Radiomics analysis of baseline computed tomography to predict oncological outcomes in patients treated for resectable colorectal cancer liver metastasis.

OBJECTIVE: The purpose of this study was to determine and compare the performance of pre-treatment clinical risk score (CRS), radiomics models based on computed (CT), and their combination for predicting time to recurrence (TTR) and disease-specific survival (DSS) in patients with colorectal cancer liver metastases. METHODS: We retrospectively analyzed a prospectively maintained registry of 241 patients treated with systemic chemotherapy and surgery for colorectal cancer liver metastases. Radiomics features were extracted from baseline, pre-treatment, contrast-enhanced CT images. Multiple aggregation strategies were investigated for cases with multiple metastases. Radiomics signatures were derived using feature selection methods. Random survival forests (RSF) and neural network survival models (DeepSurv) based on radiomics features, alone or combined with CRS, were developed to predict TTR and DSS. Leveraging survival models predictions, classification models were trained to predict TTR within 18 months and DSS within 3 years. Classification performance was assessed with area under the receiver operating characteristic curve (AUC) on the test set. RESULTS: For TTR prediction, the concordance index (95% confidence interval) was 0.57 (0.57-0.57) for CRS, 0.61 (0.60-0.61) for RSF in combination with CRS, and 0.70 (0.68-0.73) for DeepSurv in combination with CRS. For DSS prediction, the concordance index was 0.59 (0.59-0.59) for CRS, 0.57 (0.56-0.57) for RSF in combination with CRS, and 0.60 (0.58-0.61) for DeepSurv in combination with CRS. For TTR classification, the AUC was 0.33 (0.33-0.33) for CRS, 0.77 (0.75-0.78) for radiomics signature alone, and 0.58 (0.57-0.59) for DeepSurv score alone. For DSS classification, the AUC was 0.61 (0.61-0.61) for CRS, 0.57 (0.56-0.57) for radiomics signature, and 0.75 (0.74-0.76) for DeepSurv score alone. CONCLUSION: Radiomics-based survival models outperformed CRS for TTR prediction. More accurate, noninvasive, and early prediction of patient outcome may help reduce exposure to ineffective yet toxic chemotherapy or high-risk major hepatectomies.

Remote Patient Monitoring Program for COVID-19 Patients Following Hospital Discharge: A Cross-Sectional Study.

Background: The COVID-19 pandemic created an urgent need to act to reduce the spread of the virus and alleviate congestion from healthcare services, protect healthcare providers, and help them maintain satisfactory quality and safety of care. Remote COVID-19 monitoring platforms emerged as potential solutions. Objective: The purpose of this study was to evaluate the capacity and contribution of two different platforms used to remotely monitor patients with COVID-19 to maintain quality, safety, and patient engagement in care, as well as their acceptability, usefulness, and user-friendliness from the user's perspective. The first platform is focused on telecare phone calls (Telecare-Covid), and the second is a telemonitoring app (CareSimple-Covid). Methods: We performed a cross-sectional study. The data were collected through a phone survey from May to August 2020. Data were analyzed using descriptive statistics and t-test analysis. Participants' responses and comments on open-ended questions were analyzed using content analysis to identify certain issues and challenges and potential avenues for improving the platforms. Results: Fifty one patients participated in the study. Eighteen participants used the CareSimple-Covid platform and 33 participants used the Telecare-Covid platform. Overall, the satisfaction rate for quality and safety of care for the two platforms was 80%. Over 88% of the users on each platform considered the platforms' services to be engaging, useful, user-friendly, and appropriate to their needs. The survey identified a few significant differences in users' perceptions of each platform: empathy toward users and the quality and safety of the care received were rated significantly higher on the CareSimple-Covid platform than on the Telecare-Covid platform. Users appreciated four aspects of these telehealth approaches: (1) the ease of access to services and the availability of care team members; (2) the user-friendliness of the platforms; (3) the continuity of care provided, and (4) the wide range of services delivered. Users identified some technical limitations and raised certain issues, such as the importance of maintaining human contact, data security, and confidentiality. Improvement suggestions include promoting access to connected devices; enhancing communications between institutions, healthcare users, and the public on confidentiality and personal data protection standards; and integrating a participatory approach to telehealth platform development and deployment efforts. Conclusion: This study provides preliminary evidence that the two remote monitoring platforms are well-received by users, with very few significant differences between them concerning users' experiences and views. This type of program could be considered for use in a post-pandemic era and for other post-hospitalization clienteles. To maximize efficiency, the areas for improvement and the issues identified should be addressed with a patient-centered approach.

Considerations for the Design and Implementation of COVID-19 Contact Tracing Apps: Scoping Review.

BACKGROUND: Given the magnitude and speed of SARS-CoV-2 transmission, achieving timely and effective manual contact tracing has been a challenging task. Early in the pandemic, contact tracing apps generated substantial enthusiasm due to their potential for automating tracing and reducing transmission rates while enabling targeted confinement strategies. However, although surveys demonstrate public interest in using such apps, their actual uptake remains limited. Their social acceptability is challenged by issues around privacy, fairness, and effectiveness, among other concerns. OBJECTIVE: This study aims to examine the extent to which design and implementation considerations for contact tracing apps are detailed in the available literature, focusing on aspects related to participatory and responsible eHealth innovation, and synthesize recommendations that support the development of successful COVID-19 contact tracing apps and related eHealth technologies. METHODS: Searches were performed on five databases, and articles were selected based on eligibility criteria. Papers pertaining to the design, implementation, or acceptability of contact tracing apps were included. Articles published since 2019, written in English or French, and for which the full articles were available were considered eligible for analysis. To assess the scope of the knowledge found in the current literature, we used three complementary frameworks: (1) the Holistic Framework to Improve the Uptake and Impact of eHealth Technologies, (2) the Montreal model, and (3) the Responsible Innovation in Health Assessment Tool. RESULTS: A total of 63 articles qualified for the final analysis. Less than half of the selected articles cited the need for a participatory process (n=25, 40%), which nonetheless was the most frequently referenced item of the Framework to Improve the Uptake and Impact of eHealth Technologies. Regarding the Montreal model, stakeholder consultation was the most frequently described level of engagement in the development of contact tracing apps (n=24, 38%), while collaboration and partnership were cited the least (n=2, 3%). As for the Responsible Innovation in Health framework, all the articles (n=63, 100%) addressed population health, whereas only 2% (n=1) covered environmental considerations. CONCLUSIONS: Most studies lacked fundamental aspects of eHealth development and implementation. Our results demonstrate that stakeholders of COVID-19 contact tracing apps lack important information to be able to critically appraise this eHealth innovation. This may have contributed to the modest uptake of contact tracing apps worldwide. We make evidence-informed recommendations regarding data management, communication, stakeholder engagement, user experience, and implementation strategies for the successful and responsible development of contact tracing apps.