Role of Predictive Modeling in Healthcare Research: A Scoping Review

Nihar Ranjan Panda; Jitendra Kumar Pati; Ruchi Bhuyan

doi:10.6000/1929-6029.2022.11.09

Authors

Nihar Ranjan Panda Department of Medical Research, IMS & SUM Hospital, SOA deemed to be University, Bhubaneswar, Odisha, India and Department of Mathematics, CV Raman Global University, Bhubaneswar, Odisha, India https://orcid.org/0000-0002-3438-1433
Jitendra Kumar Pati Department of Mathematics, CV Raman Global University, Bhubaneswar, Odisha, India
Ruchi Bhuyan Department of Medical Research, IMS & SUM Hospital, SOA deemed to be University, Bhubaneswar, Odisha, India https://orcid.org/0000-0002-4082-8393

DOI:

https://doi.org/10.6000/1929-6029.2022.11.09

Keywords:

Predictive model, Healthcare, Roc curve, Model validation

Abstract

The huge preponderance of inferences drawn in empirical medical research follows from model-based relations (e.g. regression). Here, we described the role of predictive modeling as a complement to this approach. Predictive models are usually probabilistic model which gives a good quality fit to our data. In medical research, it’s very common to use regression models for predictive purposes. Here in this article, we described the types of predictive modeling (Linear and Non-linear) used in medical research and how effectively the researchers take decisions based on predictive modeling, and what precautions, we have to take while building a predictive model. Finally, we consider a working example to illustrate the effectiveness of the predictive model in healthcare.

References

Toll DB, Janssen KJ, Vergouwe Y, et al. Validation, updating and impact of clinical prediction rules: a review. J Clin Epidemiol 2008; 61: 1085-1094. https://doi.org/10.1016/j.jclinepi.2008.04.008 DOI: https://doi.org/10.1016/j.jclinepi.2008.04.008

Waljee AK, Joyce JC, Wang SJ, et al. Algorithms outperform metabolite tests in predicting response of patients with inflammatory bowel disease to thiopurines. Clin Gastroenterol Hepatol 2010; 8: 143-150. https://doi.org/10.1016/j.cgh.2009.09.031 DOI: https://doi.org/10.1016/j.cgh.2009.09.031

Singal AG, Mukherjee A, Higgins PD, et al. Machine learning algorithms outperform conventional regression models in identifying risk factors for hepatocellular carcinoma in patients with cirrhosis. Am J Gastroenterol 2013; 108: 1723-1730. https://doi.org/10.1038/ajg.2013.332 DOI: https://doi.org/10.1038/ajg.2013.332

Singal AG, Yopp AC, Gupta S, et al. Failure rates in the hepatocellular carcinoma surveillance process. Cancer Prev Res (Phila) 2012; 5: 1124-1130. https://doi.org/10.1158/1940-6207.CAPR-12-0046 DOI: https://doi.org/10.1158/1940-6207.CAPR-12-0046

Singal AG, Rahimi RS, Clark C, et al. An automated model using electronic medical record data to identify patients with cirrhosis at high risk for readmission. Clinical Gastroenterol and Hepatol 2013; 11: 1335-1341. https://doi.org/10.1016/j.cgh.2013.03.022 DOI: https://doi.org/10.1016/j.cgh.2013.03.022

Moons KG, Royston P, Vergouwe Y, et al. Prognosis and prognostic research: what, why, and how? BMJ 2009; 338: b375. https://doi.org/10.1136/bmj.b375 DOI: https://doi.org/10.1136/bmj.b375

Hemingway H, Riley RD, Altman DG. Ten steps towards improving prognosis research. BMJ 2009; 339: b4184. https://doi.org/10.1136/bmj.b4184 DOI: https://doi.org/10.1136/bmj.b4184

Waljee AK, Higgins PD. Machine learning in medicine: a primer for physicians. Am J Gastroenterol 2010; 105: 1224-1226. https://doi.org/10.1038/ajg.2010.173 DOI: https://doi.org/10.1038/ajg.2010.173

Siegel CA, Siegel LS, Hyams JS, et al. Real-time tool to display the predicted disease course and treatment response for children with Crohn’s disease. Inflamm Bowel Dis 2011; 17: 30-38. https://doi.org/10.1002/ibd.21386 DOI: https://doi.org/10.1002/ibd.21386

Core Team. R: A language and environment for statistical computing. R Foundation for Statistical Computing, Vienna, Austria. 2013, ISBN 3-900051-07-0, http://www.R-project.org/

Breiman L. Random forests. Machine Learning 2001; 45: 5-32. https://doi.org/10.1023/A:1010933404324 DOI: https://doi.org/10.1023/A:1010933404324

Liaw A, Wiener M. Classification and regression by random Forest. R News 2002; 2: 18-22.

Royston P, Moons KG, Altman DG et al. Prognosis and prognostic research: developing a prognostic model. BMJ 2009; 338: b604. https://doi.org/10.1136/bmj.b604 DOI: https://doi.org/10.1136/bmj.b604

Greenland S. Modelling and variable selection in epidemiologic analysis. Am J Public Health 1989; 79: 340-349. https://doi.org/10.2105/AJPH.79.3.340 DOI: https://doi.org/10.2105/AJPH.79.3.340

Ibrahim JG, Chu H, Chen MH. Missing data in clinical studies: issues and methods. J Clin Oncol 2012; 30: 3297-3303. https://doi.org/10.1200/JCO.2011.38.7589 DOI: https://doi.org/10.1200/JCO.2011.38.7589

Kaambwa B, Bryan S, Billingham L. Do the methods used to analyse missing data really matter? An examination of data from an observational study of Intermediate Care patients. BMC Res Notes 2012; 5: 330. https://doi.org/10.1186/1756-0500-5-330 DOI: https://doi.org/10.1186/1756-0500-5-330

Waljee A, Mukherjee A, Singal A, et al. Comparison of modern imputation methods for missing laboratory data in medicine. BMJ Open 2013; 3: pii: e002847. https://doi.org/10.1136/bmjopen-2013-002847 DOI: https://doi.org/10.1136/bmjopen-2013-002847

Altman DG, Vergouwe Y, Royston P, et al. Prognosis and prognostic research: validating a prognostic model. BMJ 2009; 338: b605. https://doi.org/10.1136/bmj.b605 DOI: https://doi.org/10.1136/bmj.b605

Steyerberg EW, Harrell FE Jr, Borsboom GJ, et al. Internal validation of predictive models: efficiency of some procedures for logistic regression analysis. J Clin Epidemiol 2001; 54: 774-781. https://doi.org/10.1016/S0895-4356(01)00341-9 DOI: https://doi.org/10.1016/S0895-4356(01)00341-9

Steyerberg EW, Vickers AJ, Cook NR, et al. Assessing the performance of prediction models: a framework for traditional and novel measures. Epidemiology 2010; 21: 128-138. https://doi.org/10.1097/EDE.0b013e3181c30fb2 DOI: https://doi.org/10.1097/EDE.0b013e3181c30fb2