Volume 3 Number 1 2022
When Prediction Isn't Enough: Causal Machine Learning for Personalized Treatment Selection and Clinical Outcome Prediction
Sanjida Alam Eshra1*, Md. Fatin2
Journal of Primeasia 3 (1) 1-14 https://doi.org/10.25163/primeasia.3110913
Submitted: 30 May 2022 Revised: 04 August 2022 Accepted: 10 August 2022 Published: 12 August 2022
Machine learning has become part of the everyday vocabulary of clinical research, and for good reason — it is good at finding patterns. What it is not naturally built to do, though, is tell us what would have happened if a patient had received a different treatment, and that gap matters a great deal once the goal shifts from prediction to decision-making. Causal machine learning tries to close that gap by pairing causal inference with modern ML, so that treatment effects, not just correlations, become something we can estimate at the level of a single patient. In this narrative review, we trace the conceptual foundations of this approach — counterfactual reasoning and the potential-outcomes framework — through to the estimation methods built on top of them: meta-learners, causal forests, and deep learning-based causal models, among others. Across all of these, the same story repeats itself in different technical dialects: these methods can recover individualized and subgroup-level treatment effects reasonably well when data are rich and confounding is at least partially measured, and considerably less well when either condition fails. Applications in oncology, cardiovascular care, and critical care illustrate the promise; unmeasured confounding, patchy data quality, and limited interpretability illustrate the ceiling. We also try to be honest about the boundaries of the exercise itself: this is a narrative synthesis of the literature, not a systematic one, and we have not attempted a formal risk-of-bias assessment of the sources it draws on. What emerges, on balance, is a field with real conceptual promise for personalized medicine — but one whose clinical value will hinge on validation discipline, external cohorts, sensitivity analyses, and honest uncertainty reporting, rather than on ever more elaborate architectures.
Keywords: Causal Machine Learning; Causal Inference; Personalized Medicine; Treatment Effect Estimation; Clinical Decision Support
Ahmad, Z., Rahim, S., Zubair, M., & Abdul-Ghafar, J. (2021). Artificial intelligence (AI) in medicine, current applications and future role with special emphasis on its potential and promise in pathology: present and future impact, obstacles including costs and acceptance among pathologists, practical and philosophical considerations. A comprehensive review. Diagnostic Pathology, 16(1), 24. https://doi.org/10.1186/s13000-021-01085-4
Alber, M., Buganza Tepole, A., Cannon, W. R., De, S., Dura-Bernal, S., Garikipati, K., Karniadakis, G., Lytton, W. W., Perdikaris, P., Petzold, L., & Kuhl, E. (2019). Integrating machine learning and multiscale modeling—perspectives, challenges, and opportunities in the biological, biomedical, and behavioral sciences. Npj Digital Medicine, 2(1), 115. https://doi.org/10.1038/s41746-019-0193-y
Badgeley, M. A., Zech, J. R., Oakden-Rayner, L., Glicksberg, B. S., Liu, M., Gale, W., McConnell, M. V., Percha, B., Snyder, T. M., & Dudley, J. T. (2019). Deep learning predicts hip fracture using confounding patient and healthcare variables. Npj Digital Medicine, 2(1), 31. https://doi.org/10.1038/s41746-019-0105-1
Baubeta Fridh, E., Andersson, M., Thuresson, M., Sigvant, B., Kragsterman, B., Johansson, S., Hasvold, P., Falkenberg, M., & Nordanstig, J. (2017). Amputation Rates, Mortality, and Pre-operative Comorbidities in Patients Revascularised for Intermittent Claudication or Critical Limb Ischaemia: A Population Based Study. European Journal of Vascular and Endovascular Surgery, 54(4), 480–486. https://doi.org/10.1016/j.ejvs.2017.07.005
Bica, I., Alaa, A. M., Lambert, C., & van der Schaar, M. (2021). From Real-World Patient Data to Individualized Treatment Effects Using Machine Learning: Current and Future Methods to Address Underlying Challenges. Clinical Pharmacology & Therapeutics, 109(1), 87–100. https://doi.org/10.1002/cpt.1907
