Prediction of Effectiveness and Toxicities of Immune Checkpoint Inhibitors Using Real-World Patient Data.

PURPOSE: Although immune checkpoint inhibitors (ICIs) have improved outcomes in certain patients with cancer, they can also cause life-threatening immunotoxicities. Predicting immunotoxicity risks alongside response could provide a personalized risk-benefit profile, inform therapeutic decision making, and improve clinical trial cohort selection. We aimed to build a machine learning (ML) framework using routine electronic health record (EHR) data to predict hepatitis, colitis, pneumonitis, and 1-year overall survival. METHODS: Real-world EHR data of more than 2,200 patients treated with ICI through December 31, 2018, were used to develop predictive models. Using a prediction time point of ICI initiation, a 1-year prediction time window was applied to create binary labels for the four outcomes for each patient. Feature engineering involved aggregating laboratory measurements over appropriate time windows (60-365 days). Patients were randomly partitioned into training (80%) and test (20%) sets. Random forest classifiers were developed using a rigorous model development framework. RESULTS: The patient cohort had a median age of 63 years and was 61.8% male. Patients predominantly had melanoma (37.8%), lung cancer (27.3%), or genitourinary cancer (16.4%). They were treated with PD-1 (60.4%), PD-L1 (9.0%), and CTLA-4 (19.7%) ICIs. Our models demonstrate reasonably strong performance, with AUCs of 0.739, 0.729, 0.755, and 0.752 for the pneumonitis, hepatitis, colitis, and 1-year overall survival models, respectively. Each model relies on an outcome-specific feature set, though some features are shared among models. CONCLUSION: To our knowledge, this is the first ML solution that assesses individual ICI risk-benefit profiles based predominantly on routine structured EHR data. As such, use of our ML solution will not require additional data collection or documentation in the clinic.

A novel approach for determining instantaneous centers of rotation of the mandible with an intraoral scanner: A preliminary study.

OBJECTIVES: Recording and reproducing mandibular movements have been of key importance in the practice of dentistry for over a century. Recently, it has become possible to use digital technologies for these tasks. This study presents a preliminary method to try to identify the mandibular instantaneous centres of rotation based solely on intraoral scanners. METHODS: The dentitions of four participants were scanned, multiple inter-occlusal registrations and buccal scans were performed in closed and opened positions. Blender software was used to align the meshes during the post-scan digital workflow. Bite alignment accuracy was assessed and then improved with a strict exclusion protocol. An automated algorithm was used to find rotations between closed stage and open stage meshes. RESULTS: Our exclusion protocol reduced the bite alignment error significantly (p = 0.001) and the root-mean-square error value of the meshes decreased from 0.09 mm (SD = 0.15) to 0.03 mm (SD = 0.017). However, the remaining translational error caused an unexpectedly large shift in the axis of rotation (mean = 1.35 mm, SD = 0.77) with a 41.83: 1 ratio. As found in other studies, our results showed even a small amount of error during registration can shift the axis of rotation a large amount. This phenomenon will compromise the results of common pantographic methods which assume a rotation axis of the condyle. It also adds valuable information to the concept of instantaneous centers of rotation by revealing their true characteristics.