Search

Abstract Background Artificial intelligence (AI) has the potential to transform our healthcare systems significantly. New AI technologies based on machine learning approaches should play a key role in clinical decision-making in the future. However, their implementation in health care settings remains limited, mostly due to a lack of robust validation procedures. There is a need to develop reliable assessment frameworks for the clinical validation of AI. We present here an approach for assessing AI for predicting treatment response in triple-negative breast cancer (TNBC), using real-world data and molecular -omics data from clinical data warehouses and biobanks. Methods The European “ITFoC (Information Technology for the Future Of Cancer)” consortium designed a framework for the clinical validation of AI technologies for predicting treatment response in oncology. Results This framework is based on seven key steps specifying: (1) the intended use of AI, (2) the target population, (3) the timing of AI evaluation, (4) the datasets used for evaluation, (5) the procedures used for ensuring data safety (including data quality, privacy and security), (6) the metrics used for measuring performance, and (7) the procedures used to ensure that the AI is explainable. This framework forms the basis of a validation platform that we are building for the “ITFoC Challenge”. This community-wide competition will make it possible to assess and compare AI algorithms for predicting the response to TNBC treatments with external real-world datasets. Conclusions The predictive performance and safety of AI technologies must be assessed in a robust, unbiased and transparent manner before their implementation in healthcare settings. We believe that the consideration of the ITFoC consortium will contribute to the safe transfer and implementation of AI in clinical settings, in the context of precision oncology and personalized care.

Background: Artificial intelligence (AI) has the potential to transform our healthcare systems significantly. New AI technologies based on machine learning approaches should play a key role in clinical decision-making in the future. However, their implementation in health care settings remains limited, mostly due to a lack of robust validation procedures. There is a need to develop reliable assessment frameworks for the clinical validation of AI. We present here an approach for assessing AI for predicting treatment response in triple-negative breast cancer (TNBC), using real-world data and molecular -omics data from clinical data warehouses and biobanks. Methods: The European "ITFoC (Information Technology for the Future Of Cancer)" consortium designed a framework for the clinical validation of AI technologies for predicting treatment response in oncology. Results: This framework is based on seven key steps specifying: (1) the intended use of AI, (2) the target population, (3) the timing of AI evaluation, (4) the datasets used for evaluation, (5) the procedures used for ensuring data safety (including data quality, privacy and security), (6) the metrics used for measuring performance, and (7) the procedures used to ensure that the AI is explainable. This framework forms the basis of a validation platform that we are building for the "ITFoC Challenge". This community-wide competition will make it possible to assess and compare AI algorithms for predicting the response to TNBC treatments with external real-world datasets. Conclusions: The predictive performance and safety of AI technologies must be assessed in a robust, unbiased and transparent manner before their implementation in healthcare settings. We believe that the consideration of the ITFoC consortium will contribute to the safe transfer and implementation of AI in clinical settings, in the context of precision oncology and personalized care. [ABSTRACT FROM AUTHOR]

Background: Computerized decision support systems (CDSSs) are computer programs that provide doctors with person-specific, actionable recommendations, or management options that are intelligently filtered or presented at appropriate times to enhance health care. CDSSs might be integrated with patient electronic health records (EHRs) and evidence-based knowledge. Methods Design: The Computerized DEcision Support in ONCOlogy (ONCO CODES) trial is a pragmatic, parallel group, randomized controlled study with 1:1 allocation ratio. The trial is designed to evaluate the effectiveness on clinical practice and quality of care of a multi-specialty collection of patient-specific reminders generated by a CDSS in the IRCCS Istituto Scientifico Romagnolo per lo Studio e la Cura dei Tumori (IRST) hospital. We hypothesize that the intervention can increase clinician adherence to guidelines and, eventually, improve the quality of care offered to cancer patients. The primary outcome is the rate at which the issues reported by the reminders are resolved, aggregating specialty and primary care reminders. We will include all the patients admitted to hospital services. All analyses will follow the intention to treat principle. Discussion: The results of our study will contribute to the current understanding of the effectiveness of CDSSs in cancer hospitals, thereby informing healthcare policy about the potential role of CDSS use. Furthermore, the study will inform whether CDSS may facilitate the integration of primary care in cancer settings, known to be usually limited. The increasing use of and familiarity with advanced technology among new generations of physicians may support integrated approaches to be tested in pragmatic studies determining the optimal interface between primary and oncology care. [ABSTRACT FROM AUTHOR]