Detecting depression severity using weighted random forest and oxidative stress biomarkers.
Biochemistry
Depression severity
Machine learning
Oxidative stress
PHQ-9
Journal
Scientific reports
ISSN: 2045-2322
Titre abrégé: Sci Rep
Pays: England
ID NLM: 101563288
Informations de publication
Date de publication:
15 Jul 2024
15 Jul 2024
Historique:
received:
01
03
2024
accepted:
09
07
2024
medline:
16
7
2024
pubmed:
16
7
2024
entrez:
15
7
2024
Statut:
epublish
Résumé
This study employs machine learning to detect the severity of major depressive disorder (MDD) through binary and multiclass classifications. We compared models that used only biomarkers of oxidative stress with those that incorporate sociodemographic and health-related factors. Data collected from 830 participants, based on the Patient Health Questionnaire (PHQ-9) score, inform our analysis. In binary classification, the Random Forest (RF) classifier achieved the highest Area Under the Curve (AUC) of 0.84 when all features were included. In multiclass classification, the AUC improved from 0.84 with only oxidative stress biomarkers to 0.88 when all characteristics were included. To address data imbalance, weighted classifiers, and Synthetic Minority Over-sampling Technique (SMOTE) approaches were applied. Weighted random forest (WRF) improved multiclass classification, achieving an AUC of 0.91. Statistical tests, including the Friedman test and the Conover post-hoc test, confirmed significant differences between model performances, with WRF using all features outperforming others. Feature importance analysis shows that oxidative stress biomarkers, particularly GSH, are top ranked among all features. Clinicians can leverage the results of this study to improve their decision-making processes by incorporating oxidative stress biomarkers in addition to the standard criteria for depression diagnosis.
Identifiants
pubmed: 39009760
doi: 10.1038/s41598-024-67251-y
pii: 10.1038/s41598-024-67251-y
doi:
Substances chimiques
Biomarkers
0
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
16328Informations de copyright
© 2024. The Author(s).
Références
Hidaka, B. H. Depression as a disease of modernity: Explanations for increasing prevalence. J. Affect. Disord. 140, 205–214. https://doi.org/10.1016/j.jad.2011.12.036 (2012).
doi: 10.1016/j.jad.2011.12.036
pubmed: 22244375
pmcid: 3330161
Institute of Health Metrics and Evaluation. Global Health Data Exchange (ghdx) (2022).
World Health Organization. Depressive Disorder (Depression) (2022).
Ashraf, A. et al. A Summarization of the Visual Depression Databases for Depression Detection. 1–6. https://doi.org/10.1109/ICWT50448.2020.9243625 (2020).
Saha, B., Nguyen, T., Phung, D. & Venkatesh, S. A framework for classifying online mental health-related communities with an interest in depression. IEEE J. Biomed. Health Inform. 20, 1008–1015. https://doi.org/10.1109/JBHI.2016.2543741 (2016).
doi: 10.1109/JBHI.2016.2543741
pubmed: 27008680
Kang, M., Oh, S., Oh, K., Kang, S. & Lee, Y. The deep learning method for predict Beck’s depression inventory score using EEG. In 2021 International Conference on Information and Communication Technology Convergence (ICTC). 490–493. https://doi.org/10.1109/ICTC52510.2021.9620922 (2021).
Black, C. N., Bot, M., Scheffer, P. G., Cuijpers, P. & Penninx, B. W. Is depression associated with increased oxidative stress? A systematic review and meta-analysis. Psychoneuroendocrinology 51, 164–175 https://doi.org/10.1016/j.psyneuen.2014.09.025 (2015) (this issue includes a special section on biomarkers in the military—new findings from prospective studies).
