Machine learning approach for predicting cardiovascular disease in Bangladesh: evidence from a cross-sectional study in 2023

BACKGROUND

Cardiovascular disorders (CVDs) are the leading cause of death worldwide. Lower- and middle-income countries (LMICs), such as Bangladesh, are also affected by several types of CVDs, such as heart failure and stroke. The leading cause of death in Bangladesh has recently switched from severe infections and parasitic illnesses to CVDs.

MATERIALS AND METHODS

The study dataset comprised a random sample of 391 CVD patients' medical records collected between August 2022 and April 2023 using simple random sampling. Moreover, 260 data points were collected from individuals with no CVD problems for comparison purposes. Crosstabs and chi-square tests were used to determine the association between CVD and the explanatory variables. Logistic regression, Naïve Bayes classifier, Decision Tree, AdaBoost classifier, Random Forest, Bagging Tree, and Ensemble learning classifiers were used to predict CVD. The performance evaluations encompassed accuracy, sensitivity, specificity, and area under the receiver operator characteristic (AU-ROC) curve.

RESULTS

Random Forest had the highest precision among the five techniques considered. The precision rates for the mentioned classifiers are as follows: Logistic Regression (93.67%), Naïve Bayes (94.87%), Decision Tree (96.1%), AdaBoost (94.94%), Random Forest (96.15%), and Bagging Tree (94.87%). The Random Forest classifier maintains the highest balance between correct and incorrect predictions. With 98.04% accuracy, the Random Forest classifier achieved the best precision (96.15%), robust recall (100%), and high F1 score (97.7%). In contrast, the Logistic Regression model achieved the lowest accuracy of 95.42%. Remarkably, the Random Forest classifier achieved the highest AUC value (0.989).

CONCLUSION

This research mainly focused on identifying factors that are critical in impacting patients with CVD and predicting CVD risk. It is strongly advised that the Random Forest technique be implemented in a system for predicting cardiac diseases. This research may change clinical practice by providing doctors with a new instrument to determine a patient's CVD prognosis.

Evaluation of the Changes of Blood Pressure and Serum Calcium Level In Postmenopausal Women

Menopause is the permanent cessation of menstruation at the end of the reproductive life due to loss of ovarian follicular activity. The prevalence of hypertension in women increases after menopause, suggesting that an absence of female gonadal steroids may represent a major risk factor for postmenopausal hypertension. Menopause is the phase from where bone mineralization becomes critics because of various physiological and hormonal changes. Estrogen deficiency and age related processes alter the rate of calcium turnover in bone that the ageing women face. Both systolic and diastolic blood pressure is significantly higher and serum calcium level is significantly lower among post menopausal women as compared with reproductive aged women. The objective of the study was to assess the blood pressure and serum calcium level changes in healthy postmenopausal women in order to compare this parameter with healthy reproductive aged women. This comparative study was carried out in the Department of Physiology, Mymensingh Medical College, Mymensingh, Bangladesh from July 2018 to June 2019. Two hundred healthy women (100 female were postmenopausal as study group and 100 female were reproductive aged women as control group) aged between 25 to 65 years were enrolled in this study. Blood pressure was measured by indirect auscultatory method with an aneroid sphygmomanometer and serum calcium level of the individual was measured by enzymatic colorimetric method with o-cresoftaline-complexon. Data were expressed as mean±SD and statistical significance of difference among the group was calculated by unpaired students' 't' test. The mean value ±SD of blood pressure was higher and serum calcium level was lower in postmenopausal group in comparison to the reproductive women group. This study concludes, blood pressure increases and serum calcium level decreases in postmenopausal women.

A comparative study of MR imaging profile of titanium pedicle screws

Objective: We compared the MR imaging profile of three different types of titanium pedicle screw implants in common usage in a human cadaveric model. We additionally compared the change in temperature during imaging among three constructs.

Material and Methods: Titanium-based lumbar pedicle screw/rod constructs from three manufacturers were implanted sequentially in a human cadaveric spine. MR imaging was then performed using both conventional spin-echo sequences and advanced imaging pulse sequences. Changes in tissue temperature were also measured during imaging to assess differences among the various implants. MR images were compared in a blinded fashion by two neuroradiologists.

Results: No significant differences in imaging profile were noted between the three types of titanium implants with regards to their MR artifact profile. Fast spin-echo sequences led to a decrease in perceptible MR artifacts. Moreover, there were no significant differences in temperature increase among the three manufacturers (mean increase 0.5°C) during imaging.

Conclusion: Slight differences in the percentage of titanium among the three pedicle screw systems does not appear to result in artifact differences during MR imaging. Therefore, with regard to imaging profile considerations, the three systems studied should be considered interchangeable.

Iron Polymaltose Complex in the Treatment of Iron Deficiency Anemia in Pregnancy

Iron deficiency anaemia is a major public health problem in pregnancy. About 58% of pregnant women in developed countries are anaemic mainly due to iron deficiency resulting a serious negative consequences on children, mothers and eventually on the nation. This quasi-experimental multi centered study (Before after study) was done to evaluate the efficacy and tolerability of Iron Polymaltose Complex (IPC) in the treatment of iron deficiency anaemia and it was performed at the OPD of Bangladesh Medical College and two other clinics of Dhaka city from August 2011 to September 2013. A total of 80 (eighty) subjects were selected by purposive sampling as per inclusion and exclusion criteria. They were treated by Iron Polymaltose-IPC [47mg elemental iron + Folic Acid 0.5mg + Zinc 22.5mg - Once daily orally for 12 weeks]. At the beginning and after 12 weeks of intervention by Iron Polymaltose Complex (IPC) Hb%, Packed Cell Volume (PCV), Mean Corpuscular Volume (MCV), Mean Corpuscular Hemoglobin (MCH), Serum iron, and Serum ferritin were measured. Data were analyzed by SPSS version 13.0. Paired and unpaired 't' test was used to analyze differences within groups and between groups. Chi-square test was done to analyze primary efficacy parameters and adverse drug reactions (ADR). Most of the respondents were within the age group of 18-23 and 30-35 years (32.6% each). Significant differences were found by treatment with IPC for 12 weeks in Hb%, PCV, MCV, MCH, Serum iron, and Serum ferritin level. In iron deficiency anaemia during pregnancy IPC may be used as a safe and cost-effective therapeutic management.