Depression Severity Estimation from Multiple Modalities
نویسندگان
چکیده
Depression is a major debilitating disorder which can affect people from all ages. With a continuous increase in the number of annual cases of depression, there is a need to develop automatic techniques for the detection of the presence and extent of depression. In this AVEC challenge we explore different modalities (speech, language and visual features extracted from face) to design and develop automatic methods for the detection of depression. In psychology literature, the PHQ-8 questionnaire is well established as a tool for measuring the severity of depression. In this paper we aim to automatically predict the PHQ-8 scores from features extracted from the different modalities. We show that visual features extracted from facial landmarks obtain the best performance in terms of estimating the PHQ-8 results with a mean absolute error (MAE) of 4.66 on the development set. Behavioral characteristics from speech provide an MAE of 4.73. Language features yield a slightly higher MAE of 5.17. When switching to the test set, our Turn Features derived from audio transcriptions achieve the best performance, scoring an MAE of 4.11 (corresponding to an RMSE of 4.94), which makes our system the winner of the AVEC 2017 depression sub-challenge.
منابع مشابه
Evaluation of the effectiveness of crocin isolated from saffron in treatment of burning mouth syndrome: A randomized controlled trial
Objective: Burning mouth syndrome (BMS) is a debilitating disorder with few limited treatment modalities. Because of the proven association between BMS symptoms, and depression and anxiety, treatment modalities that alleviate the two latter etiologic factors can be clinically effective. Thus, owing to the antidepressant and potential analgesic effects of crocin (as an active co...
متن کاملChildhood trauma and dimensions of depression: a specific association with the cognitive domain.
OBJECTIVE To investigate associations between a history of childhood trauma and dimensions of depression in a sample of clinically depressed patients. METHODS A sample of 217 patients from a mood-disorder outpatient unit was investigated with the Beck Depression Inventory, the Hamilton Depression Rating Scale, the CORE Assessment of Psychomotor Change, and the Childhood Trauma Questionnaire. ...
متن کاملThe Role of Depression in Predicting the Presence of Fatigue in Patients with Multiple Sclerosis
Abstract Introduction: Multiple sclerosis is one the most common diseases of the central nervous system. Fatigue and depression are common symptoms of the disorder. The identification of the factors associated with fatigue can help to solve this problem and subsequently, reduce the problems of these patients. Objective: This study aimed to determine the predictor role of depression in...
متن کاملThe Effectiveness of Mindfulness-Based Cognitive Therapy in Reducing Psychological Symptoms, Meta-Worry and Thought Fusion of Multiple Sclerosis Patients
Purpose: Multiple sclerosis is a progressive neurological disease and a cause of many disabilities in individuals. Set of symptoms and the chronic nature of this disease, together impair the mental state of the person and cause awidervariety of psychological symptoms worsening the disease. Therefor, this study aimed to evaluate the effectiveness of cognitive therapy based on mindfulness psy...
متن کاملتخمین شناختی در بیماران مبتلا به اختلال اسکیزوفرنی، افسردگی اساسی و افراد بهنجار
Background and Objective: Estimation abilities are a group of processes that involve cognitive functions such as planning, attention, abstract reasoning, and memory. The goal of this study was to assess cognitive estimation in patients with schizophrenia, major depression disorder (MDD) and normal individuals. Materials and Methods: Three groups including patients with schizophrenia, m...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید
ثبت ناماگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید
ورودعنوان ژورنال:
- CoRR
دوره abs/1711.06095 شماره
صفحات -
تاریخ انتشار 2017