Wium-Andersen, I. K., Osler, M., Jørgensen, M. B., Rungby, J. & Wium-Andersen, M. K. Diabetes, antidiabetic medications and risk of depression—A population-based cohort and nested case–control study. Psychoneuroendocrinology 140, 105715. https://doi.org/10.1016/j.psyneuen.2022.105715 (2022).
doi: 10.1016/j.psyneuen.2022.105715
pubmed: 35338947
Maes, M., Galecki, P., Chang, Y. S. & Berk, M. A review on the oxidative and nitrosative stress (o &ns) pathways in major depression and their possible contribution to the (neuro)degenerative processes in that illness. Prog. Neuro-Psychopharmacol. Biol. Psychiatry 35, 676–692 https://doi.org/10.1016/j.pnpbp.2010.05.004 (2011) (the neuro-inflammatory and neuroprogressive pathways in depression).
Bhatt, S., Nagappa, A. N. & Patil, C. R. Role of oxidative stress in depression. Drug Discov. Today 25, 1270–1276. https://doi.org/10.1016/j.drudis.2020.05.001 (2020).
doi: 10.1016/j.drudis.2020.05.001
pubmed: 32404275
Pouvreau, C., Dayre, A., Butkowski, E. G., de Jong, B. & Jelinek, H. F. Inflammation and oxidative stress markers in diabetes and hypertension. J. Inflamm. Res. 11, 61–68. https://doi.org/10.2147/JIR.S148911 (2018).
doi: 10.2147/JIR.S148911
pubmed: 29497324
pmcid: 5822844
Hassan, W. et al. Association of oxidative stress with psychiatric disorders. Curr. Pharmaceut. Des. 22, 2960–2974. https://doi.org/10.2174/1381612822666160307145931 (2016).
doi: 10.2174/1381612822666160307145931
Wicke, F. et al. The association of depression and all-cause mortality: Explanatory factors and the influence of gender. J. Affect. Disord. 303, 315–322. https://doi.org/10.1016/j.jad.2022.02.034 (2022).
doi: 10.1016/j.jad.2022.02.034
pubmed: 35176339
Tautan, A.-M., Ionescu, B. & Santarnecchi, E. Artificial intelligence in neurodegenerative diseases: A review of available tools with a focus on machine learning techniques. Artif. Intell. Med. 117, 102081. https://doi.org/10.1016/j.artmed.2021.102081 (2021).
doi: 10.1016/j.artmed.2021.102081
pubmed: 34127244
Triantafyllidis, A. & Tsanas, A. Applications of machine learning in real-life digital health interventions: Review of the literature. J. Med. Internet Res. https://doi.org/10.2196/12286 (2019).
doi: 10.2196/12286
pubmed: 30950797
pmcid: 6473205
Pienaar, M. A., Sempa, J. B., Luwes, N. & Solomon, L. J. An artificial neural network model for pediatric mortality prediction in two tertiary pediatric intensive care units in South Africa. A development study. Front. Pediatr. https://doi.org/10.3389/fped.2022.797080 (2022).
doi: 10.3389/fped.2022.797080
pubmed: 36458145
pmcid: 9705750
Nemesure, M., Heinz, M., Huang, R. & Jacobson, N. Predictive modeling of depression and anxiety using electronic health records and a novel machine learning approach with artificial intelligence. Sci. Rep. 11, 1980. https://doi.org/10.1038/s41598-021-81368-4 (2021).
doi: 10.1038/s41598-021-81368-4
pubmed: 33479383
pmcid: 7820000
Kaushik, P., Yang, H., Roy, P. & Vugt, M. Comparing resting state and task-based EEG using machine learning to predict vulnerability to depression in a non-clinical population. Sci. Rep. https://doi.org/10.1038/s41598-023-34298-2 (2023).
doi: 10.1038/s41598-023-34298-2
pubmed: 37884529
pmcid: 10603087
Cvetkovic, J. Breast cancer patients’ depression prediction by machine learning approach. Cancer Invest. 35, 569–572. https://doi.org/10.1080/07357907.2017.1363892 (2017) (PMID: 28872366).
doi: 10.1080/07357907.2017.1363892
pubmed: 28872366
Sau, A. & Bhakta, I. Predicting anxiety and depression in elderly patients using machine learning technology. Healthc. Technol. Lett. https://doi.org/10.1049/htl.2016.0096 (2017).
doi: 10.1049/htl.2016.0096
pubmed: 28261491
Priya, A., Garg, S. & Tigga, N. P. Predicting anxiety, depression and stress in modern life using machine learning algorithms. Proc. Comput. Sci. 167, 1258–1267 https://doi.org/10.1016/j.procs.2020.03.442 (2020) (international conference on computational intelligence and data science).
