Predicting Adherence to Internet-Delivered Psychotherapy for Symptoms of Depression and Anxiety After Myocardial Infarction: Machine Learning Insights From the U-CARE Heart Randomized Controlled Trial

John Wallert, Emelie Gustafson, Claes Held, Guy Madison, Fredrika Norlund, Louise von Essen, Erik Martin Gustaf Olsson, John Wallert, Emelie Gustafson, Claes Held, Guy Madison, Fredrika Norlund, Louise von Essen, Erik Martin Gustaf Olsson

Abstract

Background: Low adherence to recommended treatments is a multifactorial problem for patients in rehabilitation after myocardial infarction (MI). In a nationwide trial of internet-delivered cognitive behavior therapy (iCBT) for the high-risk subgroup of patients with MI also reporting symptoms of anxiety, depression, or both (MI-ANXDEP), adherence was low. Since low adherence to psychotherapy leads to a waste of therapeutic resources and risky treatment abortion in MI-ANXDEP patients, identifying early predictors for adherence is potentially valuable for effective targeted care.

Objectives: The goal of the research was to use supervised machine learning to investigate both established and novel predictors for iCBT adherence in MI-ANXDEP patients.

Methods: Data were from 90 MI-ANXDEP patients recruited from 25 hospitals in Sweden and randomized to treatment in the iCBT trial Uppsala University Psychosocial Care Programme (U-CARE) Heart study. Time point of prediction was at completion of the first homework assignment. Adherence was defined as having completed more than 2 homework assignments within the 14-week treatment period. A supervised machine learning procedure was applied to identify the most potent predictors for adherence available at the first treatment session from a range of demographic, clinical, psychometric, and linguistic predictors. The internal binary classifier was a random forest model within a 3×10-fold cross-validated recursive feature elimination (RFE) resampling which selected the final predictor subset that best differentiated adherers versus nonadherers.

Results: Patient mean age was 58.4 years (SD 9.4), 62% (56/90) were men, and 48% (43/90) were adherent. Out of the 34 potential predictors for adherence, RFE selected an optimal subset of 56% (19/34; Accuracy 0.64, 95% CI 0.61-0.68, P<.001). The strongest predictors for adherence were, in order of importance, (1) self-assessed cardiac-related fear, (2) sex, and (3) the number of words the patient used to answer the first homework assignment.

Conclusions: For developing and testing effective iCBT interventions, investigating factors that predict adherence is important. Adherence to iCBT for MI-ANXDEP patients in the U-CARE Heart trial was best predicted by cardiac-related fear and sex, consistent with previous research, but also by novel linguistic predictors from written patient behavior which conceivably indicate verbal ability or therapeutic alliance. Future research should investigate potential causal mechanisms and seek to determine what underlying constructs the linguistic predictors tap into. Whether these findings replicate for other interventions outside of Sweden, in larger samples, and for patients with other conditions who are offered iCBT should also be investigated.

Trial registration: ClinicalTrials.gov NCT01504191; https://ichgcp.net/clinical-trials-registry/NCT01504191 (Archived at Webcite at http://www.webcitation.org/6xWWSEQ22).

Keywords: Web-based interventions; applied predictive modeling; cardiac rehabilitation; linguistics; recursive feature elimination; supervised machine learning; treatment adherence and compliance.

Conflict of interest statement

Conflicts of Interest: None declared.

©John Wallert, Emelie Gustafson, Claes Held, Guy Madison, Fredrika Norlund, Louise von Essen, Erik Martin Gustaf Olsson. Originally published in the Journal of Medical Internet Research (http://www.jmir.org), 10.10.2018.

Figures

Figure 1
Figure 1
Predictor selection result with recursive feature elimination.
Figure 2
Figure 2
Relative importance of each predictor for adherence sorted by group. BADS: Behavioral Activation for Depression Scale–Short Form; BMI: body mass index; CAQ: Cardiac Anxiety Questionnaire; EQ5D: European Quality of Life Questionnaire–Five Dimensions; HADS: Hospital Anxiety and Depression Scale ; MI: myocardial infarction; VAS: visual analog scale.