Boevé, L. M. S., Hulshof, M. C. C. M., Vis, A. N., Zwinderman, A. H., Twisk, J. W. R., Witjes, W. P. J., Delaere, K. P. J., Moorselaar, R. J. A. van, Verhagen, P. C. M. S., & van Andel, G. (2019). Effect on Survival of Androgen Deprivation Therapy Alone Compared to Androgen Deprivation Therapy Combined with Concurrent Radiation Therapy to the Prostate in Patients with Primary Bone Metastatic Prostate Cancer in a Prospective Randomised Clinical Trial: Data from the HORRAD Trial. European Urology, 75(3), 410–418. https://doi.org/10.1016/j.eururo.2018.09.008
Burhenn, P. S., McCarthy, A. L., Begue, A., Nightingale, G., Cheng, K., & Kenis, C. (2016). Geriatric assessment in daily oncology practice for nurses and allied health care professionals: Opinion paper of the Nursing and Allied Health Interest Group of the International Society of Geriatric Oncology (SIOG). Journal of Geriatric Oncology, 7(5), 315–324. https://doi.org/10.1016/j.jgo.2016.02.006
Cammarota, G., Ianiro, G., Ahern, A., Carbone, C., Temko, A., Claesson, M. J., Gasbarrini, A., & Tortora, G. (2020). Gut microbiome, big data and machine learning to promote precision medicine for cancer. Nature Reviews Gastroenterology & Hepatology, 17(10), 635–648. https://doi.org/10.1038/s41575-020-0327-3
Clarke, N. W., Ali, A., Ingleby, F. C., Hoyle, A., Amos, C. L., Attard, G., Brawley, C. D., Calvert, J., Chowdhury, S., Cook, A., Cross, W., Dearnaley, D. P., Douis, H., Gilbert, D., Gillessen, S., Jones, R. J., Langley, R. E., MacNair, A., Malik, Z., … James, N. D. (2019). Addition of docetaxel to hormonal therapy in low- and high-burden metastatic hormone sensitive prostate cancer: long-term survival results from the STAMPEDE trial. Annals of Oncology, 30(12), 1992–2003. https://doi.org/10.1093/annonc/mdz396
Coulter, A., Entwistle, V. A., Eccles, A., Ryan, S., Shepperd, S., & Perera, R. (2015). Personalised care planning for adults with chronic or long-term health conditions. Cochrane Database of Systematic Reviews, 2015(3). https://doi.org/10.1002/14651858.CD010523.pub2
Currie, G., & Delles, C. (2018). Precision Medicine and Personalized Medicine in Cardiovascular Disease (pp. 589–605). https://doi.org/10.1007/978-3-319-77932-4_36
Derakhshan, P., Azadmanjir, Z., Naghdi, K., Habibi Arejan, R., Safdarian, M., Zarei, M. R., Jazayeri, S. B., Sharif-Alhoseini, M., Arab Kheradmand, J., Amirjamshidi, A., Ghodsi, Z., Faghih Jooybari, M., Mohammadzadeh, M., Khazaeipour, Z., Abdollah Zadegan, S., Abedi, A., Oreilly, G., Noonan, V., Benzel, E. C., … Rahimi-Movaghar, V. (2021). The impact of data quality assurance and control solutions on the completeness, accuracy, and consistency of data in a national spinal cord injury registry of Iran (NSCIR-IR). Spinal Cord Series and Cases, 7(1), 51. https://doi.org/10.1038/s41394-020-00358-2
Geeslin, M. G., & Gaskin, C. M. (2016). Electronic Health Record–Driven Workflow for Diagnostic Radiologists. Journal of the American College of Radiology, 13(1), 45–53. https://doi.org/10.1016/j.jacr.2015.08.008
Goetz, L. H., & Schork, N. J. (2018). Personalized medicine: motivation, challenges, and progress. Fertility and Sterility, 109(6), 952–963. https://doi.org/10.1016/j.fertnstert.2018.05.006
Golas, S. B., Shibahara, T., Agboola, S., Otaki, H., Sato, J., Nakae, T., Hisamitsu, T., Kojima, G., Felsted, J., Kakarmath, S., Kvedar, J., & Jethwani, K. (2018). A machine learning model to predict the risk of 30-day readmissions in patients with heart failure: a retrospective analysis of electronic medical records data. BMC Medical Informatics and Decision Making, 18(1), 44. https://doi.org/10.1186/s12911-018-0620-z
Huang, S.-C., Pareek, A., Seyyedi, S., Banerjee, I., & Lungren, M. P. (2020). Fusion of medical imaging and electronic health records using deep learning: a systematic review and implementation guidelines. Npj Digital Medicine, 3(1), 136. https://doi.org/10.1038/s41746-020-00341-z
Imhof, C., Bergamin, P., & McGarrity, S. (2020). Implementation of Adaptive Learning Systems: Current State and Potential (pp. 93–115). https://doi.org/10.1007/978-3-030-48190-2_6