Chao, H.-Y., Hsu, C.-H., Wang, S.-T., Yu, C.-Y. & Chen, H.-M. Mediating effect of social support on the relationship between illness concealment and depression symptoms in patients with pulmonary arterial hypertension. Heart Lung 50, 706–713. https://doi.org/10.1016/j.hrtlng.2021.03.082 (2021).
doi: 10.1016/j.hrtlng.2021.03.082
pubmed: 34107395
Nguyen, H., Oh, H. & Kim, M.-S. The association between curry-rice consumption and hypertension, type 2 diabetes, and depression: The findings from Knhanes 2012–2016. Diabetes Metab. Syndr. Clin. Res. Rev. https://doi.org/10.1016/j.dsx.2021.102378 (2021).
doi: 10.1016/j.dsx.2021.102378
Zheng, H. & Jia, C. Gender differences in the association of depression trajectories with executive and memory functions: Evidence from the longitudinal study of the survey of health, ageing and retirement in Europe (2004–2017). J. Psychiatr. Res. 149, 177–184. https://doi.org/10.1016/j.jpsychires.2022.03.007 (2022).
doi: 10.1016/j.jpsychires.2022.03.007
pubmed: 35278782
Terauchi, M. Depressive symptoms are associated with oxidative stress in middle-aged women: A cross-sectional study. BioPsychoSoc. Med. 10, 12. https://doi.org/10.1186/s13030-016-0066-4 (2016).
doi: 10.1186/s13030-016-0066-4
pubmed: 27118992
pmcid: 4845355
Tuura, R. et al. Prefrontal glutathione levels in major depressive disorder are linked to a lack of positive affect. Brain Sci. 13, 1475. https://doi.org/10.3390/brainsci13101475 (2023).
doi: 10.3390/brainsci13101475
pubmed: 37891842
pmcid: 10605149
Maes, M. et al. Increased 8-hydroxy-deoxyguanosine, a marker of oxidative damage to DNA, in major depression and myalgic encephalomyelitis/chronic fatigue syndrome. Neuro Endocrinol. Lett. 30, 715–722 (2009).
pubmed: 20035260
Forlenza, M. J. & Miller, G. E. Increased serum levels of 8-hydroxy-2’-deoxyguanosine in clinical depression. Psychosom. Med. 68, 1–7. https://doi.org/10.1097/01.psy.0000195780.37277.2a (2006).
doi: 10.1097/01.psy.0000195780.37277.2a
pubmed: 16449405
Chen, H. & Chang, X. Photovoltaic power prediction of LSTM model based on Pearson feature selection. Energy Rep. 7, 1047–1054. https://doi.org/10.1016/j.egyr.2021.09.167 (2021) (2021 international conference on energy engineering and power systems).
Richter, T., Fishbain, B., Markus, A., Richter-Levin, G. & Okon-Singer, H. Using machine learning-based analysis for behavioral differentiation between anxiety and depression. Sci. Rep. https://doi.org/10.1038/s41598-020-72289-9 (2020).
doi: 10.1038/s41598-020-72289-9
pubmed: 33214619
pmcid: 7677539
Na, K.-S., Cho, S.-E., Geem, Z. W. & Kim, Y.-K. Predicting future onset of depression among community dwelling adults in the Republic of Korea using a machine learning algorithm. Neurosci. Lett. 721, 134804. https://doi.org/10.1016/j.neulet.2020.134804 (2020).
doi: 10.1016/j.neulet.2020.134804
pubmed: 32014516
Hooker, S. A. et al. Depression and cardiovascular risk in primary care patients. J. Psychosom. Res. 158, 110920. https://doi.org/10.1016/j.jpsychores.2022.110920 (2022).
