1. An end-to-end framework for extracting observable cues of depression from diary recordingsIzidor Mlakar, Umut Arioz, Urška Smrke, Nejc Plohl, Valentino Šafran, Matej Rojc, 2024, original scientific article Abstract: Because of the prevalence of depression, its often-chronic course, relapse and associated disability, early detection and non-intrusive monitoring is a crucial tool for timely diagnosis and treatment, remission of depression and prevention of relapse. In this way, its impact on quality of life and well-being can be limited. Current attempts to use artificial intelligence for the early classification of depression are mostly data-driven and thus non-transparent and lack effective means to deal with uncertainties. Therefore, in this paper, we propose an end-to-end framework for extracting observable depression cues from diary recordings. Furthermore, we also explore its feasibility for automatic detection of depression symptoms using observable behavioural cues. The proposed end-to-end framework for extracting depression was used to evaluate 28 video recordings from the Symptom Media dataset and 27 recordings from the DAIC-WOZ dataset. We compared the presence of the extracted features between recordings of individuals with and without a depressive disorder. We identified several cues consistent with previous studies in terms of their differentiation between individuals with and without depressive disorder across both datasets among language (i.e., use of negatively valanced words, use of first-person singular pronouns, some features of language complexity, explicit mentions of treatment for depression), speech (i.e., monotonous speech, voiced speech and pauses, speaking rate, low articulation rate), and facial cues (i.e., rotational energy of head movements). The nature/context of the discourse, the impact of other disorders and physical/psychological stress, and the quality and resolution of the recordings all play an important role in matching the digital features to the relevant background. In this way, the work presented in this paper provides a novel approach to extracting a wide range of cues relevant to the classification of depression and opens up new opportunities for further research.
Keywords: digital biomarkers of depression, facial cues, speech cues, language cues, deep learning, end-to-end pipeline, artificial intelligence
Published in DKUM: 17.01.2025; Views: 0; Downloads: 5
 Full text (2,34 MB) |
2. Quality of life and health status in middle-aged presumed healthy Slovenian family practice attendeesMatic Tement, Polona Selič-Zupančič, 2021, original scientific article Abstract: Background: There is a gap in our knowledge of health-related quality of life (HRQoL) in a population presumed healthy, so this study aimed to assess the associations between HRQoL, demographics and clinical variables.
Methods: The participants were attendees, presumed healthy, at 40 pre-selected model family medicine practices (MFMPs), aged between 30 and 65 years and recruited during a preventive check-up in 2019. Each MFMP pragmatically invited 30 attendees to voluntarily participate. The EQ-5D questionnaire was administered as a measure of HRQoL; the independent variables were demographic characteristics, smoking, alcohol consumption, stress perception, physical activity, signs of depression, cardiovascular risk, body mass index, blood pressure values, and blood sugar and lipidogram laboratory test values. Ordinal logistic regression was used to calculate associations between self-assessed quality of life, demographics, and clinical variables, with P<0.05 set as statistically significant.
Results: Of 986 participants, 640 (64.9%) were women and 346 (35.1%) men, aged 42.7+-8.6 years. The average values for the EQ-5D-3L were 0.9+1-0.15. In the multivariate model, a positive association between adequate physical activity (p=0.003), and a negative association between higher age (p<0.001), female gender (p=0.009), signs of depression (p<0.001), stress (p=0.013), and EQ-5D score were identified.
Conclusion: Given that physical activity was shown to be positively associated with HRQoL, it is of the utmost importance for family physicians to motivate their middle-aged patients, especially women and those with signs of depression and excessive stress, to adopt a more rigorously physically active lifestyle.
