Machine Learning-based Classifiers for the Prediction of Low Birth Weight.

OBJECTIVES: Low birth weight (LBW) is a global concern associated with fetal and neonatal mortality as well as adverse consequences such as intellectual disability, impaired cognitive development, and chronic diseases in adulthood. Numerous factors contribute to LBW and vary based on the region. The main objectives of this study were to compare four machine learning classifiers in the prediction of LBW and to determine the most important factors related to this phenomenon in Hamadan, Iran. METHODS: We carried out a retrospective cross-sectional study on a dataset collected from Fatemieh Hospital in 2017 that included 741 mother-newborn pairs and 13 potential factors. Decision tree, random forest, artificial neural network, support vector machine, and logistic regression (LR) methods were used to predict LBW, with five evaluation criteria utilized to compare performance. RESULTS: Our findings revealed a 7% prevalence of LBW. The average accuracy of all models was 87% or higher. The LR method provided a sensitivity, specificity, positive likelihood ratio, negative likelihood ratio, and accuracy of 74%, 89%, 7.04%, 29%, and 88%, respectively. Using LR, gestational age, number of abortions, gravida, consanguinity, maternal age at delivery, and neonatal sex were determined to be the six most important variables associated with LBW. CONCLUSIONS: Our findings underscore the importance of facilitating timely diagnosis of causes of abortion, providing genetic counseling to consanguineous couples, and strengthening care before and during pregnancy (particularly for young mothers) to reduce LBW.

Sensory interventions on motor function, activities of daily living, and spasticity of the upper limb in people with stroke: A randomized clinical trial.

STUDY DESIGN: This is a single-blinded clinical trial study. Clinical Trial Number registry: IRCT201610223551N4. INTRODUCTION: Stroke is the second cause of death around the world. Motor and sensory problems are common complications of the stroke. These defects in the upper limb cause reduced use of the affected limb and consequently a decrease in the quality of life. PURPOSE OF THE STUDY: The purpose of this study was to examine the effect of exteroceptive and proprioceptive stimulations on motor function, spasticity of the upper limb, and activities of daily living in people who have had stroke. METHODS: Sixty people with chronic stroke selected by convenience sampling. Before the intervention, Modified Ashworth Scale, Fugl-Meyer assessment of Motor Recovery after Stroke, and Barthel Index were measured and then the intervention phase was started. Exteroceptive and proprioceptive sensory stimulations were performed for 6 weeks. Independent t-test was used to compare groups. RESULTS: The intervention group made improvement in motor function (P = .0001, Cohen's d = 2.14), activities of daily living of upper limb (P = .0001, Cohen's d = 1.32), and spasticity (P = .002, Cohen's d = -0.94). DISCUSSION: Motor function and activities of daily living and spasticity of the upper limb can be improved through exteroceptive and proprioceptive stimulations. In this study, this type of intervention had the most impact on motor function compared with the rest. CONCLUSION: Exteroceptive and proprioceptive stimulations in upper limb can be used in chronic phase of stroke. Improvement in motor function and activities of daily living and reducing spasticity are the results of these stimulations.