doi: 10.1016/j.jpsychores.2022.110920
pubmed: 35461074
pmcid: 9237849
Li, H., Liu, X., Zheng, Q., Zeng, S. & Luo, X. Gender differences and determinants of late-life depression in China: A cross-sectional study based on Charls. J. Affect. Disord. 309, 178–185. https://doi.org/10.1016/j.jad.2022.04.059 (2022).
doi: 10.1016/j.jad.2022.04.059
pubmed: 35472476
Kodydková, J. et al. Antioxidative enzymes and increased oxidative stress in depressive women. Clin. Biochem. 42, 1368–1374. https://doi.org/10.1016/j.clinbiochem.2009.06.006 (2009).
doi: 10.1016/j.clinbiochem.2009.06.006
pubmed: 19527700
Cabello, M. et al. The relationship between all-cause mortality and depression in different gender and age groups of the Spanish population. J. Affect. Disord. 266, 424–428. https://doi.org/10.1016/j.jad.2020.01.162 (2020).
doi: 10.1016/j.jad.2020.01.162
pubmed: 32056909
Shen, J. et al. A diagnostic model based on bioinformatics and machine learning to differentiate bipolar disorder from schizophrenia and major depressive disorder. Schizophrenia https://doi.org/10.1038/s41537-023-00417-1 (2024).
doi: 10.1038/s41537-023-00417-1
pubmed: 38355593
pmcid: 10866880
Zulfiker, M., Ety, N., Biswas, A. A., Nazneen, T. & Uddin, M. S. An in-depth analysis of machine learning approaches to predict depression. Curr. Res. Behav. Sci. 2, 100044. https://doi.org/10.1016/j.crbeha.2021.100044 (2021).
doi: 10.1016/j.crbeha.2021.100044
Nandanwar, H. & Nallamolu, S. Depression prediction on twitter using machine learning algorithms. In 2021 2nd Global Conference for Advancement in Technology (GCAT). 1–7. https://doi.org/10.1109/GCAT52182.2021.9587695 (2021).
Chawla, N., Bowyer, K., Hall, L. & Kegelmeyer, W. Smote: Synthetic minority over-sampling technique. J. Artif. Intell. Res. (JAIR) 16, 321–357. https://doi.org/10.1613/jair.953 (2002).
doi: 10.1613/jair.953
Pedregosa, F. et al. Scikit-learn: Machine learning in Python. J. Mach. Learn. Res. 12, 129 (2012).
Maalouf, M. & Trafalis, T. B. Robust weighted kernel logistic regression in imbalanced and rare events data. Comput. Stat. Data Anal. 55, 168–183 (2011).
doi: 10.1016/j.csda.2010.06.014
Jelinek, H., Wilding, C. & Tinely, P. An innovative multi-disciplinary diabetes complications screening program in a rural community: A description and preliminary results of the screening. Aust. J. Prim. Health https://doi.org/10.1071/PY06003 (2006).
doi: 10.1071/PY06003
Ye, Y.-X. et al. Associations between depression, oxidative stress, and semen quality among 1,000 healthy men screened as potential sperm donors. Fertil. Steril. 117, 86–94. https://doi.org/10.1016/j.fertnstert.2021.09.013 (2022).
doi: 10.1016/j.fertnstert.2021.09.013
pubmed: 34656302
Jelinek, H., Yatsko, A., Stranieri, A. & Venkatraman, S. Novel data mining techniques for incomplete clinical data in diabetes management. Br. J. Appl. Sci. Technol. 4, 4591–4606. https://doi.org/10.9734/BJAST/2014/11744 (2014).
doi: 10.9734/BJAST/2014/11744
Altmann, A., Tolosi, L., Sander, O. & Lengauer, T. Permutation importance: A corrected feature importance measure. Bioinformatics (Oxford, England) 26, 1340–7. https://doi.org/10.1093/bioinformatics/btq134 (2010).
doi: 10.1093/bioinformatics/btq134
pubmed: 20385727
Maalouf, M. Logistic regression in data analysis: An overview. Int. J. Data Anal. Tech. Strateg. 3, 281–299 (2011).
doi: 10.1504/IJDATS.2011.041335
Chao-Ying Joanne Peng, K. L. L. & Ingersoll, G. M. An introduction to logistic regression analysis and reporting. J. Educ. Res. 96, 3–14. https://doi.org/10.1080/00220670209598786 (2002).
doi: 10.1080/00220670209598786
Subasi, A. Practical Machine Learning for Data Analysis Using Python (2020).
