristics of the tumor immune microenvironment reflected MHC neoantigen reliance, and analysis of immune checkpoints revealed LAG3 as a potential target in MHC-II but not MHC-I reliant responses. This study highlights the value of interpretable machine learning models in elucidating the biological basis of therapy responses.
Events
Calendar
- This event has passed.
SBME Research Seminar: Prompting Patients to Self-Rescue from Respiratory Depression – Dr. Lara Brewer
September 19, 2024 @ 11:00 am - 12:00 pm PDT
SBME Research Seminar: Prompting Patients to Self-Rescue from Respiratory Depression – Dr. Lara Brewer
Seminar Abstract:
Patients often receive opioids after surgery to treat pain. One side effect of the opioids is that the patient is at risk for experiencing a reduced drive to breathe. In extreme cases, the patient will become apneic, leading to a code blue and cardiopulmonary arrest. The whole event can take place within 10-15 minutes. The traditional way to monitor a patient at risk for respiratory depression or arrest is to measure their blood oxygen saturation with a pulse oximeter and their respiratory rate with a capnometer sampled by a nasal cannula. A central nursing station typically displays the monitored parameters and alerts. Pulse oximeters and capnometers also alarm in the patient’s room if the parameters are lower than normal. Unfortunately, the patient monitors frequently sound false alarms, leading to clinician burnout and fatigue. It is not uncommon for a nurse to be summoned to the bedside by many false alarms before missing a rare but fatal code blue event.
Our team is investigating a solution that involves monitoring the patient and asking them by name to self-rescue by taking life-saving breaths during a respiratory depression event. Our algorithm uses a reliable machine learning approach to identify ventilation problems. A speaker in the room annunciates prompts and makes bystanders aware of the respiratory depression. Our verbal prompting system shows excellent promise in correctly identifying periods of respiration depression, effectively inducing respiration resumption in both volunteers and patients, and maintaining repeated prompt effectiveness for at least 10 minutes. Together, our work demonstrates that an automated prompting system may help to keep a patient safe until a clinician can be summoned to the bedside.
Dr. Lara Brewer’s Biography:
Dr. Lara Brewer is a Research Associate Professor at the University of Utah, Salt Lake City, USA, Departments of Anesthesiology and Biomedical Engineering. She is one of three professors leading research in the Bioengineering Lab, which is imbedded in the Department of Anesthesiology. Her translational research is focused on developing and applying new technologies for anesthesia and intensive care. Recently, Dr. Brewer has focused on prompting respiration in patients receiving opioids post-surgically for pain relief. She and her team apply machine learning techniques to identify respiration problems and then prompt a patient to self-rescue, thereby improving patient safety until a clinician can return to the bedside. Dr. Brewer also partners closely with medical device manufacturers to test new concepts and to improve existing technologies throughout the clinical environment. Her work has been funded by the NIH, the Anesthesia Patient Safety Foundation, and NASA, among others. Before joining the University of Utah as faculty, Dr. Brewer earned both her Ph.D. and M.S. in Bioengineering from the U of U, working under Drs. Dwayne Westenskow and Joe Orr, where she developed a method for noninvasive measurement of Functional Residual Capacity based on a novel oxygen sensor.
Location:
LSC 1001 LT1