Management of severe symptomatic immune-related adverse events (IrAEs) related to immune checkpoint inhibitors (ICIs) can be facilitated by timely detection. As patients face a heterogeneous set of symptoms outside the clinical setting, remotely monitoring and assessing symptoms by using patient-reported outcomes (PROs) may result in shorter delays between symptom onset and clinician detection.We assess the effect of a model of care for remote patient monitoring and symptom management based on PRO data on the time to detection of symptomatic IrAEs from symptom onset. The secondary objectives are to assess its effects on the time between symptomatic IrAE detection and intervention, IrAE grade (severity), health-related quality of life, self-efficacy, and overall survival at 6 months.For this study, 198 patients with cancer receiving systemic treatment comprising ICIs exclusively will be recruited from 2 Swiss university hospitals. Patients are randomized (1:1) to a digital model of care (intervention) or usual care (control group). Patients are enrolled for 6 months, and they use an electronic app to complete weekly Functional Assessment of Cancer Therapy-General questionnaire and PROMIS (PROs Measurement Information System) Self-Efficacy to Manage Symptoms questionnaires. The intervention patient group completes a standard set of 37 items in a weekly PROs version of the Common Terminology Criteria for Adverse Events (PRO-CTCAE) questionnaire, and active symptoms are reassessed daily for the first 3 months by using a modified 24-hour recall period. Patients can add items from the full PRO-CTCAE item library to their questionnaire. Nurses call patients in the event of new or worsening symptoms and manage them by using a standardized triage algorithm based on the United Kingdom Oncology Nursing Society 24-hour triage tool. This algorithm provides guidance on deciding if patients should receive in-person care, if monitoring should be increased, or if self-management education should be reinforced.The Institut Suisse de Recherche Expérimentale sur le Cancer Foundation and Kaiku Health Ltd funded this study. Active recruitment began since November 2021 and is projected to conclude in November 2023. Trial results are expected to be published in the first quarter of 2024 and will be disseminated through publications submitted at international scientific conferences.This trial is among the first trials to use PRO data to directly influence routine care of patients treated with ICIs and addresses some limitations in previous studies. This trial collects a wider spectrum of self-reported symptom data daily. There are some methodological limitations brought by changes in evolving treatment standards for patients with cancer. This trial's results could entail further academic discussions on the challenges of diagnosing and managing symptoms associated with treatment remotely by providing further insights into the burden symptoms represent to patients and highlight the complexity of care procedures involved in managing symptomatic IrAEs.ClinicalTrials.gov NCT05530187; https://www.clinicaltrials.gov/study/NCT05530187.DERR1-10.2196/48386.
e21529 Background: The combination of ipilimumab and nivolumab in metastatic melanoma patients increases response rates (RR) and survival outcomes. As checkpoint inhibitors bear a significant financial impact on the healthcare system, we performed a study that addresses the global costs of the treatment, focusing on immune-related adverse event (irAE) management costs. Methods: We conducted a retrospective analysis of 62 metastatic melanoma patients treated with ipilimumab and nivolumab at the Oncology Department of Lausanne University Hospital (CHUV) between June 1, 2016 and August 31, 2019. The frequency of irAEs, the duration, management, and outcomes were evaluated. All melanoma-specific costs were analyzed by mining the electronic healthcare record and billing data of the hospital. Results: The median follow-up was 32 months (range 20-1066 days). In our cohort, 54/62 (87%) patients presented at least one irAE, and 22/62 (35%) presented a grade 3 irAE. One patient died from an irAE (pneumonitis). The most common irAEs were diarrhea 23/62 (37%) any grade, 8/62 (13%) grade 3-4; hepatitis 22/62 (36%) any grade, 9/62 (15%) grade 3-4; and skin rash 21/62 (34%) any grade, 6/32 (10%) grade 3-4. The overall response rate was 29/62 (47%), with 15/62 (24%) of complete response (CR) and 14/62 (23%) of partial response (PR). The majority of patients who had a CR 13/15 (87%) and 20/28 (71%) of overall responders presented a grade 3-4 toxicity, and there were no responses in patients without toxicity. However, toxicity does not imply response, as only 29/54 (54%) of patients with toxicity (any grade) and 20/31 (65%) (grade 3-4) responded. The toxicity costs represent only 3% on average of the total expenses per patient. The most significant contributions were medication costs (44%) and disease costs (39%, mainly disease-related hospitalization costs). Patients with a CR had the lowest global cost per week (2,860 USD, converted from CHF) despite the associated toxicities and patients who had progressive disease, the highest one (9,999 USD). Except for the one patient who had a grade 5 toxicity (7,472 USD/week), we observe that less severe toxicity grades (11,603 USD/week for grade 1), or even the absence of toxicity (12,266 USD/week), are associated to higher median costs per week (against 4,039 USD/ week for grade 4 and 3,524 USD/week for grade 3). Conclusions: The cost of toxicities was unexpectedly small (only 3%) compared to the total costs, especially medication costs (44%). Also, patients with a higher degree of toxicity had lower costs and better outcomes.
