首页|Technische Hochschule Nurnberg Georg Simon Ohm Reports Findings in Sepsis (A mac hine learning framework for interpretable predictions in patient pathways: The c ase of predicting ICU admission for patients with symptoms of sepsis)
Technische Hochschule Nurnberg Georg Simon Ohm Reports Findings in Sepsis (A mac hine learning framework for interpretable predictions in patient pathways: The c ase of predicting ICU admission for patients with symptoms of sepsis)
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 Blood Diseases and Con ditions - Sepsis is the subject of a report. According to news reporting origina ting from Nuremberg, Germany, by NewsRx correspondents, research stated, "Proact ive analysis of patient pathways helps healthcare providers anticipate treatment -related risks, identify outcomes, and allocate resources. Machine learning (ML) can leverage a patient's complete health history to make informed decisions abo ut future events." Financial support for this research came from Friedrich-Alexander-Universitat Er langen-Nurnberg. Our news editors obtained a quote from the research from Technische Hochschule N urnberg Georg Simon Ohm, "However, previous work has mostly relied on so-called black-box models, which are unintelligible to humans, making it difficult for cl inicians to apply such models. Our work introduces PatWay-Net, an ML framework d esigned for interpretable predictions of admission to the intensive care unit (I CU) for patients with symptoms of sepsis. We propose a novel type of recurrent n eural network and combine it with multi-layer perceptrons to process the patient pathways and produce predictive yet interpretable results. We demonstrate its u tility through a comprehensive dashboard that visualizes patient health trajecto ries, predictive outcomes, and associated risks. Our evaluation includes both pr edictive performance - where PatWay-Net outperforms standard models such as deci sion trees, random forests, and gradient-boosted decision trees - and clinical u tility, validated through structured interviews with clinicians."
NurembergGermanyEuropeBlood Diseas es and ConditionsBloodstream InfectionCyborgsEmerging TechnologiesHealth and MedicineMachine LearningSepsisSepticemia
NETL
NSTL
