Machine Learning and Medication Adherence: Scoping Review

Aaron Bohlmann, Javed Mostafa, Manish Kumar, Aaron Bohlmann, Javed Mostafa, Manish Kumar

Abstract

Background: This is the first scoping review to focus broadly on the topics of machine learning and medication adherence.

Objective: This review aims to categorize, summarize, and analyze literature focused on using machine learning for actions related to medication adherence.

Methods: PubMed, Scopus, ACM Digital Library, IEEE, and Web of Science were searched to find works that meet the inclusion criteria. After full-text review, 43 works were included in the final analysis. Information of interest was systematically charted before inclusion in the final draft. Studies were placed into natural categories for additional analysis dependent upon the combination of actions related to medication adherence. The protocol for this scoping review was created using the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews) guidelines.

Results: Publications focused on predicting medication adherence have uncovered 20 strong predictors that were significant in two or more studies. A total of 13 studies that predicted medication adherence used either self-reported questionnaires or pharmacy claims data to determine medication adherence status. In addition, 13 studies that predicted medication adherence did so using either logistic regression, artificial neural networks, random forest, or support vector machines. Of the 15 studies that predicted medication adherence, 6 reported predictor accuracy, the lowest of which was 77.6%. Of 13 monitoring systems, 12 determined medication administration using medication container sensors or sensors in consumer electronics, like smartwatches or smartphones. A total of 11 monitoring systems used logistic regression, artificial neural networks, support vector machines, or random forest algorithms to determine medication administration. The 4 systems that monitored inhaler administration reported a classification accuracy of 93.75% or higher. The 2 systems that monitored medication status in patients with Parkinson disease reported a classification accuracy of 78% or higher. A total of 3 studies monitored medication administration using only smartwatch sensors and reported a classification accuracy of 78.6% or higher. Two systems that provided context-aware medication reminders helped patients to achieve an adherence level of 92% or higher. Two conversational artificial intelligence reminder systems significantly improved adherence rates when compared against traditional reminder systems.

Conclusions: Creation of systems that accurately predict medication adherence across multiple data sets may be possible due to predictors remaining strong across multiple studies. Higher quality measures of adherence should be adopted when possible so that prediction algorithms are based on accurate information. Currently, medication adherence can be predicted with a good level of accuracy, potentially allowing for the development of interventions aimed at preventing nonadherence. Monitoring systems that track inhaler use currently classify inhaler-related actions with an excellent level of accuracy, allowing for tracking of adherence and potentially proper inhaler technique. Systems that monitor medication states in patients with Parkinson disease can currently achieve a good level of classification accuracy and have the potential to inform medication therapy changes in the future. Medication administration monitoring systems that only use motion sensors in smartwatches can currently achieve a good level of classification accuracy but only when differentiating between a small number of possible activities. Context-aware reminder systems can help patients achieve high levels of medication adherence but are also intrusive, which may not be acceptable to users. Conversational artificial intelligence reminder systems can significantly improve adherence.

Keywords: adherence monitoring; adherence prediction; health technology; machine learning; medication adherence; medication compliance.

Conflict of interest statement

Conflicts of Interest: None declared.

©Aaron Bohlmann, Javed Mostafa, Manish Kumar. Originally published in JMIRx Med (https://med.jmirx.org), 24.11.2021.

Figures

Figure 1
Figure 1
Article review process.