References

    1. GBD 2013 Mortality and Causes of Death Collaborators Global, regional, and national age-sex specific all-cause and cause-specific mortality for 240 causes of death, 1990-2013: a systematic analysis for the Global Burden of Disease Study 2013. Lancet. 2015 Jan 10;385(9963):117–171. doi: 10.1016/S0140-6736(14)61682-2.
    1. Piepoli MF, Corrà U, Dendale P, Frederix I, Prescott E, Schmid JP, Cupples M, Deaton C, Doherty P, Giannuzzi P, Graham I, Hansen TB, Jennings C, Landmesser U, Marques-Vidal P, Vrints C, Walker D, Bueno H, Fitzsimons D, Pelliccia A. Challenges in secondary prevention after acute myocardial infarction: a call for action. Eur J Prev Cardiol. 2016 Dec;23(18):1994–2006. doi: 10.1177/2047487316663873.
    1. Yusuf S, Hawken S, Ounpuu S, Dans T, Avezum A, Lanas F, McQueen M, Budaj A, Pais P, Varigos J, Lisheng L, INTERHEART Study Investigators Effect of potentially modifiable risk factors associated with myocardial infarction in 52 countries (the INTERHEART study): case-control study. Lancet. 2004;364(9438):937–952. doi: 10.1016/S0140-6736(04)17018-9.
    1. Roest AM, Martens EJ, Denollet J, de Jonge P. Prognostic association of anxiety post myocardial infarction with mortality and new cardiac events: a meta-analysis. Psychosom Med. 2010 Jul;72(6):563–569. doi: 10.1097/PSY.0b013e3181dbff97.
    1. Meijer A, Conradi HJ, Bos EH, Thombs BD, van Melle JP, de Jonge P. Prognostic association of depression following myocardial infarction with mortality and cardiovascular events: a meta-analysis of 25 years of research. Gen Hosp Psychiatry. 2011;33(3):203–216. doi: 10.1016/j.genhosppsych.2011.02.007.
    1. Huffman JC, Mastromauro CA, Beach SR, Celano CM, DuBois CM, Healy BC, Suarez L, Rollman BL, Januzzi JL. Collaborative care for depression and anxiety disorders in patients with recent cardiac events: the Management of Sadness and Anxiety in Cardiology (MOSAIC) randomized clinical trial. JAMA Intern Med. 2014 Jun;174(6):927–935. doi: 10.1001/jamainternmed.2014.739.
    1. Davidson KW, Rieckmann N, Clemow L, Schwartz JE, Shimbo D, Medina V, Albanese G, Kronish I, Hegel M, Burg MM. Enhanced depression care for patients with acute coronary syndrome and persistent depressive symptoms: coronary psychosocial evaluation studies randomized controlled trial. Arch Intern Med. 2010 Apr 12;170(7):600–608. doi: 10.1001/archinternmed.2010.29.
    1. Dickens C, Cherrington A, Adeyemi I, Roughley K, Bower P, Garrett C, Bundy C, Coventry P. Characteristics of psychological interventions that improve depression in people with coronary heart disease: a systematic review and meta-regression. Psychosom Med. 2013 Feb;75(2):211–221. doi: 10.1097/PSY.0b013e31827ac009.
    1. Piepoli MF, Hoes AW, Agewall S, Albus C, Brotons C, Catapano AL, Cooney M, Corr&agrave; U, Cosyns B, Deaton C, Graham I, Hall MS, Hobbs FDR, L&oslash;chen M, L&ouml;llgen H, Marques-Vidal P, Perk J, Prescott E, Redon J, Richter DJ, Sattar N, Smulders Y, Tiberi M, van der Worp HB, van Dis I, Verschuren WMM, Binno S, ESC Scientific Document Group 2016 European guidelines on cardiovascular disease prevention in clinical practice: the Sixth Joint Task Force of the European Society of Cardiology and other societies on cardiovascular disease prevention in clinical practice. Eur Heart J. 2016 Dec 01;37(29):2315–2381. doi: 10.1093/eurheartj/ehw106.
    1. Olthuis JV, Watt MC, Bailey K, Hayden JA, Stewart SH. Therapist-supported Internet cognitive behavioural therapy for anxiety disorders in adults. Cochrane Database Syst Rev. 2016 Mar 12;3:CD011565. doi: 10.1002/14651858.CD011565.pub2.