Iqbal, M. J., Javed, Z., Sadia, H., Qureshi, I. A., Irshad, A., Ahmed, R., Malik, K., Raza, S., Abbas, A., Pezzani, R., & Sharifi-Rad, J. (2021). Clinical applications of artificial intelligence and machine learning in cancer diagnosis: looking into the future. Cancer Cell International, 21(1), 270. https://doi.org/10.1186/s12935-021-01981-1
Jacob, D. (2021). CATE meets ML. Digital Finance, 3(2), 99–148. https://doi.org/10.1007/s42521-021-00033-7
Jacoba, C. M. P., Celi, L. A., & Silva, P. S. (2021). Biomarkers for Progression in Diabetic Retinopathy: Expanding Personalized Medicine through Integration of AI with Electronic Health Records. Seminars in Ophthalmology, 36(4), 250–257. https://doi.org/10.1080/08820538.2021.1893351
Johnson, K. B., Wei, W., Weeraratne, D., Frisse, M. E., Misulis, K., Rhee, K., Zhao, J., & Snowdon, J. L. (2021). Precision Medicine, AI, and the Future of Personalized Health Care. Clinical and Translational Science, 14(1), 86–93. https://doi.org/10.1111/cts.12884
Kantae, V., Krekels, E. H. J., Esdonk, M. J. Van, Lindenburg, P., Harms, A. C., Knibbe, C. A. J., Van der Graaf, P. H., & Hankemeier, T. (2017). Integration of pharmacometabolomics with pharmacokinetics and pharmacodynamics: towards personalized drug therapy. Metabolomics, 13(1), 9. https://doi.org/10.1007/s11306-016-1143-1
Kawashima, M., Nagare, T., & Doi, M. (2017). Clinical efficacy and safety of benzoyl peroxide for acne vulgaris: Comparison between Japanese and Western patients. The Journal of Dermatology, 44(11), 1212–1218. https://doi.org/10.1111/1346-8138.13996
Keele, L., & Small, D. S. (2021). Comparing Covariate Prioritization via Matching to Machine Learning Methods for Causal Inference Using Five Empirical Applications. The American Statistician, 75(4), 355–363. https://doi.org/10.1080/00031305.2020.1867638
Linden, A., & Yarnold, P. R. (2016). Combining machine learning and propensity score weighting to estimate causal effects in multivalued treatments. Journal of Evaluation in Clinical Practice, 22(6), 875–885. https://doi.org/10.1111/jep.12610
Liu, R., Wei, L., & Zhang, P. (2021). A deep learning framework for drug repurposing via emulating clinical trials on real-world patient data. Nature Machine Intelligence, 3(1), 68–75. https://doi.org/10.1038/s42256-020-00276-w
Majnaric, L. T., Babic, F., O'Sullivan, S., & Holzinger, A. (2021). AI and Big Data in Healthcare: Towards a More Comprehensive Research Framework for Multimorbidity. Journal of Clinical Medicine, 10(4), 766. https://doi.org/10.3390/jcm10040766
Markus, A. F., Kors, J. A., & Rijnbeek, P. R. (2021). The role of explainability in creating trustworthy artificial intelligence for health care: A comprehensive survey of the terminology, design choices, and evaluation strategies. Journal of Biomedical Informatics, 113, 103655. https://doi.org/10.1016/j.jbi.2020.103655
Meid, A. D., Ruff, C., Wirbka, L., Stoll, F., Seidling, H. M., Groll, A., & Haefeli, W. E. (2020). Using the Causal Inference Framework to Support Individualized Drug Treatment Decisions Based on Observational Healthcare Data. Clinical Epidemiology, Volume 12, 1223–1234. https://doi.org/10.2147/CLEP.S274466
Miotto, R., Li, L., Kidd, B. A., & Dudley, J. T. (2016). Deep Patient: An Unsupervised Representation to Predict the Future of Patients from the Electronic Health Records. Scientific Reports, 6(1), 26094. https://doi.org/10.1038/srep26094
Prosperi, M., Guo, Y., Sperrin, M., Koopman, J. S., Min, J. S., He, X., Rich, S., Wang, M., Buchan, I. E., & Bian, J. (2020). Causal inference and counterfactual prediction in machine learning for actionable healthcare. Nature Machine Intelligence, 2(7), 369–375. https://doi.org/10.1038/s42256-020-0197-y
Prosperi, M., Min, J. S., Bian, J., & Modave, F. (2018). Big data hurdles in precision medicine and precision public health. BMC Medical Informatics and Decision Making, 18(1), 139. https://doi.org/10.1186/s12911-018-0719-2
Schmidt, K. T., Chau, C. H., Price, D. K., & Figg, W. D. (2016). Precision Oncology Medicine: The Clinical Relevance of Patient-Specific Biomarkers Used to Optimize Cancer Treatment. The Journal of Clinical Pharmacology, 56(12), 1484–1499. https://doi.org/10.1002/jcph.765