Keywords: health related quality of life, health status, family practice, middle-age, physical activity, depression, stress, coping
Published in DKUM: 11.12.2024; Views: 0; Downloads: 8
Full text (488,49 KB)
This document has many files! More... |
3. Efficacy of direct or indirect use of probiotics for the improvement of maternal depression during pregnancy and in the postnatal period : a systematic review and meta-analysisKlavdija Čuček-Trifkovič, Dušanka Mičetić-Turk, Sergej Kmetec, Maja Strauss, Hannah Dahlen, Jann Foster, Sabina Fijan, 2022, review article Abstract: The mother and infant form a unique bond, with maternal mental health affecting the interactions with the infant and infant behaviours impacting maternal mental health. One of the possible mechanisms influencing maternal mental health is the manipulation of the gut-brain axis by consuming probiotic supplements. Probiotics can also have an indirect influence on maternal mental health via the modulation of the infant microbiome and consequently improving the infant’s health and thus, indirectly leading to an improvement in maternal mood. This systematic review evaluated the efficacy of probiotics on maternal mental health by searching for randomised controlled trials via international databases: Cochrane Library, PubMed, Scopus, ScienceDirect, and Web of Science until January 2022. A meta-analysis was performed using the Cochrane Collaboration methodology where possible. We found seven clinical trials that included the word probiotics and addressed maternal depression and/or anxiety. Of these, five trials investigated the influence of maternal probiotic supplementation on the gut-brain axis. Two trials investigated the indirect influence of probiotics on maternal depression via supplementation of probiotics by infants and subsequent influence on the crying of colicky infants. Meta-analysis of two studies of pregnant and postnatal women and two studies of infants consuming probiotics on the outcome of the Edinburgh Postnatal Depression Scale for mothers showed no statistical difference. The findings indicate that maternal depression is very complex and is influenced by various bidirectional factors. One of the factors that can improve maternal mental health is probiotics, however, careful consideration must be given to correct strain selection as strain-specific effectiveness was observed. Further well-designed, robust clinical studies are warranted.
Keywords: probiotics, pregnancy, postpartum, depression, prevention, psychobiotics
Published in DKUM: 05.07.2024; Views: 147; Downloads: 18
Full text (960,02 KB)
This document has many files! More... |
4. Psychometric properties of the Slovenian version of the Cancer Survivors' Unmet Needs (CaSUN-SL) measure in post-treatment cancer survivorsŠpela Miroševič, Polona Selič-Zupančič, Judith B. Prins, Vesna Homar, Zalika Klemenc-Ketiš, 2022, original scientific article Abstract: Background: As the number of cancer survivors is growing, valid instruments for assessing cancer survivors' needs are required. Thus, the aim of this study was to translate and validate the Cancer Survivors Unmet Needs (CaSUN) scale.
Methods: Cancer survivors were recruited from 30 family medicine practices and separated into two samples (sample 1, n = 147; sample 2, n = 148). Factor structure was explored with an exploratory analysis in sample 1 and determined with a confirmatory analysis in sample 2. Psychometric properties were assessed with internal consistency, test-retest reliability and construct validity.
Results: A translation and cultural adaptation of the CaSUN scale resulted in 34 items being included in the final version. The factor structure confirmed the five-factors solution of the CaSUN-SL. Cronbach's alpha was 0.94 for the CaSUN-SL and ranged from 0.71-0.88 for specific domains. Test-retest reliability showed moderate-high stability over time. The CaSUN-SL significantly and positively correlated with anxiety (r = 0.49), depression (r = 0.44), health-related quality of life (r = 0.36), and negatively with self-perceived health (r = - 0.36) and resilience (r = - 0.47), which confirms the construct validity. In addition, we found a significant correlation between unmet needs and age (r = - 0.29), gender (r = 0.14), cancer stage (r = 0.20), cancer type (r = 0.19), and time since treatment (r = - 0.20).
Conclusions: Results indicate that CaSUN-SL is a valid and reliable measure to assess the Slovenian cancer survivors' unmet, met and total needs and can be used for further prospective studies.
