Globally, cardiovascular disease (CVD) remains the leading cause of death, warranting effective management and prevention measures. Risk prediction tools are indispensable for directing primary and secondary prevention strategies for CVD and are critical for estimating CVD risk. Machine learning (ML) methodologies have experienced significant advancements across numerous practical domains in recent years. Several ML and statistical models predicting CVD time-to-event outcomes have been developed. However, it is not known as to which of the two model types—ML and statistical models—have higher discrimination and calibration in this regard. Hence, this planned work aims to systematically review studies that compare ML with statistical methods in terms of their predictive abilities in the case of time-to-event data with censoring.
Original research articles published as prognostic prediction studies, which involved the development and/or validation of a prognostic model, within a peer-reviewed journal, using cohort or experimental design with at least a 12-month follow-up period will be systematically reviewed. The review process will adhere to the Critical Appraisal and Data Extraction for Systematic Reviews of Prediction Modelling Studies checklist.
Ethical approval is not required for this review, as it will exclusively use data from published studies. The findings of this study will be published in an open-access journal and disseminated at scientific conferences.
CRD42023484178.
by Aminu S. Abdullahi, Abubaker Suliman, Moien AB Khan, Howaida Khair, Saad Ghazal-Aswad, Iffat Elbarazi, Fatima Al-Maskari, Tom Loney, Rami H. Al-Rifai, Luai A. Ahmed
BackgroundLow hemoglobin (Hb) level is a leading cause of many adverse pregnancy outcomes. Patterns of changes in Hb levels during pregnancy are not well understood.
AimThis study estimated Hb levels, described its changing patterns across gestational trimesters, and identified factors associated with these changes among pregnant women.
Materials and methodsData from the ongoing maternal and child health cohort study–The Mutaba’ah Study, was used (N = 1,120). KML machine learning algorithm was applied to identify three distinct cluster trajectories of Hb levels between the first and the third trimesters. Descriptive statistics were used to profile the study participants. Multinomial multivariable logistic regression was employed to identify factors associated with change patterns in Hb levels.
ResultsThe three identified clusters–A, B and C–had, respectively, median Hb levels (g/L) of 123, 118, and 104 in the first trimester and 119, 100, and 108 in the third trimester. Cluster ’A’ maintained average normal Hb levels in both trimesters. Cluster ’B’, on average, experienced a decrease in Hb levels below the normal range during the third trimester. Cluster ’C’ showed increased Hb levels in the third trimester but remained, on average, below the normal range in both trimesters. Pregnant women with higher gravida, diabetes mellitus (type 1 or 2), nulliparity or lower level of education were more likely to be in cluster ’B’ than the normal cluster ’A’. Pregnant women who reported using iron supplements before pregnancy or those with low levels of education. were more likely to be in cluster ’C’ than the normal cluster ’A’.
ConclusionThe majority of pregnant women experienced low Hb levels during pregnancy. Changes in Hb levels during pregnancy were associated with parity, gravida, use of iron before pregnancy, and the presence of diabetes mellitus (type 1 or 2).