首页|University of Utah Researcher Yields New Findings on Machine Learning (Validatin g, Implementing, and Monitoring Machine Learning Solutions in the Clinical Labor atory Safely and Effectively)
University of Utah Researcher Yields New Findings on Machine Learning (Validatin g, Implementing, and Monitoring Machine Learning Solutions in the Clinical Labor atory Safely and Effectively)
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 – Investigators publish new report on ar tificial intelligence. According to news originating from Salt Lake City, Utah, by NewsRx correspondents, research stated, “Machine learning solutions offer tre mendous promise for improving clinical and laboratory operations in pathology. P roof-of-concept descriptions of these approaches have become commonplace in labo ratory medicine literature, but only a scant few of these have been implemented within clinical laboratories, owing to the often substantial barriers in validat ing, implementing, and monitoring these applications in practice.” The news correspondents obtained a quote from the research from University of Ut ah: “This minireview aims to highlight the key considerations in each of these steps. Content: Effective and responsible applications of machine learning in cl inical laboratories require robust validation prior to implementation. A compreh ensive validation study involves a critical evaluation of study design, data eng ineering and interoperability, target label definition, metric selection, genera lizability and applicability assessment, algorithmic fairness, and explainabilit y. While the main text highlights these concepts in broad strokes, a supplementa ry code walk-through is also provided to facilitate a more practical understandi ng of these topics using a real-world classification task example, the detection of saline-contaminated chemistry panels. Following validation, the laboratorian ’s role is far from over. Implementing machine learning solutions requires an in terdisciplinary effort across several roles in an organization. We highlight the key roles, responsibilities, and terminologies for successfully deploying a val idated solution into a live production environment. Finally, the implemented sol ution must be routinely monitored for signs of performance degradation and updat ed if necessary.”
University of UtahSalt Lake CityUtahUnited StatesNorth and Central AmericaCyborgsEmerging TechnologiesMach ine Learning
NETL
NSTL