Abstract Thanks to its ability to offer a time-oriented perspective on the clinical events that define the patient’s path of care, Process Mining (PM) is assuming an emerging role in clinical data analytics. PM’s ability to exploit time-series data and to build processes without any a priori knowledge suggests interesting synergies with the most common statistical analyses in healthcare, in particular survival analysis. In this work we demonstrate contributions of our process-oriented approach in analyzing a real-world retrospective dataset of patients treated for advanced melanoma at the Lausanne University Hospital. Addressing the clinical questions raised by our oncologists, we integrated PM in almost all the steps of a common statistical analysis. We show: (1) how PM can be leveraged to improve the quality of the data (data cleaning/pre-processing), (2) how PM can provide efficient data visualizations that support and/or suggest clinical hypotheses, also allowing to check the consistency between real and expected processes (descriptive statistics), and (3) how PM can assist in querying or re-expressing the data in terms of pre-defined reference workflows for testing survival differences among sub-cohorts (statistical inference). We exploit a rich set of PM tools for querying the event logs, inspecting the processes using statistical hypothesis testing, and performing conformance checking analyses to identify patterns in patient clinical paths and study the effects of different treatment sequences in our cohort.
ABSTRACT Using real-world evidence in biomedical research, an indispensable complement to clinical trials, requires access to large quantities of patient data that are typically held separately by multiple healthcare institutions. Centralizing those data for a study is often infeasible due to privacy and security concerns. Federated analytics is rapidly emerging as a solution for enabling joint analyses of distributed medical data across a group of institutions, without sharing patient-level data. However, existing approaches either provide only limited protection of patients’ privacy by requiring the institutions to share intermediate results, which can in turn leak sensitive patient-level information, or they sacrifice the accuracy of results by adding noise to the data to mitigate potential leakage. We propose FAMHE, a novel federated analytics system that, based on multiparty homomorphic encryption (MHE), enables privacy-preserving analyses of distributed datasets by yielding highly accurate results without revealing any intermediate data. We demonstrate the applicability of FAMHE to essential biomedical analysis tasks, including Kaplan-Meier survival analysis in oncology and genome-wide association studies in medical genetics. Using our system, we accurately and efficiently reproduce two published centralized studies in a federated setting, enabling biomedical insights that are not possible from individual institutions alone. Our work represents a necessary key step towards overcoming the privacy hurdle in enabling multi-centric scientific collaborations.
The function of a protein depends on its three-dimensional structure. Current approaches based on homology for predicting a given protein's function do not work well at scale. In this work, we propose a representation of proteins that explicitly encodes secondary and tertiary structure into fix-sized images. In addition, we present a neural network architecture that exploits our data representation to perform protein function prediction. We validate the effectiveness of our encoding method and the strength of our neural network architecture through a 5-fold cross validation over roughly 63 thousand images, achieving an accuracy of 80% across 8 distinct classes. Our novel approach of encoding and classifying proteins is suitable for real-time processing, leading to high-throughput analysis.
Abstract Mutations in the G protein-coupled receptor (GPCR) rhodopsin are a common cause of autosomal dominant retinitis pigmentosa, a blinding disease. Rhodopsin self-associates in the membrane, and the purified monomeric apo-protein opsin dimerizes in vitro as it transitions from detergent micelles to reconstitute into a lipid bilayer. We previously reported that the retinitis pigmentosa-linked F220C opsin mutant fails to dimerize in vitro, reconstituting as a monomer. Using fluorescence-based assays and molecular dynamics simulations we now report that whereas wild-type and F220C opsin display distinct dimerization propensities in vitro as previously shown, they both dimerize in the plasma membrane of HEK293 cells. Unexpectedly, molecular dynamics simulations show that F220C opsin forms an energetically favored dimer in the membrane when compared with the wild-type protein. The conformation of the F220C dimer is unique, with transmembrane helices 5 and 6 splayed apart, promoting widening of the intracellular vestibule of each protomer and influx of water into the protein interior. FRET experiments with SNAP-tagged wild-type and F220C opsin expressed in HEK293 cells are consistent with this conformational difference. We speculate that the unusual mode of dimerization of F220C opsin in the membrane may have physiological consequences.