References

    1. Adherence to long-term therapies: evidence for action. World Health Organization. 2003. [2020-04-30]. .
    1. Awan SE, Bennamoun M, Sohel F, Sanfilippo FM, Dwivedi G. Machine learning-based prediction of heart failure readmission or death: implications of choosing the right model and the right metrics. ESC Heart Fail. 2019 Apr;6(2):428–435. doi: 10.1002/ehf2.12419.
    1. Cresswell K, Callaghan M, Khan S, Sheikh Z, Mozaffar H, Sheikh A. Investigating the use of data-driven artificial intelligence in computerised decision support systems for health and social care: A systematic review. Health Informatics J. 2020 Sep;26(3):2138–2147. doi: 10.1177/1460458219900452.
    1. Vrijens B, De Geest S, Hughes DA, Przemyslaw K, Demonceau J, Ruppar T, Dobbels F, Fargher E, Morrison V, Lewek P, Matyjaszczyk M, Mshelia C, Clyne W, Aronson JK, Urquhart J, Project Team ABC. A new taxonomy for describing and defining adherence to medications. Br J Clin Pharmacol. 2012 May;73(5):691–705. doi: 10.1111/j.1365-2125.2012.04167.x.
    1. Walczak S, Okuboyejo S. An artificial neural network classification of prescription nonadherence. Int J Healthcare Inf Syst Inform. 2017;12(1):1–13. doi: 10.4018/ijhisi.2017010101.
    1. Son Y, Kim H, Kim E, Choi S, Lee S. Application of support vector machine for prediction of medication adherence in heart failure patients. Healthc Inform Res. 2010 Dec;16(4):253–9. doi: 10.4258/hir.2010.16.4.253.
    1. Aziz F, Malek S, Mhd Ali A, Wong M, Mosleh M, Milow P. Determining hypertensive patients' beliefs towards medication and associations with medication adherence using machine learning methods. PeerJ. 2020;8:e8286. doi: 10.7717/peerj.8286.8286
    1. Aznar-Lou I, Pottegård A, Fernández A, Peñarrubia-María MT, Serrano-Blanco A, Sabés-Figuera R, Gil-Girbau M, Fajó-Pascual M, Moreno-Peral P, Rubio-Valera M. Effect of copayment policies on initial medication non-adherence according to income: a population-based study. BMJ Qual Saf. 2018 Nov;27(11):878–891. doi: 10.1136/bmjqs-2017-007416.bmjqs-2017-007416
    1. Zhang JX, Meltzer DO. Identifying patients with cost-related medication non-adherence: a big-data approach. J Med Econ. 2016 Aug;19(8):806–11. doi: 10.1080/13696998.2016.1176031.
    1. Aznar-Lou I, Fernández A, Gil-Girbau M, Fajó-Pascual M, Moreno-Peral P, Peñarrubia-María MT, Serrano-Blanco A, Sánchez-Niubó A, March-Pujol MA, Jové AM, Rubio-Valera M. Initial medication non-adherence: prevalence and predictive factors in a cohort of 1.6 million primary care patients. Br J Clin Pharmacol. 2017 Jun;83(6):1328–1340. doi: 10.1111/bcp.13215.
    1. Haas K, Ben Miled Z, Mahoui M. Medication adherence prediction through online social forums: a case study of fibromyalgia. JMIR Med Inform. 2019 Apr 04;7(2):e12561. doi: 10.2196/12561. v7i2e12561
    1. Lu Z, Ying H, Lin F, Neufeld S, Luborsky M, Brawn DM, Sankar A. Multi-class support vector machines for modeling HIV/AIDS treatment adherence using patient data. 2005 IEEE International Joint Conference on Neural Networks; July 31-August 4, 2005; Montreal, QC. 2005. pp. 2417–2422.
    1. Franklin JM, Shrank WH, Lii J, Krumme AK, Matlin OS, Brennan TA, Choudhry NK. Observing versus predicting: initial patterns of filling predict long-term adherence more accurately than high-dimensional modeling techniques. Health Serv Res. 2016 Feb;51(1):220–39. doi: 10.1111/1475-6773.12310.
    1. Karanasiou GS, Tripoliti EE, Papadopoulos TG, Kalatzis FG, Goletsis Y, Naka KK, Bechlioulis A, Errachid A, Fotiadis DI. Predicting adherence of patients with HF through machine learning techniques. Healthc Technol Lett. 2016 Sep;3(3):165–170. doi: 10.1049/htl.2016.0041.HTL.2016.0041
    1. Bourdès V, Ferrières J, Amar J, Amelineau E, Bonnevay S, Berlion M, Danchin N. Prediction of persistence of combined evidence-based cardiovascular medications in patients with acute coronary syndrome after hospital discharge using neural networks. Med Biol Eng Comput. 2011 Aug;49(8):947–55. doi: 10.1007/s11517-011-0785-4.
    1. Kim N, McCarthy DE, Loh W, Cook JW, Piper ME, Schlam TR, Baker TB. Predictors of adherence to nicotine replacement therapy: machine learning evidence that perceived need predicts medication use. Drug Alcohol Depend. 2019 Dec 01;205:107668. doi: 10.1016/j.drugalcdep.2019.107668. S0376-8716(19)30445-4
    1. Kardas P, Cieszyński J, Czech M, Banaś I, Lewek P. Primary nonadherence to medication and its drivers in Poland: findings from the electronic prescription pilot analysis. Pol Arch Intern Med. 2020 Jan 31;130(1):8–16. doi: 10.20452/pamw.14994.
