Electronic patient-reported outcomes and machine learning in predicting immune-related adverse events of immune checkpoint inhibitor therapies.

BACKGROUND: Immune-checkpoint inhibitors (ICIs) have introduced novel immune-related adverse events (irAEs), arising from various organ systems without strong timely dependency on therapy dosing. Early detection of irAEs could result in improved toxicity profile and quality of life. Symptom data collected by electronic (e) patient-reported outcomes (PRO) could be used as an input for machine learning (ML) based prediction models for the early detection of irAEs. METHODS: The utilized dataset consisted of two data sources. The first dataset consisted of 820 completed symptom questionnaires from 34 ICI treated advanced cancer patients, including 18 monitored symptoms collected using the Kaiku Health digital platform. The second dataset included prospectively collected irAE data, Common Terminology Criteria for Adverse Events (CTCAE) class, and the severity of 26 irAEs. The ML models were built using extreme gradient boosting algorithms. The first model was trained to detect the presence and the second the onset of irAEs. RESULTS: The model trained to predict the presence of irAEs had an excellent performance based on four metrics: accuracy score 0.97, Area Under the Curve (AUC) value 0.99, F1-score 0.94 and Matthew's correlation coefficient (MCC) 0.92. The prediction of the irAE onset was more difficult with accuracy score 0.96, AUC value 0.93, F1-score 0.66 and MCC 0.64 but the model performance was still at a good level. CONCLUSION: The current study suggests that ML based prediction models, using ePRO data as an input, can predict the presence and onset of irAEs with a high accuracy, indicating that ePRO follow-up with ML algorithms could facilitate the detection of irAEs in ICI-treated cancer patients. The results should be validated with a larger dataset. Trial registration Clinical Trials Register (NCT3928938), registration date the 26th of April, 2019.

ePRO symptom follow-up of colorectal cancer patients receiving oxaliplatin-based adjuvant chemotherapy is feasible and enhances the quality of patient care: a prospective multicenter study.

PURPOSE: Electronic (e) patient-reported outcomes (PROs) have been shown to improve the quality of life and survival in chemotherapy treated advanced cancer patients. We hypothesized that multidimensional ePRO centered approach could improve symptom management, streamline patient flow, and optimize the use of healthcare resources. METHODS: In this multicenter trial (NCT04081558), colorectal cancer (CRC) patients receiving oxaliplatin-based chemotherapy as adjuvant or in the first- or second-line setting in advanced disease were included in the prospective ePRO cohort, while a comparative retrospective cohort was collected from the same institutes. The investigated tool consisted of a weekly e-symptom questionnaire integrated to an urgency algorithm and laboratory value interface, which generated semi-automated decision support for chemotherapy cycle prescription and individualized symptom management. RESULTS: Recruitment to the ePRO cohort occurred 1/2019-1/2021 (n = 43). The comparator group (n = 194) consisted of patients treated in the same institutes 1-7/2017. The analysis was limited to adjuvant treated (n = 36 and n = 35). The feasibility of the ePRO follow-up was good with 98% reporting easy usage and 86% improved care, while health care personnel valued the easy use and logical workflow. In the ePRO cohort, 42% needed a phone call before planned chemotherapy cycles, while this was 100% in the retrospective cohort (p = 1.4e-8). Peripheral sensory neuropathy was detected significantly earlier with ePRO followed (p = 1e-5) but did not translate to earlier dose reduction, delays, or unplanned therapy termination compared to the retrospective cohort. CONCLUSION: The results suggest that the investigated approach is feasible and streamlines workflow. Earlier symptom detection may improve the quality in cancer care.

Follow-Up of Cancer Patients Receiving Anti-PD-(L)1 Therapy Using an Electronic Patient-Reported Outcomes Tool (KISS): Prospective Feasibility Cohort Study.

BACKGROUND: Immune checkpoint inhibitors (ICIs) have become a standard of care for various tumor types. Their unique spectrum of side effects demands continuous and long-lasting assessment of symptoms. Electronic patient-reported outcome (ePRO) follow-up has been shown to improve survival and quality of life of cancer patients treated with chemotherapy. OBJECTIVE: This study aimed to investigate whether ePRO follow-up of cancer patients treated with ICIs is feasible. The study analyzed (1) the variety of patient reported symptoms, (2) etiology of alerts, (3) symptom correlations, and (4) patient compliance. METHODS: In this prospective, one-arm, multi-institutional study, we recruited adult cancer patients whose advanced cancer was treated with anti-programmed cell death protein 1 (PD)- ligand (L)1 agents in outpatient settings. The ePRO tool consisted of a weekly questionnaire evaluating the presence of typical side effects, with an algorithm assessing the severity of the symptom according to National Cancer Institute Common Terminology Criteria for Adverse Events and an urgency algorithm sending alerts to the care team. A patient experience survey was conducted monthly. The patients were followed up to 6 months or until disease progression. RESULTS: A total of 889 symptom questionnaires was completed by 37 patients (lung cancer, n=15; melanoma, n=9; genitourinary cancer, n=9; head and neck cancer, n=4). Patients showed good adherence to ePRO follow-up. The most common grade 1 symptoms were fatigue (28%) and itching (13%), grade 2 symptoms were loss of appetite (12%) and nausea (12%), and grade 3-4 symptoms were cough (6%) and loss of appetite (4%). The most common reasons for alerts were loss of appetite and shortness of breath. In the treatment benefit analysis, positive correlations were seen between clinical benefit and itching as well as progressive disease and chest pain. CONCLUSIONS: According to the results, ePRO follow-up of cancer patients receiving ICIs is feasible. ePROs capture a wide range of symptoms. Some symptoms correlate to treatment benefit, suggesting that individual prediction models could be generated. TRIAL REGISTRATION: Clinical Trials Register, NCT3928938; https://clinicaltrials.gov/ct2/show/NCT03928938.