Keywords: Cancer survivors, needs assessment, psychometrics, anxiety, depression, quality of life, cancer, survivol, psychometrics
Published in DKUM: 27.06.2024; Views: 130; Downloads: 18
Full text (993,82 KB)
This document has many files! More... |
5. Hybrid visualization-based framework for depressive state detection and characterization of atypical patientsLeon Kopitar, Peter Kokol, Gregor Štiglic, 2023, original scientific article Keywords: hybrid visualization, interpretation, explainable, shapley, feature importance, depression
Published in DKUM: 12.06.2024; Views: 101; Downloads: 19
Full text (1,83 MB)
This document has many files! More... |
6. The effectiveness of computerized cognitive remediation therapy (CCRT) for deficits in attention and executive functions in depression : a pilot studyMonika Klojčnik, Karin Bakračevič, 2023, original scientific article Abstract: Depression is associated with cognitive deficits and changes in the brain. Major depression is often associated with cognitive problems; however, there are only a few studies that have focused on the systematic use of cognitive remediation in depression. The objective of this study was to assess the effectiveness of computerized cognitive remediation in depressed patients with cognitive dysfunction. Patients (n % 20) with depression were randomly assigned to the active or control group. The active intervention (computerized cognitive remediation) comprised 12 sessions focused on the remediation of attention and executive functions through the CogniPlus software. All participants completed neuropsychological testing before and after the intervention. A mixeddesign analysis of variance revealed a significant time group interaction in the attention and planning task, on the Beck Depression Inventory and on the Shifting, Emotional Control and Initiating sub-scales of the Behavior Rating Inventory of Executive Function-Adult. The results showed that patients undergoing cognitive remediation improved in domains related to attention and executive functions and scored significantly lower on the Beck Depression Inventory. The findings provide some evidence that cognitive remediation could be an efficient approach to dealing with cognitive deficits in depression.
Keywords: attention, cognitive remediation, depression, executive function, neuroplasticity
Published in DKUM: 31.05.2024; Views: 182; Downloads: 21
Full text (1,13 MB)
This document has many files! More... |
7. Honey, there´s something on my mind --- : adverse consequences of negative and positive work rumination on attention to the partner, and the advantage of talking about itJulia Schoellbauer, Sara Tement, Christian Korunka, 2023, original scientific article Abstract: In the contemporary 24/7 working society, the separation of work and private life is increasingly turning into an unrealizable ideal. Ruminating about work outside the work context lets work spill over into private lives and afects the dynamics of workers’ private relationships. Although negative work rumination was linked to couples’ reduced relationship satisfaction, little is known about the mechanism of action and the impact of positive work rumination. Drawing on the load theory of selective attention, we hypothesize that both negative and positive work rumination occupy attentional resources and thus reduce workers’ attention to the partner on the same day. Lower levels of attention to the partner, in turn, should relate to lower levels of both partners’relationship satisfaction. However, sharing the work-related thoughts with the partner might support the resolution of the work issue the worker is ruminating about, which releases attentional resources and thus bufers the negative association between rumination and attention to the partner. We conducted a daily diary study and the fndings based on 579 daily dyadic observations from 42 dualearner couples support the proposed cognitive spillover-crossover mechanism and the bufer mechanism of thought-sharing. We conclude that negative and positive work rumination takes up scarce attentional resources and thus jeopardizes relationship quality. However, sharing thoughts with one’s partner seems to be a useful strategy for couples to maintain or even increase their relationship satisfaction in the light of work rumination.
Keywords: Diary study, Dyadic research, Relationship quality, Psychological availability, Spillover-crossover, Actor-partner interdependence mode, family conflict, perceptual load, relationship satisfaction, marital, quality, daily-diary, couples, stress, experiences
depression, crossover, Psychology
Published in DKUM: 20.02.2024; Views: 333; Downloads: 17
Full text (989,06 KB)
This document has many files! More... |
8. Scoping review on the multimodal classification of depression and experimental study on existing multimodal modelsUmut Arioz, Urška Smrke, Nejc Plohl, Izidor Mlakar, 2022, review article Abstract: Depression is a prevalent comorbidity in patients with severe physical disorders, such as cancer, stroke, and coronary diseases. Although it can significantly impact the course of the primary disease, the signs of depression are often underestimated and overlooked. The aim of this paper was to review algorithms for the automatic, uniform, and multimodal classification of signs of depression from human conversations and to evaluate their accuracy. For the scoping review, the PRISMA guidelines for scoping reviews were followed. In the scoping review, the search yielded 1095 papers, out of which 20 papers (8.26%) included more than two modalities, and 3 of those papers provided codes. Within the scope of this review, supported vector machine (SVM), random forest (RF), and long short-term memory network (LSTM; with gated and non-gated recurrent units) models, as well as different combinations of features, were identified as the most widely researched techniques. We tested the models using the DAIC-WOZ dataset (original training dataset) and using the SymptomMedia dataset to further assess their reliability and dependency on the nature of the training datasets. The best performance was obtained by the LSTM with gated recurrent units (F1-score of 0.64 for the DAIC-WOZ dataset). However, with a drop to an F1-score of 0.56 for the SymptomMedia dataset, the method also appears to be the most data-dependent.