Zolbanin, H. M., Delen, D. & Hassan Zadeh, A. Predicting overall survivability in comorbidity of cancers: A data mining approach. Decis. Supp. Syst. 74, 150–161. https://doi.org/10.1016/j.dss.2015.04.003 (2015).
doi: 10.1016/j.dss.2015.04.003
Firouzabadi, N., Farshadfar, P., Haghnegahdar, M., Alavi-Shoushtari, A. & Ghanbarinezhad, V. Impact of ace 2 genetic variant on antidepressant efficacy of SSRIS. Acta Neuropsychiatr. 34, 1–25. https://doi.org/10.1017/neu.2021.32 (2021).
doi: 10.1017/neu.2021.32
Hastie, T., Tibshirani, R. & Friedman, J. The Elements of Statistical Learning: Data Mining, Inference, and Prediction. 2nd Ed. (Springer Series in Statistics, 2009).
Ali, N., Neagu, D. & Trundle, P. Evaluation of k-nearest neighbour classifier performance for heterogeneous data sets. SN Appl. Sci. https://doi.org/10.1007/s42452-019-1356-9 (2019).
doi: 10.1007/s42452-019-1356-9
Churcher, A. et al. An experimental analysis of attack classification using machine learning in IoT networks. Sensors https://doi.org/10.3390/s21020446 (2021).
doi: 10.3390/s21020446
pubmed: 33435202
pmcid: 7827441
Pavlidis, P., Wapinski, I. & Noble, W. S. Support vector machine classification on the web. Bioinformatics 20, 586–587. https://doi.org/10.1093/bioinformatics/btg461 (2004).
doi: 10.1093/bioinformatics/btg461
pubmed: 14990457
Goodfellow, I., Bengio, Y. & Courville, A. Deep Learning. http://www.deeplearningbook.org (MIT Press, 2016).
Yuan, Y., Su, W. & Zhu, M. Threshold-free measures for assessing the performance of medical screening tests. Front. Public Health 3, 57. https://doi.org/10.3389/fpubh.2015.00057 (2015).
doi: 10.3389/fpubh.2015.00057
pubmed: 25941668
pmcid: 4403252
Keilwagen, J., Grosse, I. & Grau, J. Area under precision-recall curves for weighted and unweighted data. PLOS ONE 9, 1–13. https://doi.org/10.1371/journal.pone.0092209 (2014).
doi: 10.1371/journal.pone.0092209
Pereira, D., Afonso, A. & Medeiros, F. Overview of Friedman’s test and post-hoc analysis. Commun. Stat.-Simul. Comput. 44, 2636–2653. https://doi.org/10.1080/03610918.2014.931971 (2015).
doi: 10.1080/03610918.2014.931971
Zhang, C., Li, Y., Yu, Z. & Tian, F. A Weighted Random Forest Approach to Improve Predictive Performance for Power System Transient Stability Assessment. 1259–1263. https://doi.org/10.1109/APPEEC.2016.7779695 (2016).
Maalouf, M. & Siddiqi, M. Weighted logistic regression for large-scale imbalanced and rare events data. Knowl.-Based Syst. 59, 142–148 (2014).
doi: 10.1016/j.knosys.2014.01.012
Chawla, N. V., Bowyer, K. W., Hall, L. O. & Kegelmeyer, W. P. Smote: Synthetic minority over-sampling technique. J. Artif. Int. Res. 16, 321–357 (2002).
Lopresti, A. L., Maker, G. L., Hood, S. D. & Drummond, P. D. A review of peripheral biomarkers in major depression: The potential of inflammatory and oxidative stress biomarkers. Prog. Neuro-Psychopharmacol. Biol. Psychiatry 48, 102–111. https://doi.org/10.1016/j.pnpbp.2013.09.017 (2014).
doi: 10.1016/j.pnpbp.2013.09.017