    1. Desai R, Jo A, Marlow NM. Risk for medication nonadherence among Medicaid enrollees with fibromyalgia: development of a validated risk prediction tool. Pain Pract. 2019 Mar;19(3):295–302. doi: 10.1111/papr.12743.
    1. Elahinia H, Raffa JD, Wu JTY, Ghassemi MM. Predicting medical nonadherence using natural language processing. 2017 IEEE MIT Undergraduate Research Technology Conference; November 3-5, 2017; Cambridge, MA. 2017.
    1. Hezarjaribi N, Fallahzadeh R, Ghasemzadeh H. A machine learning approach for medication adherence monitoring using body-worn sensors. 2016 Design, Automation & Test in Europe Conference & Exhibition; March 14-18, 2016; Dresden, Germany. 2016.
    1. Fozoonmayeh D, Le HV, Wittfoth E, Geng C, Ha N, Wang J, Vasilenko M, Ahn Y, Woodbridge DM. A scalable smartwatch-based medication intake detection system using distributed machine learning. J Med Syst. 2020 Feb 28;44(4):76. doi: 10.1007/s10916-019-1518-8.10.1007/s10916-019-1518-8
    1. Aldeer M, Alaziz M, Ortiz J, Howard R, Martin R. A sensing-based framework for medication compliance monitoring. Proceedings of the 1st ACM International Workshop on Device-Free Human Sensing; DFHS'19; November 10, 2019; New York, NY. 2019. pp. 52–56.
    1. Ntalianis V, Nousias S, Lalos AS, Birbas M, Tsafas N, Moustakas K. Assessment of medication adherence in respiratory diseases through deep sparse convolutional coding. 24th IEEE International Conference on Emerging Technologies and Factory Automation; September 10-13, 2019; Zaragoza, Spain. 2019.
    1. Tucker CS, Behoora I, Nembhard HB, Lewis M, Sterling NW, Huang X. Machine learning classification of medication adherence in patients with movement disorders using non-wearable sensors. Comput Biol Med. 2015 Nov 01;66:120–34. doi: 10.1016/j.compbiomed.2015.08.012. S0010-4825(15)00293-0
    1. Ma J, Ovalle A, Woodbridge DMK. Medhere: a smartwatch-based medication adherence monitoring system using machine learning and distributed computing. Annu Int Conf IEEE Eng Med Biol Soc. 2018 Jul;2018:4945–4948. doi: 10.1109/EMBC.2018.8513169.
    1. Nousias S, Lakoumentas J, Lalos A, Kikidis D, Moustakas K, Votis K, Tzovaras D. Monitoring asthma medication adherence through content based audio classification. 2016 IEEE Symposium Series on Computational Intelligence; December 6-9, 2016; Athens, Greece. 2016.
    1. Bilodeau G, Ammouri S. Monitoring of medication intake using a camera system. J Med Syst. 2011 Jun;35(3):377–89. doi: 10.1007/s10916-009-9374-6.
    1. Aldeer M, Ortiz J, Howard R, Martin R. PatientSense: patient discrimination from in-bottle sensors data. Proceedings of the 16th EAI International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services; MobiQuitous '19; November 12-14, 2019; Houston, TX. 2019. pp. 143–152.
    1. Zhang H, Xu C, Li H, Rathore AS, Song C, Yan Z, Li D, Lin F, Wang K, Xu W. PDMove: towards passive medication adherence monitoring of Parkinson's disease using smartphone-based gait assessment. Proc ACM Interactive Mobile Wearable Ubiquitous Technologies. 2019 Sep 09;3(3):1–23. doi: 10.1145/3351281.
    1. Pettas D, Nousias S, Zacharaki E, Moustakas K. Recognition of breathing activity and medication adherence using LSTM neural networks. IEEE 19th International Conference on Bioinformatics and Bioengineering; October 28-30, 2019; Athens, Greece. 2019. pp. 941–946.
    1. Moldovan D, Antal M, Pop C, Olosutean A, Cioara T, Anghel I, Salomie I. Spark-based classification algorithms for daily living activities. In: Silhavy R, editor. Artificial Intelligence and Algorithms in Intelligent Systems Proceedings of 7th Computer Science On-line Conference 2018, Volume 2. Cham: Springer; 2019. pp. 69–78.
    1. Kikidis D, Votis K, Tzovaras D. Utilizing convolution neural networks for the acoustic detection of inhaler actuations. 2015 E-Health and Bioengineering Conference; November 19-21, 2015; Iasi, Romania. 2015.
    1. da Silva VJ, da Silva Souza V, Guimarães da Cruz R, Mesquita Vidal Martinez de Lucena J, Jazdi N, Ferreira de Lucena Junior V. Commercial devices-based system designed to improve the treatment adherence of hypertensive patients. Sensors (Basel) 2019 Oct 18;19(20):4539. doi: 10.3390/s19204539. s19204539
    1. Lundell J, Hayes T, Vurgun S, Ozertem U, Kimel J, Kaye J, Guilak F, Pavel M. Continuous activity monitoring and intelligent contextual prompting to improve medication adherence. Annu Int Conf IEEE Eng Med Biol Soc. 2007;2007:6287–90. doi: 10.1109/IEMBS.2007.4353792.