Keywords: multimodal depression classification, scoping review, real-world data, mental health
Published in DKUM: 11.08.2023; Views: 529; Downloads: 83
Full text (1,43 MB)
This document has many files! More... |
9. Factors associated with health-related quality of life among university studentsZalika Klemenc-Ketiš, Janko Kersnik, Ksenija Eder, Dušan Colarič, 2011, original scientific article Abstract: Introduction: University students are subjected to different kinds of stressors, i.e.academic pressures, social issues and financial problems. This can affect their academic achievements and quality of life.
Objective: The aim of this study was to determine the health-related quality of life of university students, and how it is affected by the presence of chronic diseases, mental disorders comorbidity, and patterns of medical services' use.
Methods: This web-based study included a sample of 1,410 Slovenian university students. We used a self-administered questionnaire, containing a sheet with demographic data, Zung's self-assessment inventories about anxiety and depression, and EQ-5D questionnaire. The main outcome measures were scores on EQ-5D part and VAS part of the EQ-5D questionnaire.
Results: Independent factors associated with the health-related quality of life of university students, were the presence of chronic pain, the presence of depression and anxiety, need for urgent medical help and at least one visit to a clinical specialist in the past year. The independent factors associated with the health status of university students were the presence of chronic diseases, chronic pain, depression and anxiety, a visit to a clinical specialist, a need for urgent medical help and a visit to an emergency unit in the past year.
Conclusion: Health-related quality of life of university students can be seriously affected by the presence of mental disorders and chronic pain. Appropriate health-related measures should be adopted to achieve early recognition of worse health-related quality of life, the presence of mental disorders and other chronic conditions, and to enable their effective treatment.
Keywords: quality of life, students, chronic disease, pain, depression, anxiety
Published in DKUM: 04.08.2017; Views: 1333; Downloads: 487
Full text (192,97 KB)
This document has many files! More... |
10. Comorbidities and characteristics of coronary heart disease patients: their impact on health-related quality of lifeKsenija Tušek-Bunc, Davorina Petek, 2016, original scientific article Abstract: Background: Patients with coronary heart disease (CHD) commonly present with more than one comorbid condition, contributing to poorer health-related quality of life (HRQoL). The aim of our study was to identify the associations between HRQoL and patient characteristics, vascular comorbidities and anxiety/depression disorders.
Methods: This observational study was conducted in 36 family medicine practices selected by random stratified sampling from all regions of Slovenia. HRQoL was assessed using the European Quality of Life - 5 Dimensions (EQ-5D) questionnaire and EQ Visual Analogue Scale (EQ-VAS). The associations between HRQoL and patient characteristics stratified by demographics, vascular comorbidities, health services used, their assessment of chronic illness care, and anxiety/depression disorders were identified by ordinal logistic regression and linear regression models.
Results: The final sample included 423 CHD patients with a mean age of 68.0 ± SD 10.8 years; 35.2% were female. Mean EQ-VAS score was 58.6 ± SD 19.9 (median: 60 with interquartile range of 45–75), and mean EQ-5D index was 0.60 ± SD 0.19 (median: 0.56 with interquartile range of 0.41–0.76). The statistically significant predictors of a lower EQ-VAS score were higher family physician visit frequency, heart failure (HF) and anxiety/depression disorders (R² 0.240; F = 17.368; p < 0.001). The statistically significant predictor of better HRQoL, according to EQ-5D was higher patient education, whereas higher family physician visit frequency, HF and peripheral artery disease (PAD) were predictors of poorer HRQoL (Nagelkerke R 2 = 0.298; χ 2 = 148.151; p < 0.001).
Conclusions: Results of our study reveal that comorbid conditions (HF and PAD), family physician visit frequency and years in education are significant predictors of HRQoL in Slovenian CHD patients.
Keywords: coronary heart disease patient, health-related quality of life, vascular comorbidities, anxiety/depression disorders
Published in DKUM: 29.06.2017; Views: 1747; Downloads: 429
Full text (407,23 KB)
This document has many files! More... |
