Skip to main content
SpringerLink
Log in

Predicting Medical Outcomes

  • Chapter
  • First Online:
Intelligent Systems in Medicine and Health

Part of the book series: Cognitive Informatics in Biomedicine and Healthcare ((CIBH))

  • 1121 Accesses

Abstract

Clinical outcomes are measurable changes in health, function or quality of life that result from patients’ care. The capability of predicting changes related to specific care actions, including administration of drugs, therapeutic protocols, guidelines and technology-related interventions, is of obvious great interest, in particular when such actions are implemented in the real-world, after clinical trials. AI and machine learning hold the promise to provide methods and tools able to add several important elements to traditional statistical modeling techniques, including the capability of analyzing and synthesizing very large data sets, the tools for handling non-linear relationships between variables, and the strategies for incorporating prior knowledge coming from experts into the analysis. This chapter introduces the problem of predicting different types of clinical outcomes, ranging from binary responses to temporal trajectories, and an overview of AI approaches able to deal with such types of prediction. The chapter will also discuss how to carefully assess the prediction performances and will finally provide some application examples in different clinical areas.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
eBook
USD 16.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 64.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info
Hardcover Book
USD 99.99
Price excludes VAT (USA)
  • Durable hardcover edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Notes

  1. 1.

    ImageNet is an image database that has been very important in advancing computer vision and deep learning research also by means of a number of large image recognition challenges.

  2. 2.

    https://www.fda.gov/medical-devices/software-medical-device-samd/artificial-intelligence-and-machine-learning-software-medical-device, with (accessed August 18, 2022).

  3. 3.

    Hematopoietic disorders are heterogeneous diseases that can be caused by problems with red blood cells, white blood cells, platelets, bone marrow, lymph nodes, and the spleen.

References

  1. Goodfellow IJ, Bengio Y, Courville A. Deep learning. Cambridge, MA: MIT Press; 2016.

    MATH  Google Scholar 

  2. Bzdok D, Altman N, Krzywinski M. Statistics versus machine learning. Nat Methods. 2018;15:233–4.

    Article  Google Scholar 

  3. Tejedor M, Woldaregay AZ, Godtliebsen F. Reinforcement learning application in diabetes blood glucose control: a systematic review. Artif Intell Med. 2020;104:101836.

    Article  Google Scholar 

  4. Rubin DB. Inference and missing data. Biometrika. 1976;63:581–92.

    Article  MathSciNet  MATH  Google Scholar 

  5. Pedersen AB, et al. Missing data and multiple imputation in clinical epidemiological research. Clin Epidemiol. 2017;9:157–66.

    Article  Google Scholar 

  6. van Buuren S, Groothuis-Oudshoorn K. Mice: multivariate imputation by chained equations in R. J Stat Softw. 2011;45:1–67.

    Article  Google Scholar 

  7. Chandrashekar G, Sahin F. A survey on feature selection methods. Comput Electr Eng. 2014;40:16–28.

    Article  Google Scholar 

  8. Pearson KLIII. On lines and planes of closest fit to systems of points in space. Lond Edinb Dublin Philos Mag J Sci. 1901;2:559–72.

    Article  MATH  Google Scholar 

  9. Hotelling H. Analysis of a complex of statistical variables into principal components. J Educ Psychol. 1933;24:417–41.

    Article  MATH  Google Scholar 

  10. Jolliffe IT, Cadima J. Principal component analysis: a review and recent developments. Philos Trans R Soc A Math Phys Eng Sci. 2016;374:20150202.

    Article  MathSciNet  MATH  Google Scholar 

  11. van der Maaten L, Hinton G. Visualizing data using t-SNE. J Mach Learn Res. 2008;9:2579–605.

    MATH  Google Scholar 

  12. Wang F, Casalino LP, Khullar D. Deep learning in medicine-promise, progress, and challenges. JAMA Intern Med. 2019;179:293–4.

    Article  Google Scholar 

  13. Xu X, Liang T, Zhu J, Zheng D, Sun T. Review of classical dimensionality reduction and sample selection methods for large-scale data processing. Neurocomputing. 2019;328:5–15.

    Article  Google Scholar 

  14. Yu Y, Si X, Hu C, Zhang J. A review of recurrent neural networks: LSTM cells and network architectures. Neural Comput. 2019;31:1235–70.