    1. Silva V, Souza V, da Cruz Rg, Jazdi N, de Lucena Vf. MobiHealth: a system to improve medication adherence in hypertensive patients. Procedia Computer Sci. 2018;141:366–373. doi: 10.1016/j.procs.2018.10.188.
    1. Silva VJ, Rodrigues MAS, Barreto R, de Lucena V. UbMed: a ubiquitous system for monitoring medication adherence. IEEE 18th International Conference on e-Health Networking, Applications and Services; September 14-16, 2016; Munich, Germany. 2016.
    1. Nousias S, Lalos AS, Arvanitis G, Moustakas K, Tsirelis T, Kikidis D, Votis K, Tzovaras D. An mHealth system for monitoring medication adherence in obstructive respiratory diseases using content based audio classification. IEEE Access. 2018;6:11871–11882. doi: 10.1109/access.2018.2809611.
    1. Persell SD, Peprah YA, Lipiszko D, Lee JY, Li JJ, Ciolino JD, Karmali KN, Sato H. Effect of home blood pressure monitoring via a smartphone hypertension coaching application or tracking application on adults with uncontrolled hypertension: a randomized clinical trial. JAMA Netw Open. 2020 Mar 02;3(3):e200255. doi: 10.1001/jamanetworkopen.2020.0255. 2761794
    1. Brar Prayaga R, Jeong EW, Feger E, Noble HK, Kmiec M, Prayaga RS. Improving refill adherence in Medicare patients with tailored and interactive mobile text messaging: pilot study. JMIR Mhealth Uhealth. 2018 Jan 30;6(1):e30. doi: 10.2196/mhealth.8930. v6i1e30
    1. Chaix B, Bibault J, Pienkowski A, Delamon G, Guillemassé A, Nectoux P, Brouard B. When chatbots meet patients: one-year prospective study of conversations between patients with breast cancer and a chatbot. JMIR Cancer. 2019 May 02;5(1):e12856. doi: 10.2196/12856. v5i1e12856
    1. Curci S, Mura A, Riboni D. Toward naturalistic self-monitoring of medicine intake. Proceedings of the 12th Biannual Conference on Italian SIGCHI Chapter; CHItaly '17; September 18-20, 2017; Cagliari, Italy. 2017. pp. 1–6.
    1. Labovitz DL, Shafner L, Reyes Gil M, Virmani D, Hanina A. Using artificial intelligence to reduce the risk of nonadherence in patients on anticoagulation therapy. Stroke. 2017 May;48(5):1416–1419. doi: 10.1161/STROKEAHA.116.016281. STROKEAHA.116.016281
    1. Brar Prayaga R, Agrawal R, Nguyen B, Jeong EW, Noble HK, Paster A, Prayaga RS. Impact of social determinants of health and demographics on refill requests by Medicare patients using a conversational artificial intelligence text messaging solution: cross-sectional study. JMIR Mhealth Uhealth. 2019 Nov 18;7(11):e15771. doi: 10.2196/15771. v7i11e15771
    1. Killian J, Wilder B, Sharma A, Choudhary V, Dilkina B, Tambe M. Learning to prescribe interventions for tuberculosis patients using digital adherence data. Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining; KDD '19; August 4-8, 2019; Anchorage, AK. 2019. pp. 2430–2438.
    1. Bain EE, Shafner L, Walling DP, Othman AA, Chuang-Stein C, Hinkle J, Hanina A. Use of a novel artificial intelligence platform on mobile devices to assess dosing compliance in a phase 2 clinical trial in subjects with schizophrenia. JMIR Mhealth Uhealth. 2017 Feb 21;5(2):e18. doi: 10.2196/mhealth.7030. v5i2e18
    1. Tripoliti EE, Papadopoulos TG, Karanasiou GS, Kalatzis FG, Goletsis Y, Bechlioulis A, Ghimenti S, Lomonaco T, Bellagambi F, Fuoco R, Marzilli M, Scali MC, Naka KK, Errachid A, Fotiadis DI. Estimation of heart failure patients medication adherence through the utilization of saliva and breath biomarkers and data mining techniques. IEEE 30th International Symposium on Computer-Based Medical Systems; June 22-24, 2017; Thessaloniki, Greece. 2017.
    1. Piette JD, Sussman JB, Pfeiffer PN, Silveira MJ, Singh S, Lavieri MS. Maximizing the value of mobile health monitoring by avoiding redundant patient reports: prediction of depression-related symptoms and adherence problems in automated health assessment services. J Med Internet Res. 2013 Jul 05;15(7):e118. doi: 10.2196/jmir.2582. v15i7e118
    1. Stirratt MJ, Dunbar-Jacob J, Crane HM, Simoni JM, Czajkowski S, Hilliard ME, Aikens JE, Hunter CM, Velligan DI, Huntley K, Ogedegbe G, Rand CS, Schron E, Nilsen WJ. Self-report measures of medication adherence behavior: recommendations on optimal use. Transl Behav Med. 2015 Dec;5(4):470–82. doi: 10.1007/s13142-015-0315-2. 315

Source: PubMed

Sponsor e collaboratori

Condizioni mediche

Interventi farmacologici

3
Sottoscrivi