Evaluating the cerebrospinal fluid tap test with the Hellström iNPH scale for patients with idiopathic normal pressure hydrocephalus

MRI-Based Prediction of Clinical Improvement after Ventricular Shunt Placement for Normal Pressure Hydrocephalus: Development and Evaluation of an Integrated Multisequence Machine Learning Algorithm

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.

Symptoms and signs did not predict outcome after surgery: a prospective study of 143 patients with idiopathic normal pressure hydrocephalus

OBJECTIVE

To determine the utility of symptoms, signs, comorbidities and background variables for the prediction of outcome of treatment in iNPH.

METHODS

A prospective observational study of consecutively included iNPH patients, who underwent neurological, physiotherapeutic and neuropsychological assessments before and after shunt surgery. The primary outcome measure was the total change on the iNPH scale, and patients were defined as improved postoperatively if they had improved by at least five points on that scale.

RESULTS

143 iNPH patients were included, and 73% of those were improved after surgery. None of the examined symptoms or signs could predict which patients would improve after shunt surgery. A dominant subjective complaint of memory problems at baseline was predictive of non-improvement. The reported comorbidities, duration of symptoms and BMI were the same in improved and non-improved patients. Each of the symptom domains (gait, neuropsychology, balance, and continence) as well as the total iNPH scale score improved significantly (from median 53 to 69, p < 0.001). The proportions of patients with shuffling gait, broad-based gait, paratonic rigidity and retropulsion all decreased significantly.

DISCUSSION

This study confirms that the recorded clinical signs, symptoms, and impairments in the adopted clinical tests are characteristic findings in iNPH, based on that most of them improved after shunt surgery. However, our clinical data did not enable predictions of whether patients would respond to shunt surgery, indicating that the phenotype is unrelated to the reversibility of the iNPH state and should mainly support diagnosis. Absence of specific signs should not be used to exclude patients from treatment.

Tap Test Can Predict Cognitive Improvement in Patients With iNPH-Results From the Multicenter Prospective Studies SINPHONI-1 and -2

Background: We analyzed the predictive value of the tap test (TT) on the outcome of cerebrospinal fluid (CSF) shunting in patients with idiopathic normal pressure hydrocephalus (iNPH) and cognitive impairment up to 12 months postoperatively. Methods: We analyzed the data of two prospective multicenter studies on ventriculoperitoneal shunt (VPS) and lumboperitoneal shunt (LPS) use in iNPH patients. We selected patients with Mini-Mental State Examination (MMSE) scores ≤ 26 points as study subjects. We used a multivariate logistic regression model to obtain the optimal threshold of MMSE scores after TT to predict the score improvement at 12 months following shunting and that helped to control for confounding factors such as age and MMSE scores before TT. We used logistic regression models to identify variables with age-adjusted odds ratio (A-OR) and multivariate-adjusted OR (M-OR). Results: For an improvement of ≥3 points in the MMSE score cutoff 7 days following TT in VPS and LPS cohort studies, the MMSE scores improved by 6 points after 12 months. The VPS cohort had sensitivity, specificity, and area under the curve (AUC) of 69.2, 73.7, and 0.771%, respectively; however, for the LPS cohort, they were 86.2, 90.9, and 0.906%, respectively. For MMSE scores that improved by ≥3 points in patients after the TT, the possibility of an improvement by 6 points at 12 months following CSF shunt had A-OR 7.77 and M-OR 6.3 times for the VPS, and A-OR 62.3 and M-OR 59.6 times for the LPS cohort. Conclusion: CSF shunting contributes to improved cognitive function in iNPH patients. Furthermore, MMSE score evaluation at the TT can sensitively predict improvement in postoperative MMSE scores following LPS intervention. Clinical Trial Registration: SINPHONI-1 (ClinicalTrials.gov, no. NCT00221091), first posted: September 22, 2005. SINPHONI-2 [University Hospital Medical Information Network (UMIN) Clinical Trials no. UMIN000002730], the posted: February 1, 2010.