    Article  MathSciNet  MATH  Google Scholar 

  15. Yang X, Bian J, Hogan WR, Wu Y. Clinical concept extraction using transformers. J Am Med Inform Assoc. 2020;27:1935–42.

    Article  Google Scholar 

  16. Vaswani A, et al. Attention is all you need. arXiv. 2017:1706.03762 [cs].

    Google Scholar 

  17. Russakovsky O, et al. ImageNet large scale visual recognition challenge. arXiv. 2015:1409.0575 [cs].

    Google Scholar 

  18. Devlin J, Chang M-W, Lee K, Toutanova K. BERT: pre-training of deep bidirectional transformers for language understanding. arXiv. 2019:1810.04805 [cs].

    Google Scholar 

  19. Goto T, Camargo CA, Faridi MK, Freishtat RJ, Hasegawa K. Machine learning-based prediction of clinical outcomes for children during Emergency Department Triage. JAMA Netw Open. 2019;2:e186937.

    Article  Google Scholar 

  20. Skrede O-J, et al. Deep learning for prediction of colorectal cancer outcome: a discovery and validation study. Lancet. 2020;395:350–60.

    Article  Google Scholar 

  21. Yala A, Lehman C, Schuster T, Portnoi T, Barzilay R. A deep learning mammography-based model for improved breast cancer risk prediction. Radiology. 2019;292:60–6.

    Article  Google Scholar 

  22. Ling CX, Sheng VS. Cost-sensitive learning. In: Sammut C, Webb GI, editors. Encyclopedia of machine learning. New York: Springer; 2010. p. 231–5. https://doi.org/10.1007/978-0-387-30164-8_181.

    Chapter  Google Scholar 

  23. Bayati M, et al. Data-driven decisions for reducing readmissions for heart failure: general methodology and case study. PLoS One. 2014;9:e109264.

    Article  Google Scholar 

  24. Salvi E, Parimbelli E, Quaglini S, Sacchi L. Eliciting and exploiting utility coefficients in an integrated environment for shared decision-making. Methods Inf Med. 2019;58:24–30.

    Article  Google Scholar 

  25. Hastie T, Tibshirani R. Generalized additive models. Stat Sci. 1986;1:297–310.

    MathSciNet  MATH  Google Scholar 

  26. Schneider A, Hommel G, Blettner M. Linear Regression Analysis. Dtsch Arztebl Int. 2010;107:776–82.

    Google Scholar 

  27. Kleinbaum DG, Klein M. Survival analysis: a self-learning text. 3rd ed. New York: Springer-Verlag; 2012. https://doi.org/10.1007/978-1-4419-6646-9.

    Book  MATH  Google Scholar 

  28. Giolo SR, Krieger JE, Mansur AJ, Pereira AC. Survival analysis of patients with heart failure: implications of time-varying regression effects in modeling mortality. PLoS One. 2012;7:e37392.

    Article  Google Scholar 

  29. Goldhirsch A, Gelber RD, Simes RJ, Glasziou P, Coates AS. Costs and benefits of adjuvant therapy in breast cancer: a quality-adjusted survival analysis. J Clin Oncol. 1989;7:36–44.

    Article  Google Scholar 

  30. Lee ET, Go OT. Survival Analysis in Public Health Research. Annu Rev Public Health. 1997;18:105–34.

    Article  Google Scholar 

  31. Wang P, Li Y, Reddy CK. Machine learning for survival analysis: a survey. ACM Comput Surv. 2019;51:110.

    Article  Google Scholar 

  32. Huang Z, et al. SALMON: Survival Analysis Learning With Multi-Omics Neural Networks on Breast Cancer. Front Genet. 2019;10:166.

    Article  Google Scholar 

  33. Ching T, Zhu X, Garmire LX. Cox-nnet: An artificial neural network method for prognosis prediction of high-throughput omics data. PLoS Comput Biol. 2018;14:e1006076.

    Article  Google Scholar 

  34. Lee, C., Zame, W., Yoon, J. & van der Schaar, M. DeepHit: A deep learning approach to survival analysis with competing risks. AAAI 32, (2018).

    Google Scholar 

  35. Lee C, Yoon J, van der Schaar M. Dynamic-DeepHit: a deep learning approach for dynamic survival analysis with competing risks based on longitudinal data. IEEE Trans Biomed Eng. 2020;67:122–33.

