Asian journal of psychiatry · 2025
An interpretable deep-learning approach to detect biomarkers in anxious-depressed symptoms from prefrontal fNIRS signals during an autobiographical memory test.
СтатьяНазвание и аннотация: Перевод пока не подготовлен
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…
Ошибки и ограничения
История · было → стало
Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.
Zhang Yan, Xu Yawen, Cheng Yihang, Zhao Yihong, Potenza Marc N, Shi Hui
Аннотация
BACKGROUND: Individuals with anxious-depressed (AD) symptoms have more severe mood disorders and cognitive impairment than those with non-anxious depression (NAD) symptoms. Therefore, it is important to clarify the underlying neurophysiology of these two symptom groups to optimize treatment.
METHODS: We developed an interpretable deep-learning framework based on two convolutional neural networks (CNN) to diagnose depression from functional near-infrared spectroscopy (fNIRS) neuroimaging data recorded during an autobiographical memory test (AMT) from 824 participants. This system was designed to discriminate between individuals with depressed symptoms (N = 127) and healthy controls (N = 697) and identify AD (N = 72) and NAD (N = 55). Besides, we employed the SHapley Additive exPlanations (SHAP) method to discover discriminative biomarkers for AD symptoms.
RESULTS: Positive episode recall features effectively distinguished depressed symptoms with the highest accuracy of 0.89, sensitivity of 0.84, specificity of 0.90, and area under the receiver operator characteristic curve (AUC) of 0.84. Conversely, negative episode recall features achieved the highest accuracy of 0.91, sensitivity of 0.80, specificity of 0.85, and an AUC of 0.91 for identifying AD symptoms. These performances were based on a five-fold cross-validation procedure. Based on the SHAP-derived analyses, the most influential channels contributing to AD symptom prediction were located within the right hemisphere.
CONCLUSION: This study revealed that the hemodynamic hypo-activation of negative emotional valence in the right frontal pole area (rFPA) may contribute to AD symptom prediction.
METHODS: We developed an interpretable deep-learning framework based on two convolutional neural networks (CNN) to diagnose depression from functional near-infrared spectroscopy (fNIRS) neuroimaging data recorded during an autobiographical memory test (AMT) from 824 participants. This system was designed to discriminate between individuals with depressed symptoms (N = 127) and healthy controls (N = 697) and identify AD (N = 72) and NAD (N = 55). Besides, we employed the SHapley Additive exPlanations (SHAP) method to discover discriminative biomarkers for AD symptoms.
RESULTS: Positive episode recall features effectively distinguished depressed symptoms with the highest accuracy of 0.89, sensitivity of 0.84, specificity of 0.90, and area under the receiver operator characteristic curve (AUC) of 0.84. Conversely, negative episode recall features achieved the highest accuracy of 0.91, sensitivity of 0.80, specificity of 0.85, and an AUC of 0.91 for identifying AD symptoms. These performances were based on a five-fold cross-validation procedure. Based on the SHAP-derived analyses, the most influential channels contributing to AD symptom prediction were located within the right hemisphere.
CONCLUSION: This study revealed that the hemodynamic hypo-activation of negative emotional valence in the right frontal pole area (rFPA) may contribute to AD symptom prediction.