首页|University of Queensland Reports Findings in HIV/AIDS (Development and validatio n of supervised machine learning multivariable prediction models for the diagnos is of Pneumocystis jirovecii pneumonia using nasopharyngeal swab PCR in adults i n a ...)
University of Queensland Reports Findings in HIV/AIDS (Development and validatio n of supervised machine learning multivariable prediction models for the diagnos is of Pneumocystis jirovecii pneumonia using nasopharyngeal swab PCR in adults i n a ...)
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 Immune System Diseases and Conditions - HIV/AIDS is the subject of a report. According to news reporti ng originating in Herston, Australia, by NewsRx journalists, research stated, “T he global burden of the opportunistic fungal disease Pneumocystis jirovecii pneu monia (PJP) remains substantial. Polymerase chain reaction (PCR) on nasopharynge al swabs (NPS) has high specificity and may be a viable alternative to the gold standard diagnostic of PCR on invasively collected lower respiratory tract speci mens, but has low sensitivity.” Financial supporters for this research include UK Government, Royal Australasian College of Physicians. The news reporters obtained a quote from the research from the University of Que ensland, “Sensitivity may be improved by incorporating NPS PCR results into mach ine learning models. Three supervised multivariable diagnostic models (random fo rest, logistic regression and extreme gradient boosting) were constructed and va lidated using a 111-person Australian dataset. The predictors were age, gender, immunosuppression type and NPS PCR result. Model performance metrics such as acc uracy, sensitivity, specificity and predictive values were compared to select th e best-performing model. The logistic regression model performed best, with 80% accuracy, improving sensitivity to 86% and maintaining acceptable specificity of 70%. Using this model, positive and negative NPS PCR results indicated post-test probabilities of 84% (likely PJP) and 26% (unlikely PJP), respectively. The logistic regression model s hould be externally validated in a wider range of settings.”
HerstonAustraliaAustralia and New Ze alandCyborgsDiagnostics and ScreeningEmerging TechnologiesHIV/AIDSHeal th and MedicineImmune System Diseases and ConditionsInfectious DiseaseLung Diseases and ConditionsMachine LearningPneumocystisPneumoniaPrimate Len tivirusesPulmonologyRNA VirusesRespiratory TractRespiratory Tract Diseas es and ConditionsRespiratory Tract InfectionsRetroviridaeVertebrate Viruse sViral Sexually Transmitted Diseases and Conditions
NETL
NSTL