    Article  Google Scholar 

  36. Harrell FE, Califf RM, Pryor DB, Lee KL, Rosati RA. Evaluating the yield of medical tests. JAMA. 1982;247:2543–6.

    Article  Google Scholar 

  37. Brier GW. Verification of forecasts expressed in terms of probability. Mon Wea Rev. 1950;78:1–3.

    Article  Google Scholar 

  38. Muthén B, Muthén LK. Integrating person-centered and variable-centered analyses: growth mixture modeling with latent trajectory classes. Alcohol Clin Exp Res. 2000;24:882–91.

    Article  Google Scholar 

  39. van der Schoot R, Sijbrandij M, Winter SD, Depaoli S, Vermunt JK. The GRoLTS-Checklist: guidelines for reporting on latent trajectory studies. Struct Equ Model Multidiscip J. 2017;24:451–67.

    Article  MathSciNet  Google Scholar 

  40. Lennon H, et al. Framework to construct and interpret latent class trajectory modelling. BMJ Open. 2018;8:e020683.

    Article  Google Scholar 

  41. Dagliati A, et al. Latent class trajectory modeling of 2-component disease activity score in 28 joints identifies multiple rheumatoid arthritis phenotypes of response to biologic disease-modifying antirheumatic drugs. Arthritis Rheumatol. 2020;72:1632–42.

    Article  Google Scholar 

  42. Komorowski M, Raffa J. Markov models and cost effectiveness analysis: applications in medical research. In: Secondary Analysis of Electronic Health Records (ed. MIT Critical Data). New York: Springer International Publishing; 2016. p. 351–67. https://doi.org/10.1007/978-3-319-43742-2_24.

    Chapter  Google Scholar 

  43. Mor B, Garhwal S, Kumar A. A systematic review of hidden markov models and their applications. Arch Computat Methods Eng. 2021;28:1429–48.

    Article  MathSciNet  Google Scholar 

  44. Liu M, et al. A comparison between discrete and continuous time Bayesian networks in learning from clinical time series data with irregularity. Artif Intell Med. 2019;95:104–17.

    Article  Google Scholar 

  45. Ferrazzi F, Sebastiani P, Ramoni MF, Bellazzi R. Bayesian approaches to reverse engineer cellular systems: a simulation study on nonlinear Gaussian networks. BMC Bioinformatics. 2007;8:S2.

    Article  Google Scholar 

  46. Chen R, Zheng Y, Nixon E, Herskovits EH. Dynamic network model with continuous valued nodes for longitudinal brain morphometry. NeuroImage. 2017;155:605–11.

    Article  Google Scholar 

  47. Bates S, Hastie T, Tibshirani R. Cross-validation: what does it estimate and how well does it do it? arXiv. 2021:2104.00673 [math, stat].

    Google Scholar 

  48. Cabitza F, Campagner A. The need to separate the wheat from the chaff in medical informatics: Introducing a comprehensive checklist for the (self)-assessment of medical AI studies. Int J Med Inform. 2021;153:104510. https://doi.org/10.1016/j.ijmedinf.2021.104510.

    Article  Google Scholar 

  49. Chawla NV, Bowyer KW, Hall LO, Kegelmeyer WP. SMOTE: Synthetic minority over-sampling technique. J Artif Intell Res. 2002;16:321–57.

    Article  MATH  Google Scholar 

  50. Ho SY, Phua K, Wong L, Bin Goh WW. Extensions of the external validation for checking learned model interpretability and generalizability. Patterns. 2020;1:100129.

    Article  Google Scholar 

  51. Toll DB, Janssen KJM, Vergouwe Y, Moons KGM. Validation, updating and impact of clinical prediction rules: a review. J Clin Epidemiol. 2008;61:1085–94.

    Article  Google Scholar 

  52. Mesquita DPP, Rocha LS, Gomes JPP, Rocha Neto AR. Classification with reject option for software defect prediction. Appl Soft Comput. 2016;49:1085–93.

    Article  Google Scholar 

  53. Saria S, Subbaswamy A. Tutorial: safe and reliable machine learning. 2019. Preprint at https://arxiv.org/abs/1904.07204.

  54. Moons KGM, et al. Risk prediction models: II. External validation, model updating, and impact assessment. Heart. 2012;98:691–8.

