Gradient boosted trees with individual explanations: An alternative to logistic regression for viability prediction in the first trimester of pregnancy

Magnus, 2019, Role of maternal age and pregnancy history in risk of miscarriage: prospective register based study, BMJ, 364 Rossen, 2018, Trends in risk of pregnancy loss among US Women, 1990–2011, Paediatr. Perinat. Epidemiol., 32, 19, 10.1111/ppe.12417 Foo, 2020, Peri-implantation urinary hormone monitoring distinguishes between types of first-trimester spontaneous pregnancy loss, Paediatr. Perinat. Epidemiol., 34, 495, 10.1111/ppe.12613 Geller, 2004, Anxiety following miscarriage and the subsequent pregnancy: a review of the literature and future directions, J. Psychosom. Res., 56, 35, 10.1016/S0022-3999(03)00042-4 Farren, 2020, Posttraumatic stress, anxiety and depression following miscarriage and ectopic pregnancy: a multicenter, prospective, cohort study, Am. J. Obstet. Gynecol., 222, 367e1, 10.1016/j.ajog.2019.10.102 Farren, 2018, The psychological impact of early pregnancy loss, Hum. Reprod. Update, 24, 731, 10.1093/humupd/dmy025 Richardson, 2017, Anxiety associated with diagnostic uncertainty in early pregnancy, Ultrasound Obstet. Gynecol., 50, 247, 10.1002/uog.17214 Detti, 2020, Early pregnancy ultrasound measurements and prediction of first trimester pregnancy loss: a logistic model, Sci. Rep., 10, 1545, 10.1038/s41598-020-58114-3 Choong, 2003, Ultrasound prediction of risk of spontaneous miscarriage in live embryos from assisted conceptions, Ultrasound Obstet. Gynecol., 22, 571, 10.1002/uog.909 Elson, 2003, Prediction of early pregnancy viability in the absence of an ultrasonically detectable embryo, Ultrasound Obstet. Gynecol., 21, 57, 10.1002/uog.1 Lautmann, 2011, Clinical use of a model to predict the viability of early intrauterine pregnancies when no embryo is visible on ultrasound, Hum. Reprod., 26, 2957, 10.1093/humrep/der287 Guha, 2013, External validation of models and simple scoring systems to predict miscarriage in intrauterine pregnancies of uncertain viability, Hum. Reprod., 28, 2905, 10.1093/humrep/det342 Bignardi, 2010, Viability of intrauterine pregnancy in women with pregnancy of unknown location: prediction using human chorionic gonadotropin ratio vs. progesterone, Ultrasound Obstet. Gynecol., 35, 656, 10.1002/uog.7669 Esteva, 2017, Dermatologist-level classification of skin cancer with deep neural networks, Nature, 542, 115, 10.1038/nature21056 Senior, 2020, Improved protein structure prediction using potentials from deep learning, Nature, 577, 706, 10.1038/s41586-019-1923-7 Brown, 2020, Language models are few-shot learners, 1877 Chen, 2016, XGBoost: a Scalable Tree Boosting System, 785 Liu, 2020, Machine learning algorithms to predict early pregnancy loss after in vitro fertilization-embryo transfer with fetal heart rate as a strong predictor, Comput. Methods Programs Biomed., 196, 10.1016/j.cmpb.2020.105624 Moreira, 2019, Averaged one-dependence estimators on edge devices for smart pregnancy data analysis, Comput. Electr. Eng., 77, 435, 10.1016/j.compeleceng.2018.07.041 Bruno, 2020, Machine learning (ML) based-method applied in recurrent pregnancy loss (RPL) patients diagnostic work-up: a potential innovation in common clinical practice, Sci. Rep., 10, 7970, 10.1038/s41598-020-64512-4 Kuhle, 2018, Comparison of logistic regression with machine learning methods for the prediction of fetal growth abnormalities: a retrospective cohort study, BMC Pregnancy Childbirth, 18, 333, 10.1186/s12884-018-1971-2 Poon, 2018, The first-trimester of pregnancy-a window of opportunity for prediction and prevention of pregnancy complications and future life, Diabetes Res. Clin. Pract., 145, 20, 10.1016/j.diabres.2018.05.002 He, 2019, The practical implementation of artificial intelligence technologies in medicine, Nat. Med., 25, 30, 10.1038/s41591-018-0307-0 2018, Towards trustable machine learning, Nat. Biomed. Eng., 2, 709, 10.1038/s41551-018-0315-x Lundberg, 2017, A unified approach to interpreting model predictions, Adv. Neural Inf. Process. Syst., 30 Al-Memar, 2019, Early-pregnancy events and subsequent antenatal, delivery and neonatal outcomes: prospective cohort study, Ultrasound Obstet. Gynecol., 54, 530, 10.1002/uog.20262 Bottomley, 2013, Accurate prediction of pregnancy viability by means of a simple scoring system, Hum. Reprod., 28, 68, 10.1093/humrep/des352 Azur, 2011, Multiple imputation by chained equations: what is it and how does it work?, Int. J. Methods Psychiatr. Res., 20, 40, 10.1002/mpr.329 Friedman, 2001, Greedy function approximation: a gradient boosting machine, Ann. Stat., 29, 1189, 10.1214/aos/1013203451 Lundberg, 2020, From local explanations to global understanding with explainable AI for trees, Nat. Mach. Intell., 2, 56, 10.1038/s42256-019-0138-9 Lundberg, 2017, 15 Ke, 2017, A Highly Efficient Gradient Boosting Decision Tree, Advances in Neural Information Processing Systems, 30, 3146 J.S. Bergstra, R. Bardenet, Y. Bengio, B. Kégl, Algorithms for hyper-parameter optimization, in: Proceedings of the 24th International Conference on Neural Information Processing Systems, 2011, pp. 2546–2554. Steyerberg, 2019 DeLong, 1988, Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach, Biometrics, 44, 837, 10.2307/2531595 Miller, 2019, Explanation in artificial intelligence: insights from the social sciences, Artif. Intell., 267, 1, 10.1016/j.artint.2018.07.007 Janzing, 2020, Feature relevance quantification in explainable AI: a causal problem, Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics, PMLR, 2907 Sundararajan, 2020, The many shapley values for model explanation, 9269 Christodoulou, 2019, A systematic review shows no performance benefit of machine learning over logistic regression for clinical prediction models, J. Clin. Epidemiol., 110, 12, 10.1016/j.jclinepi.2019.02.004 Lynam, 2020, Logistic regression has similar performance to optimised machine learning algorithms in a clinical setting: application to the discrimination between type 1 and type 2 diabetes in young adults, Diagn. Progn. Res., 4, 6, 10.1186/s41512-020-00075-2 Breiman, 2001, Statistical modeling: the two cultures (with comments and a rejoinder by the author), Stat. Sci., 16, 199, 10.1214/ss/1009213726 Dormann, 2013, Collinearity: a review of methods to deal with it and a simulation study evaluating their performance, Ecography, 36, 27, 10.1111/j.1600-0587.2012.07348.x Harrell, 2015 Wegienka, 2002, A comparison of recalled date of last menstrual period with prospectively recorded dates, J. Womens Health, 14, 248, 10.1089/jwh.2005.14.248