首页|Data on Artificial Intelligence Reported by Zhusi Zhong and Colleagues [MRI-Based Prediction of Clinical Improvement Following Ventricular Shunt Placeme nt for Normal Pressure Hydrocephalus (NPH): Development and Evaluation of an Int egrated ...]
Data on Artificial Intelligence Reported by Zhusi Zhong and Colleagues [MRI-Based Prediction of Clinical Improvement Following Ventricular Shunt Placeme nt for Normal Pressure Hydrocephalus (NPH): Development and Evaluation of an Int egrated ...]
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-New research on Artificial Intelligence is the su bject of a report. According to news originating from Providence, Rhode Island, by NewsRx correspondents, research stated, "Symptoms of normal pressure hydrocep halus (NPH) are sometimes refractory to shunt placement, with limited ability to predict improvement for individual patients. We evaluated an MRI-based artifici al intelligence method to predict post-shunt NPH symptom improvement." Our news journalists obtained a quote from the research, "NPH patients who under went magnetic resonance imaging (MRI) prior to shunt placement at a single cente r (2014-2021) were identified. Twelvemonth post-shunt improvement in modified R ankin Scale (mRS), incontinence, gait, and cognition were retrospectively abstra cted from clinical documentation. 3D deep residual neural networks were built on skull stripped T2-weighted and fluid attenuated inversion recovery (FLAIR) imag es. Predictions based on both sequences were fused by additional network layers. Patients from 2014-2019 were used for parameter optimization, while those from 2020-2021 were used for testing. Models were validated on an external validation dataset from a second institution (n=33). Of 249 patients, n=201 and n=185 were included in the T2-based and FLAIR-based models according to imaging availabili ty. The combination of T2- weighted and FLAIR sequences offered the best performa nce in mRS and gait improvement predictions relative to models trained on imagin g acquired using only one sequence, with AUROC values of 0.7395 [0.5765-0.9024] for mRS and 0.8816 [0.8030- 0.9602] for gait. For urinary incontinence and cognition, com bined model performances on predicting outcomes were similar to FLAIR-only perfo rmance, with AUROC values of 0.7874 [0.6845-0.8903] and 0.7230 [0.5600-0.8859]. Application of a combined algorithm using both T2-weighted and FLAIR sequences offered the bes t image-based prediction of post-shunt symptom improvement, particularly for gai t and overall function in terms of mRS."
ProvidenceRhode IslandUnited StatesNorth and Central AmericaAlgorithmsArtificial IntelligenceBrain Diseases and ConditionsCardiologyCentral Nervous System Diseases and ConditionsCybo rgsEmerging TechnologiesHealth and MedicineHydrocephalusIntracranial Hyp ertensionMachine LearningNervous System Diseases and ConditionsNormal Pres sure Hydrocephalus
NETL
NSTL
