PT  - JOURNAL ARTICLE
AU  - Leary, Owen P.
AU  - Zhong, Zhusi
AU  - Bi, Lulu
AU  - Jiao, Zhicheng
AU  - Dai, Yu-Wei
AU  - Ma, Kevin
AU  - Sayied, Shanzeh
AU  - Kargilis, Daniel
AU  - Imami, Maliha
AU  - Zhao, Lin-Mei
AU  - Feng, Xue
AU  - Riccardello, Gerald
AU  - Collins, Scott
AU  - Svokos, Konstantina
AU  - Moghekar, Abhay
AU  - Yang, Li
AU  - Bai, Harrison
AU  - Klinge, Petra M.
AU  - Boxerman, Jerrold L.
TI  - MRI-Based Prediction of Clinical Improvement after Ventricular Shunt Placement for Normal Pressure Hydrocephalus: Development and Evaluation of an Integrated Multisequence Machine Learning Algorithm
AID  - 10.3174/ajnr.A8372
DP  - 2024 Sep 12
TA  - American Journal of Neuroradiology
4099  - http://www.ajnr.org/content/early/2024/09/12/ajnr.A8372.short
4100  - http://www.ajnr.org/content/early/2024/09/12/ajnr.A8372.full
AB  - BACKGROUND AND PURPOSE: Symptoms of normal pressure hydrocephalus (NPH) are sometimes refractory to shunt placement, with limited ability to predict improvement for individual patients. We evaluated an MRI-based artificial intelligence method to predict postshunt NPH symptom improvement.MATERIALS AND METHODS: Patients with NPH who underwent MRI before shunt placement at a single center (2014–2021) were identified. Twelve-month postshunt improvement in mRS, incontinence, gait, and cognition were retrospectively abstracted from clinical documentation. 3D deep residual neural networks were built on skull-stripped T2-weighted and FLAIR images. 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 data set from a second institution (n = 33).RESULTS: Of 249 patients, n = 201 and n = 185 were included in the T2-based and FLAIR-based models according to imaging availability. The combination of T2-weighted and FLAIR sequences offered the best performance in mRS and gait improvement predictions relative to models trained on imaging acquired by using only 1 sequence, with area under the receiver operating characteristic (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, combined model performances on predicting outcomes were similar to FLAIR-only performance, with AUROC values of 0.7874 [0.6845–0.8903] and 0.7230 [0.5600–0.8859].CONCLUSIONS: Application of a combined algorithm by using both T2-weighted and FLAIR sequences offered the best image-based prediction of postshunt symptom improvement, particularly for gait and overall function in terms of mRS.AIartificial intelligenceAUROCarea under the receiver operating characteristic curveCCICharlson Comorbidity IndexDESHdisproportionately enlarged subarachnoid space hydrocephalusiNPHidiopathic normal pressure hydrocephalusIQRinterquartile rangeMLmachine learningNPHnormal pressure hydrocephalussNPHsecondary normal pressure hydrocephalus