    Article  Google Scholar 

  55. Caruana R, Lundberg S, Ribeiro MT, Nori H, Jenkins S. Intelligible and Explainable Machine Learning: Best Practices and Practical Challenges. In: Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining 3511–3512. New York: Association for Computing Machinery; 2020. https://doi.org/10.1145/3394486.3406707.

    Chapter  Google Scholar 

  56. Dagliati A, et al. Machine learning methods to predict diabetes complications. J Diabetes Sci Technol. 2018;12:295–302.

    Article  Google Scholar 

  57. Dagliati A, Geifman N, et al. Using topological data analysis and pseudo time series to infer temporal phenotypes from electronic health records. Artif Intell Med. 2020;108:101930. https://doi.org/10.1016/j.artmed.2020.101930.

    Article  Google Scholar 

  58. Nicora G, et al. A continuous-time Markov model approach for modeling myelodysplastic syndromes progression from cross-sectional data. J Biomed Inform. 2020;104:103398.

    Article  Google Scholar 

  59. Greenberg PL, et al. Revised international prognostic scoring system for myelodysplastic syndromes. Blood. 2012;120:2454–65.

    Article  Google Scholar 

  60. Brat GA, et al. International electronic health record-derived COVID-19 clinical course profiles: the 4CE consortium. NPJ Digital Medicine. 2020;3:109.

    Article  Google Scholar 

  61. Weber GM, et al. International Comparisons of Harmonized Laboratory Value Trajectories to Predict Severe COVID-19: Leveraging the 4CE Collaborative Across 342 Hospitals and 6 Countries: A Retrospective Cohort Study. medRxiv. 2021:2020.12.16.20247684. https://doi.org/10.1101/2020.12.16.20247684.

  62. Klann JG, et al. Validation of an internationally derived patient severity phenotype to support COVID-19 analytics from electronic health record data. J Am Med Inform Assoc. 2021;28(7):1411–20. https://doi.org/10.1093/jamia/ocab018.

    Article  Google Scholar 

  63. World Health Organization. International statistical classification of diseases and related health problems. World Health Organization; 2015.

    Google Scholar 

  64. WHO Expert Committee on the Selection and Use of Essential Medicines, World Health Organization. The selection and use of essential medicines. In: Report of the WHO expert committee, 2005 (including the 14th model list of essential medicines), 2006.

    Google Scholar 

  65. Huff SM, et al. Development of the Logical Observation Identifier Names and Codes (LOINC) Vocabulary. J Am Med Inform Assoc. 1998;5:276–92.

    Article  Google Scholar 

  66. Liu S, Ma W, Moore R, Ganesan V, Nelson S. RxNorm: prescription for electronic drug information exchange. IT Professional. 2005;7:17–23.

    Article  Google Scholar 

  67. Estiri H, Strasser ZH, Klann JG, McCoy TH Jr., Wagholikar KB, Vasey S, Castro VM, Murphy ME, Murphy SN. Transitive sequencing medical records for mining predictive and interpretable temporal representations. Patterns 2020.

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Electrical, Computer and Biomedical Engineering, University of Pavia, Pavia, Italy

    Riccardo Bellazzi, Arianna Dagliati & Giovanna Nicora

  2. Laboratory of Informatics and Systems Engineering for Clinical Research, Istituti Clinici Scientifici Maugeri, Pavia, Italy

    Riccardo Bellazzi

Authors
  1. Riccardo Bellazzi
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Arianna Dagliati
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Giovanna Nicora
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Riccardo Bellazzi .

Editor information

Editors and Affiliations

  1. University of Washington, Seattle, WA, USA

    Trevor A. Cohen

  2. New York Academy of Medicine, New York, NY, USA

    Vimla L. Patel

  3. Columbia University, New York, NY, USA

    Edward H. Shortliffe

Rights and permissions

Reprints and permissions

Copyright information

© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this chapter

Check for updates. Verify currency and authenticity via CrossMark

Cite this chapter

Bellazzi, R., Dagliati, A., Nicora, G. (2022). Predicting Medical Outcomes. In: Cohen, T.A., Patel, V.L., Shortliffe, E.H. (eds) Intelligent Systems in Medicine and Health. Cognitive Informatics in Biomedicine and Healthcare. Springer, Cham. https://doi.org/10.1007/978-3-031-09108-7_11

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-09108-7_11

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-09107-0

  • Online ISBN: 978-3-031-09108-7

  • eBook Packages: MedicineMedicine (R0)

Publish with us

Policies and ethics

Search

Navigation