ePROs in the follow-up of cancer patients treated with immune checkpoint inhibitors: a retrospective study.

PURPOSE: Patient-reported outcome (PRO) follow-up has been shown to improve quality of life (QoL) and survival of cancer patients receiving chemotherapy. Kaiku Health application is a web-based electronic PRO (ePRO) tool which is designed for follow-up of cancer patients receiving immune checkpoint inhibitors (ICI). Purpose of the current study is to investigate whether symptoms collected by Kaiku Health ePRO tool on cancer patients receiving immune checkpoint inhibitors (ICI) follows to symptoms reported in clinical trials and whether coupling of specific symptoms does occur. METHODS: We retrospectively collected data on symptom timing and severity, and QoL of patients followed with Kaiku Health IO module in two Finnish cancer centers between 2017 and 2018. Kaiku Health IO module consists of 18 adaptive questions, which assess the presence and severity of symptoms. Patients were requested (via e-mail) to fill online symptom questionnaires with 3-7 day interval and QoL questionnaires (QLQ-C30) with 1-2 month interval. RESULTS: The IO module was used to follow 37 patients who had filled in total 559 symptom questionnaires. There was good adherence to ePRO follow-up with a median of 11 questionnaires filled per patient. The reported symptoms and their severity follow closely what has been seen in clinical trials investigating ICIs. Correlation analysis of the symptoms showed the strongest positive correlations between itching and rash; nausea and vomiting, decreased appetite, or stomach pain; cough and shortness of breath. CONCLUSIONS: The results of the current study suggest that real-world symptom data collected through the ePRO application on cancer patients receiving ICI therapy aligns with the data from clinical trials. Correlations between different symptoms occur, which might reflect therapeutic efficiency, side effects, or tumor progression. These correlations should be further investigated with data coupled to clinical outcomes.

Production of alkanes from CO2 by engineered bacteria.

BACKGROUND: Microbial biosynthesis of alkanes is considered a promising method for the sustainable production of drop-in fuels and chemicals. Carbon dioxide would be an ideal carbon source for these production systems, but efficient production of long carbon chains from CO2 is difficult to achieve in a single organism. A potential solution is to employ acetogenic bacteria for the reduction of CO2 to acetate, and engineer a second organism to convert the acetate into long-chain hydrocarbons. RESULTS: In this study, we demonstrate alkane production from CO2 by a system combining the acetogen Acetobacterium woodii and a non-native alkane producer Acinetobacter baylyi ADP1 engineered for alkane production. Nine synthetic two-step alkane biosynthesis pathways consisting of different aldehyde- and alkane-producing enzymes were combinatorically constructed and expressed in A. baylyi. The aldehyde-producing enzymes studied were AAR from Synechococcus elongatus, Acr1 from A. baylyi, and a putative dehydrogenase from Nevskia ramosa. The alkane-producing enzymes were ADOs from S. elongatus and Nostoc punctiforme, and CER1 from Arabidopsis thaliana. The performance of the pathways was evaluated with a twin-layer biosensor, which allowed the monitoring of both the intermediate (fatty aldehyde), and end product (alkane) formation. The highest alkane production, as indicated by the biosensor, was achieved with a pathway consisting of AAR and ADO from S. elongatus. The performance of this pathway was further improved by balancing the relative expression levels of the enzymes to limit the accumulation of the intermediate fatty aldehyde. Finally, the acetogen A. woodii was used to produce acetate from CO2 and H2, and the acetate was used for alkane production by the engineered A. baylyi, thereby leading to the net production of long-chain alkanes from CO2. CONCLUSIONS: A modular system for the production of drop-in liquid fuels from CO2 was demonstrated. Among the studied synthetic pathways, the combination of ADO and AAR from S. elongatus was found to be the most efficient in heterologous alkane production in A. baylyi. Furthermore, limiting the accumulation of the fatty aldehyde intermediate was found to be beneficial for the alkane production. Nevertheless, the alkane productivity of the system remained low, representing a major challenge for future research.