首页|University of Applied Sciences and Arts Northwestern Switzerland (FHNW) Reports Findings in Cancer (Towards an early warning system for monitoring of cancer pat ients using hybrid interactive machine learning)
University of Applied Sciences and Arts Northwestern Switzerland (FHNW) Reports Findings in Cancer (Towards an early warning system for monitoring of cancer pat ients using hybrid interactive machine learning)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – New research on Cancer is the subject of a report. According to news originating from Olten, Switzerland, by NewsRx co rrespondents, research stated, “The use of smartphone apps in cancer patients un dergoing systemic treatment can promote the early detection of symptoms and ther apy side effects and may be supported by machine learning (ML) for timely adapta tion of therapies and reduction of adverse events and unplanned admissions. We a imed to create an Early Warning System (EWS) to predict situations where support ive interventions become necessary to prevent unplanned visits.” Our news journalists obtained a quote from the research from the University of A pplied Sciences and Arts Northwestern Switzerland (FHNW), “For this, dynamically collected standardized electronic patient reported outcome (ePRO) data were ana lyzed in context with the patient’s individual journey. Information on well-bein g, vital parameters, medication, and free text were also considered for establis hing a hybrid ML model. The goal was to integrate both the strengths of ML in si fting through large amounts of data and the long-standing experience of human ex perts. Given the limitations of highly imbalanced datasets (where only very few adverse events are present) and the limitations of humans in overseeing all poss ible cause of such events, we hypothesize that it should be possible to combine both in order to partially overcome these limitations. The prediction of unplann ed visits was achieved by employing a white-box ML algorithm (i.e., rule learner ), which learned rules from patient data (i.e., ePROs, vital parameters, free te xt) that were captured via a medical device smartphone app. Those rules indicate d situations where patients experienced unplanned visits and, hence, were captur ed as alert triggers in the EWS. Each rule was evaluated based on a cost matrix, where false negatives (FNs) have higher costs than false positives (FPs, i.e., false alarms). Rules were then ranked according to the costs and priority was gi ven to the least expensive ones. Finally, the rules with higher priority were re viewed by two oncological experts for plausibility check and for extending them with additional conditions. This hybrid approach comprised the application of a sensitive ML algorithm producing several potentially unreliable, but fully human - interpretable and -modifiable rules, which could then be adjusted by human expe rts. From a cohort of 214 patients and more than 16’000 available data entries, the machine-learned rule set achieved a recall of 19% on the entir e dataset and a precision of 5%. We compared this performance to a set of conditions that a human expert had defined to predict adverse events. Thi s ‘human baseline’ did not discover any of the adverse events recorded in our da taset, i.e., it came with a recall and precision of 0%. Despite mor e plentiful results were expected by our machine learning approach, the involved medical experts a) had understood and were able to make sense of the rules and b) felt capable to suggest modification to the rules, some of which could potent ially increase their precision. Suggested modifications of rules included e.g., adding or tightening certain conditions to make them less sensitive or changing the rule consequences: sometimes further monitoring the situation, applying cert ain test (such as a CRP test) or applying some simple pain-relieving measures wa s deemed sufficient, making a costly consultation with the physician unnecessary . We can thus conclude that it is possible to apply machine learning as an inspi rational tool that can help human experts to formulate rules for an EWS. While h umans seem to lack the ability to define such rules without such support, they a re capable of modifying the rules to increase their precision and generalizabili ty.”
OltenSwitzerlandEuropeAdverse Drug ReactionsCancerCyborgsDrugs and TherapiesEmerging TechnologiesHealth and MedicineMachine LearningOncology
NETL
NSTL
