Addressing Inaccurate Nosology in Mental Health: A Multi Label Data Cleansing Approach for Detecting Label Noise from Structural Magnetic Resonance Imaging Data in Mood and Psychosis Disorders

Abstract

Background: Mental health diagnostic approaches are seeking to identify biological markers to work alongside advanced machine learning approaches. It is difficult to identify a biological marker of disease when the traditional diagnostic labels themselves are not necessarily valid. Methods: We worked with T1 structural magnetic resonance imaging data collected from individuals with mood and psychosis disorders from over 1400 individuals comprising healthy controls, psychosis patients and their unaffected first-degree relatives including 176 bipolar probands, 134 schizoaffective probands, 240 schizophrenia proband, 581 patients relatives and 362 controls. We assumed there might be noise in the diagnostic labeling process. We detected label noise by classifying the data multiple times using a support vector machine classifier, and then we flagged those individuals in which all classifiers unanimously mislabeled those subjects. Next, we assigned a new diagnostic label to these individuals, based on the biological data (MRI), using iterative data cleansing approach. Results: Simulation results showed our method was highly accurate in identifying label noise. Both diagnostic and Biotype categories showed about 65% and 63% respectively of noisy labels with the largest amount of relabeling occurring between the healthy control and bipolar and schizophrenia disorder individuals as well as in the unaffected close relatives. The extraction of imaging features highlighted regional brain changes associated with each group. Conclusions: This approach represents an initial step towards developing strategies that need not assume existing mental health diagnostic categories are always valid, but rather allows us to leverage this information while also acknowledging that there are misassignments.

Research on Multi-Modal Pedestrian Detection and Tracking Algorithm Based on Deep Learning

“…Based on the clustering results obtained by k-means using the residual intersection area ratio measurement method, this paper introduces genetic algorithms to further optimize and obtain anchor frame data that best represents the dataset. This optimization aims to expedite the convergence process of the network and enhance the algorithm's robustness [13].…”

Promises and pitfalls of deep neural networks in neuroimaging-based psychiatric research

“…On the one hand, these challenges can be technology-related, such as the difficulty of deep neural networks to learn robust models on small, heterogeneous data sets or to give meaningful explanations for complex model decisions [30,31,32,33]. On the other hand, these challenges are driven by factors that are controversial within psychiatry itself, e.g., the heterogeneity of psychiatric diseases in their clinical presentation and the reliance on clinical symptoms rather than neurobiological substrates for establishing disease categories [34,35,36].…”

“…In contrast to AD and schizophrenia, internalizing disorders have been comparably less studied using classical machine learning and deep learning. On the one hand, as for most psychiatric disorders, the labels per se have been criticized for being mainly based on symptoms rather than neurobiological correlates and thus being too noisy and unspecific for the use in supervised machine learning studies [34]. On the other hand, neurobiological correlates obtained from neuroimaging data are less clear for internalizing disorders and might be mediated by underlying subtypes [214,162].…”