    1. Hedman E, Ljótsson B, Lindefors N. Cognitive behavior therapy via the Internet: a systematic review of applications, clinical efficacy and cost-effectiveness. Expert Rev Pharmacoecon Outcomes Res. 2012 Dec;12(6):745–764. doi: 10.1586/erp.12.67.
    1. Alfonsson S. Treatment Adherence in Internet-Based CBT: The Effects of Presentation, Support and Motivation [doctoral thesis] Acta Universitatis Upsaliensis: Uppsala University; 2016.
    1. Norlund F, Wallin E, Olsson EMG, Wallert J, Burell G, von Essen L, Held C. Internet-based cognitive behavioral therapy for symptoms of depression and anxiety among patients with a recent myocardial infarction: the U-CARE heart randomized controlled trial. J Med Internet Res. 2018 Mar 08;20(3):e88. doi: 10.2196/jmir.9710.
    1. Norlund F, Olsson EMG, Burell G, Wallin E, Held C. Treatment of depression and anxiety with internet-based cognitive behavior therapy in patients with a recent myocardial infarction (U-CARE Heart): study protocol for a randomized controlled trial. Trials. 2015 Apr 11;16:154. doi: 10.1186/s13063-015-0689-y.
    1. Waller R, Gilbody S. Barriers to the uptake of computerized cognitive behavioural therapy: a systematic review of the quantitative and qualitative evidence. Psychol Med. 2009 May;39(5):705–712. doi: 10.1017/S0033291708004224.
    1. Woodford J, Farrand P, Bessant M, Williams C. Recruitment into a guided internet based CBT (iCBT) intervention for depression: lesson learnt from the failure of a prevalence recruitment strategy. Contemp Clin Trials. 2011 Sep;32(5):641–648. doi: 10.1016/j.cct.2011.04.013.
    1. Andersson G, Hedman E. Effectiveness of guided internet-based cognitive behavior therapy in regular clinical settings. Verhaltenstherapie. 2013;23(3):140–148. doi: 10.1159/000354779.
    1. Kolandaivelu K, Leiden BB, O'Gara PT, Bhatt DL. Non-adherence to cardiovascular medications. Eur Heart J. 2014 Dec 07;35(46):3267–3276. doi: 10.1093/eurheartj/ehu364.
    1. El Alaoui S, Ljótsson B, Hedman E, Kaldo V, Andersson E, Rück C, Andersson G, Lindefors N. Predictors of symptomatic change and adherence in Internet-based cognitive behaviour therapy for social anxiety disorder in routine psychiatric care. PLoS One. 2015;10(4):e0124258. doi: 10.1371/journal.pone.0124258.
    1. Karyotaki E, Kleiboer A, Smit F, Turner DT, Pastor AM, Andersson G, Berger T, Botella C, Breton JM, Carlbring P, Christensen H, Griffiths K, Donker T, Farrer L, Huibers MJH, Lenndin J, Mackinnon A, Meyer B, Moritz S, Riper H, Spek V, Vernmark K, Cuijpers P. Predictors of treatment dropout in self-guided web-based interventions for depression: an 'individual patient data' meta-analysis. Psychol Med. 2015 Oct;45(13):2717–2726. doi: 10.1017/S0033291715000665.
    1. Pennebaker JW, Mehl MR, Niederhoffer KG. Psychological aspects of natural language. use: our words, our selves. Annu Rev Psychol. 2003;54:547–577. doi: 10.1146/annurev.psych.54.101601.145041.
    1. Dirkse D, Hadjistavropoulos HD, Hesser H, Barak A. Linguistic analysis of communication in therapist-assisted internet-delivered cognitive behavior therapy for generalized anxiety disorder. Cogn Behav Ther. 2015 Sep;44(1):21–32. doi: 10.1080/16506073.2014.952773.
    1. Zinken J, Zinken K, Wilson JC, Butler L, Skinner T. Analysis of syntax and word use to predict successful participation in guided self-help for anxiety and depression. Psychiatry Res. 2010 Sep 30;179(2):181–186. doi: 10.1016/j.psychres.2010.04.011.
    1. Van der Zanden R, Curie K, Van Londen M, Kramer J, Steen G, Cuijpers P. Web-based depression treatment: associations of clients' word use with adherence and outcome. J Affect Disord. 2014 May;160:10–13. doi: 10.1016/j.jad.2014.01.005.