Schneeweiss, S. (2018). Automated data-adaptive analytics for electronic healthcare data to study causal treatment effects. Clinical Epidemiology, Volume 10, 771–788. https://doi.org/10.2147/CLEP.S166545
Strianese, O., Rizzo, F., Ciccarelli, M., Galasso, G., D'Agostino, Y., Salvati, A., Del Giudice, C., Tesorio, P., & Rusciano, M. R. (2020). Precision and Personalized Medicine: How Genomic Approach Improves the Management of Cardiovascular and Neurodegenerative Disease. Genes, 11(7), 747. https://doi.org/10.3390/genes11070747
Subramanian, M., Wojtusciszyn, A., Favre, L., Boughorbel, S., Shan, J., Letaief, K. B., Pitteloud, N., & Chouchane, L. (2020). Precision medicine in the era of artificial intelligence: implications in chronic disease management. Journal of Translational Medicine, 18(1), 472. https://doi.org/10.1186/s12967-020-02658-5
Sun, W., Cai, Z., Li, Y., Liu, F., Fang, S., & Wang, G. (2018). Data Processing and Text Mining Technologies on Electronic Medical Records: A Review. Journal of Healthcare Engineering, 2018, 1–9. https://doi.org/10.1155/2018/4302425
Sushil, M., Šuster, S., Luyckx, K., & Daelemans, W. (2018). Patient representation learning and interpretable evaluation using clinical notes. Journal of Biomedical Informatics, 84, 103–113. https://doi.org/10.1016/j.jbi.2018.06.016
Traversi, D., Pulliero, A., Izzotti, A., Franchitti, E., Iacoviello, L., Gianfagna, F., Gialluisi, A., Izzi, B., Agodi, A., Barchitta, M., Calabrò, G. E., Hoxhaj, I., Sassano, M., Sbrogiò, L. G., Del Sole, A., Marchiori, F., Pitini, E., Migliara, G., Marzuillo, C., … Boccia, S. (2021). Precision Medicine and Public Health: New Challenges for Effective and Sustainable Health. Journal of Personalized Medicine, 11(2), 135. https://doi.org/10.3390/jpm11020135
Verboven, S., & Martin, N. (2022). Combining the Clinical and Operational Perspectives in Heterogeneous Treatment Effect Inference in Healthcare Processes (pp. 327–339). https://doi.org/10.1007/978-3-030-98581-3_24
Vollmer, S., Mateen, B. A., Bohner, G., Király, F. J., Ghani, R., Jonsson, P., Cumbers, S., Jonas, A., McAllister, K. S. L., Myles, P., Grainger, D., Birse, M., Branson, R., Moons, K. G. M., Collins, G. S., Ioannidis, J. P. A., Holmes, C., & Hemingway, H. (2020). Machine learning and artificial intelligence research for patient benefit: 20 critical questions on transparency, replicability, ethics, and effectiveness. BMJ, l6927. https://doi.org/10.1136/bmj.l6927
Wager, S., & Athey, S. (2018). Estimation and Inference of Heterogeneous Treatment Effects using Random Forests. Journal of the American Statistical Association, 113(523), 1228–1242. https://doi.org/10.1080/01621459.2017.1319839
Weissler, E. H., Naumann, T., Andersson, T., Ranganath, R., Elemento, O., Luo, Y., Freitag, D. F., Benoit, J., Hughes, M. C., Khan, F., Slater, P., Shameer, K., Roe, M., Hutchison, E., Kollins, S. H., Broedl, U., Meng, Z., Wong, J. L., Curtis, L., … Ghassemi, M. (2021). The role of machine learning in clinical research: transforming the future of evidence generation. Trials, 22(1), 537. https://doi.org/10.1186/s13063-021-05489-x
Wendling, T., Jung, K., Callahan, A., Schuler, A., Shah, N. H., & Gallego, B. (2018). Comparing methods for estimation of heterogeneous treatment effects using observational data from health care databases. Statistics in Medicine, 37(23), 3309–3324. https://doi.org/10.1002/sim.7820
Wong, J., Murray Horwitz, M., Zhou, L., & Toh, S. (2018). Using Machine Learning to Identify Health Outcomes from Electronic Health Record Data. Current Epidemiology Reports, 5(4), 331–342. https://doi.org/10.1007/s40471-018-0165-9
Yurkovich, J. T., Tian, Q., Price, N. D., & Hood, L. (2020). A systems approach to clinical oncology uses deep phenotyping to deliver personalized care. Nature Reviews Clinical Oncology, 17(3), 183–194. https://doi.org/10.1038/s41571-019-0273-6
Last-Resort Antibiotic Resistance: Mechanisms, Environmental Spread, and Detection Tools — A Narrative Review
Artificial Intelligence in Precision Cardiovascular Medicine: Risk Prediction, Digital Twins, and Explainability
Integrative approaches of AI in personalised disease management: From diagnosis to drug delivery