AutoModel and Medical Data
Dear RapidMiner Friends,
Congrats for implementing the AutoModel tool which I consider a critical step for more acceptance in a #noblackboxes community as the one I am working in. This is a huge step forward! Try to understand how a physician is taking a decision based on the signs and symptoms a patient is presenting with. Additional to his/her clinical view (best translated as an optimized model based on years of clinical experience), the physician looks at new data from a patient to provide the best care at a point in time. For AI or any type of advanced analytics to be integrated in the clinical decision taking process, any new data or model needs to generate additional knowledge or wisdom in this intellectual process. The medical community is not requesting a full understanding of the algorithms used in AI, but at least the findings provided by e.g. the Automodel tool should be clarified. Therefore I would like to prepare some kind of clinical translation of the results from Automodel on a real dataset based on patients admitted to a critical care facility. The label is the survival or no survival during the ICU stay. All other attributes are related to comorbidities of each patient. I am looking forward to your conclusions on the results and it might be even more interesting to have a Skype or RingCentral meeting scheduled in the near future.