    1. Wallin E, Norlund F, Olsson EMG, Burell G, Held C, Carlsson T. Treatment activity, user satisfaction, and experienced usability of internet-based cognitive behavioral therapy for adults with depression and anxiety after a myocardial infarction: mixed-methods study. J Med Internet Res. 2018 Mar 16;20(3):e87. doi: 10.2196/jmir.9690.
    1. Hastie T, Tibshirani R, Friedman J. The Elements of Statistical Learning: Data Mining, Inference, and Prediction. 2nd Edition. New York: Springer; 2009.
    1. Eifert GH, Thompson RN, Zvolensky MJ, Edwards K, Frazer NL, Haddad JW, Davig J. The cardiac anxiety questionnaire: development and preliminary validity. Behav Res Ther. 2000 Oct;38(10):1039–1053.
    1. Vaglio J, Conard M, Poston WS, O'Keefe J, Haddock CK, House J, Spertus JA. Testing the performance of the ENRICHD Social Support Instrument in cardiac patients. Health Qual Life Outcomes. 2004 May 13;2:24. doi: 10.1186/1477-7525-2-24.
    1. Svanborg P, Asberg M. A comparison between the Beck Depression Inventory (BDI) and the self-rating version of the Montgomery Asberg Depression Rating Scale (MADRS) J Affect Disord. 2001 May;64(2-3):203–216.
    1. Holländare F, Andersson G, Engström I. A comparison of psychometric properties between internet and paper versions of two depression instruments (BDI-II and MADRS-S) administered to clinic patients. J Med Internet Res. 2010;12(5):e49. doi: 10.2196/jmir.1392.
    1. Manos RC, Kanter JW, Luo W. The behavioral activation for depression scale-short form: development and validation. Behav Ther. 2011 Dec;42(4):726–739. doi: 10.1016/j.beth.2011.04.004.
    1. Zigmond AS, Snaith RP. The hospital anxiety and depression scale. Acta Psychiatr Scand. 1983 Jun;67(6):361–370.
    1. Beretta L, Santaniello A. Nearest neighbor imputation algorithms: a critical evaluation. BMC Med Inform Decis Mak. 2016 Dec 25;16 Suppl 3:74. doi: 10.1186/s12911-016-0318-z.
    1. Jönsson P, Wohlin C. An evaluation of k nearest neighbour imputation using Likert data. METRICS '04 Proceedings of the Software Metrics, 10th International Symposium. 2004:108–118.
    1. Kowarik A, Templ M. Imputation with R package VIM. J Stat Softw. 2016;74(7):1–16.
    1. Breiman L. Random forests. Machine Learn. 2001;45:5–32.
    1. Breiman L, Friedman J, Olshen R, Stone C. Classification and Regression Trees. Belmont: Wadsworth Books; 1984.
    1. Wallert J, Tomasoni M, Madison G, Held C. Predicting two-year survival versus non-survival after first myocardial infarction using machine learning and Swedish national register data. BMC Med Inform Decis Mak. 2017 Jul 05;17(1):99. doi: 10.1186/s12911-017-0500-y.
    1. Kuhn M. Building predictive models in R using the Caret package. J Stat Soft. 2008;28(5):1–26. doi: 10.18637/jss.v028.i05.
    1. Anthony L. AntConc version 3.4.4. Tokyo: Waseda University; 2016.
    1. Östling R. Stagger: an open-source part of speech tagger for Swedish. Northern Eur J Lang Technol. 2013 Sep 16;3:1–18. doi: 10.3384/nejlt.2000-1533.1331.
    1. R: A Language and Environment for Statistical Computing. Vienna: Foundation for Statistical Computing; 2015.
    1. Zullo MD, Gathright EC, Dolansky MA, Josephson RA, Cheruvu VK, Hughes JW. Influence of depression on utilization of cardiac rehabilitation postmyocardial infarction: a study of 158,991 Medicare beneficiaries. J Cardiopulm Rehabil Prev. 2017 Jan;37(1):22–29. doi: 10.1097/HCR.0000000000000222.
    1. Păsărelu CR, Andersson G, Bergman NL, Dobrean A. Internet-delivered transdiagnostic and tailored cognitive behavioral therapy for anxiety and depression: a systematic review and meta-analysis of randomized controlled trials. Cogn Behav Ther. 2017 Jan;46(1):1–28. doi: 10.1080/16506073.2016.1231219.

Source: PubMed

Sponsorer og samarbejdspartnere

Medicinske tilstande

Narkotikainterventioner

3
Abonner