No abstract

Introduction Using machine learning techniques, we developed a brief questionnaire to aid neurologists and neuropsychologists in the screening of mild cognitive impairment (MCI) and dementia. Methods With the reduction of the survey size as a goal of this research, feature selection based on information gain was performed to rank the contribution of the 45 items corresponding to patient responses to the specified questions. The most important items were used to build the optimal screening model based on the accuracy, practicality, and interpretability. The diagnostic accuracy for discriminating normal cognition (NC), MCI, very mild dementia (VMD) and dementia was validated in the test group. Results The screening model (NMD-12) was constructed with the 12 items that were ranked the highest in feature selection. The receiver-operator characteristic (ROC) analysis showed that the area under the curve (AUC) in the test group was 0.94 for discriminating NC vs. MCI, 0.88 for MCI vs. VMD, 0.97 for MCI vs. dementia, and 0.96 for VMD vs. dementia, respectively. Discussion The NMD-12 model has been developed and validated in this study. It provides healthcare professionals with a simple and practical screening tool which accurately differentiates NC, MCI, VMD, and dementia.

Background: The performance of left ventricular (LV) functional assessment using gated myocardial perfusion SPECT (MPS) relies on the accuracy of segmentation. Current methods require manual adjustments that are tedious and subjective. We propose a novel machine-learning-based method to automatically segment LV myocardium and measure its volume in gated MPS imaging without human intervention. Methods: We used an end-to-end fully convolutional neural network to segment LV myocardium by delineating its endocardial and epicardial surface. A novel compound loss function, which encourages similarity and penalizes discrepancy between prediction and training dataset, is utilized in training stage to achieve excellent performance. We retrospectively investigated 32 normal patients and 24 abnormal patients, whose LV myocardial contours automatically segmented by our method were compared with those delineated by physicians as the ground truth. Results: The results of our method demonstrated very good agreement with the ground truth. The average DSC metrics and Hausdorff distance of the contours delineated by our method are larger than 0.900 and less than 1cm, respectively, among all 32+24 patients of all phases. The correlation coefficient of the LV myocardium volume between ground truth and our results is 0.910±0.061 (P<0.001), and the mean relative error of LV myocardium volume is-1.09±3.66%. Conclusion: These results strongly indicate the feasibility of our method in accurately quantifing LV myocardium volume change over the cardiac cycle. The learning-based segmentation method in gated MPS imaging has great promise for clinical use.

Objective. The reliable diagnosis remains a challenging issue in the early stages of dementia. We aimed to develop and validate a new method based on machine learning to help the preliminary diagnosis of normal, mild cognitive impairment (MCI), very mild dementia (VMD), and dementia using an informant-based questionnaire. Methods. We enrolled 5,272 individuals who filled out a 37-item questionnaire. In order to select the most important features, three different techniques of feature selection were tested. Then, the top features combined with six classification algorithms were used to develop the diagnostic models. Results. Information Gain was the most effective among the three feature selection methods. The Naive Bayes algorithm performed the best (accuracy = 0.81, precision = 0.82, recall = 0.81, and F-measure = 0.81) among the six classification models. Conclusion. The diagnostic model proposed in this paper provides a powerful tool for clinicians to diagnose the early stages of dementia.

No abstract