Development and validation of prediction model to estimate vertigo risk after endolymphatic sac decompression in Meniere's disease: a retrospective cohort study.

PURPOSE: To study the efficacy predictors of endolymphatic sac decompression (ESD) in Meniere's disease (MD), and to establish and verify the prediction model of vertigo after ESD in patients with MD. METHODS: The retrospective cohort data of 56 patients with unilateral MD who underwent ESD surgery were recorded. A stepwise regression method was used to select optimal modeling variables, and we established a logistic regression model with the outcome of vertigo after ESD. The bootstrap method was used for internal validation. RESULTS: Potential predictors included sex, age, follow-up duration, disease course, attack duration, frequency of attack, pure-tone threshold average (PTA) of the patient's speech frequency, audiogram type, glycerin test results, MD subtype, and 10-year atherosclerotic cardiovascular disease risk classification. Using the stepwise regression method, we found that the optimal modeling variables were the audiogram type and PTA of the patient's speech frequency. The prediction model based on these two variables exhibited good discrimination [area under the receiver operating characteristic curve: 0.72 (95% confidence interval: 0.57-0.86)] and acceptable calibration (Brier score 0.21). CONCLUSION: The present model based on the audiogram type and PTA of the patient's speech frequency was found to be useful in guidance of ESD efficacy prediction and surgery selection.

The effect of vascular risk factors on the efficacy of endolymphatic sac decompression surgery for Meniere's disease: a retrospective cohort study.

Objectives: This study aimed to investigate the effect of vascular risk factors on the outcomes of endolymphatic sac decompression (ESD) surgery in patients with Meniere's disease. Methods: The study included 56 patients with Meniere's disease, who had undergone unilateral ESD surgery. The patients' vascular risk factors were assessed based on the preoperative 10-year atherosclerotic cardiovascular diseases risk classification. Those with no or low risk were defined as the low-risk group, while those with medium, high, or very high risk were defined as the high-risk group. The correlation between the vascular risk factors and ESD efficacy was evaluated by the comparison of vertigo control grade between the two groups. The functional disability score was also assessed to investigate whether ESD improved the quality of life in Meniere's disease patients with vascular risk factors. Results: After ESD, 78.95 and 81.08% of patients from the low-risk and high-risk groups, respectively, demonstrated at least grade B vertigo control; no statistically significant difference was observed (p = 0.96). The postoperative functional disability scores in both groups were significantly lower compared with those before surgery (p < 0.01), with a median decrease of two (1, 2) points in both groups. No statistically significant difference between the two groups was observed (p = 0.65). Conclusion: Vascular risk factors have little effect on the efficacy of ESD in patients with Meniere's disease. Patients with one or more vascular risk factors can still experience a not poor vertigo control and improved quality of life after ESD.

Predictive accuracy of machine learning for radiation-induced temporal lobe injury in nasopharyngeal carcinoma patients: a systematic review and meta-analysis.

Background: Radiotherapy is a common treatment for nasopharyngeal carcinoma (NPC) but can cause radiation-induced temporal lobe injury (RTLI), resulting in irreversible damage. Predicting RTLI at the early stage may help with that issue by personalized adjustment of radiation dose based on the predicted risk. Machine learning (ML) models have recently been used to predict RTLI but their predictive accuracy remains unclear because the reported concordance index (C-index) varied widely from around 0.31 to 0.97. Therefore, a meta-analysis was needed. Methods: The PubMed, Web of Science, Embase, and Cochrane Library databases were searched from inception to November 2022. Studies that fully develop one or more ML risk models of RTLI after radiotherapy for NPC were included. The Prediction model Risk Of Bias Assessment Tool (PROBAST) was used to assess the risk of bias in the included research. The primary outcome of this review was the C-index, specificity (Spe), and sensitivity (Sen). Results: The meta-analysis included 14 studies with 15,573 NPC patients reporting a total of 72 prediction models. Overall, 94.44% of models were found to have a high risk of bias. Radiomics was included in 57 models, dosimetric predictors in 28, and clinical data in 27. The pooled C-index for ML models predicting RTLI was 0.77 [95% confidence interval (CI): 0.75-0.79] in the training set and 0.78 (95% CI: 0.75-0.81) in the validation set. The pooled Sen was 0.75 (95% CI: 0.69-0.80) in the training set and 0.70 (95% CI: 0.66-0.73) in the validation set and the pooled Spe was 0.78 (95% CI: 0.73-0.82) in the training set and 0.79 (95% CI: 0.75-0.82) in the validation set. Models with radiomics and clinical data achieved the most excellent discriminative performance, with a pooled C-index of 0.895. Conclusions: ML models can accurately predict RTLI at an early stage, allowing for timely interventions to prevent further damage. The kind of ML methods and the selection of predictors may influence the predictive accuracy.