Association between breastfeeding duration and diabetes mellitus in menopausal women: a machine-learning analysis using population-based retrospective study.

BACKGROUND: Breastfeeding resets insulin resistance caused by pregnancy however, studies on the association between breastfeeding and diabetes mellitus (DM) have reported inconsistent results. Therefore, we aimed to investigate the risk of DM according to breastfeeding duration in large-scale population-based retrospective study. In addition, machine-learning prediction models for DM and hemoglobin A1c (HbA1c) were developed to further evaluate this association. METHODS: We used the Korean National Health and Nutrition Examination Surveys database, a nationwide and population-based health survey from 2010 to 2020. We included 15,946 postmenopausal women with a history of delivery, whom we divided into three groups according to the average breastfeeding duration: (1) no breastfeeding, (2) < 12 months breastfeeding, and (3) ≥ 12 months breastfeeding. Prediction models for DM and HbA1c were developed using an artificial neural network, decision tree, logistic regression, Naïve Bayes, random forest, and support vector machine. RESULTS: In total, 2248 (14.1%) women had DM and 14,402 (90.3%) had a history of breastfeeding. The prevalence of DM was the lowest in the < 12 breastfeeding group (no breastfeeding vs. < 12 months breastfeeding vs. ≥ 12 months breastfeeding; 161 [10.4%] vs. 362 [9.0%] vs. 1,725 [16.7%], p < 0.001). HbA1c levels were also the lowest in the < 12 breastfeeding group (HbA1c: no breastfeeding vs. < 12 months breastfeeding vs. ≥ 12 months breastfeeding; 5.9% vs. 5.9% vs. 6.1%, respectively, p < 0.001). After adjustment for covariates, the risk of DM was significantly increased in both, the no breastfeeding (adjusted odds ratio [aOR] 1.29; 95% CI 1.29, 1.62]) and ≥ 12 months of breastfeeding groups (aOR 1.18; 95% CI 1.01, 1.37) compared to that in the < 12 months breastfeeding group. The accuracy and the area under the receiver-operating-characteristic curve of the DM prediction model were 0.93 and 0.95, respectively. The average breastfeeding duration was ranked among the top 15 determinants of DM, which supported the strong association between breastfeeding duration and DM. This association was also observed in a prediction model for HbA1c. CONCLUSIONS: Women who did not breasted had a higher risk of developing DM than those who breastfed for up to 12 months.

Artificial intelligence in colonoscopy: from detection to diagnosis.

This study reviews the recent progress of artificial intelligence for colonoscopy from detection to diagnosis. The source of data was 27 original studies in PubMed. The search terms were "colonoscopy" (title) and "deep learning" (abstract). The eligibility criteria were: (1) the dependent variable of gastrointestinal disease; (2) the interventions of deep learning for classification, detection and/or segmentation for colonoscopy; (3) the outcomes of accuracy, sensitivity, specificity, area under the curve (AUC), precision, F1, intersection of union (IOU), Dice and/or inference frames per second (FPS); (3) the publication year of 2021 or later; (4) the publication language of English. Based on the results of this study, different deep learning methods would be appropriate for different tasks for colonoscopy, e.g., Efficientnet with neural architecture search (AUC 99.8%) in the case of classification, You Only Look Once with the instance tracking head (F1 96.3%) in the case of detection, and Unet with dense-dilation-residual blocks (Dice 97.3%) in the case of segmentation. Their performance measures reported varied within 74.0-95.0% for accuracy, 60.0-93.0% for sensitivity, 60.0-100.0% for specificity, 71.0-99.8% for the AUC, 70.1-93.3% for precision, 81.0-96.3% for F1, 57.2-89.5% for the IOU, 75.1-97.3% for Dice and 66-182 for FPS. In conclusion, artificial intelligence provides an effective, non-invasive decision support system for colonoscopy from detection to diagnosis.

Prediction of longitudinal clinical outcomes after acute myocardial infarction using a dynamic machine learning algorithm.

Several regression-based models for predicting outcomes after acute myocardial infarction (AMI) have been developed. However, prediction models that encompass diverse patient-related factors over time are limited. This study aimed to develop a machine learning-based model to predict longitudinal outcomes after AMI. This study was based on a nationwide prospective registry of AMI in Korea (n = 13,104). Seventy-seven predictor candidates from prehospitalization to 1 year of follow-up were included, and six machine learning approaches were analyzed. Primary outcome was defined as 1-year all-cause death. Secondary outcomes included all-cause deaths, cardiovascular deaths, and major adverse cardiovascular event (MACE) at the 1-year and 3-year follow-ups. Random forest resulted best performance in predicting the primary outcome, exhibiting a 99.6% accuracy along with an area under the receiver-operating characteristic curve of 0.874. Top 10 predictors for the primary outcome included peak troponin-I (variable importance value = 0.048), in-hospital duration (0.047), total cholesterol (0.047), maintenance of antiplatelet at 1 year (0.045), coronary lesion classification (0.043), N-terminal pro-brain natriuretic peptide levels (0.039), body mass index (BMI) (0.037), door-to-balloon time (0.035), vascular approach (0.033), and use of glycoprotein IIb/IIIa inhibitor (0.032). Notably, BMI was identified as one of the most important predictors of major outcomes after AMI. BMI revealed distinct effects on each outcome, highlighting a U-shaped influence on 1-year and 3-year MACE and 3-year all-cause death. Diverse time-dependent variables from prehospitalization to the postdischarge period influenced the major outcomes after AMI. Understanding the complexity and dynamic associations of risk factors may facilitate clinical interventions in patients with AMI.

Deep Learning-Based Prediction Model for Gait Recovery after a Spinal Cord Injury.

Predicting gait recovery after a spinal cord injury (SCI) during an acute rehabilitation phase is important for planning rehabilitation strategies. However, few studies have been conducted on this topic to date. In this study, we developed a deep learning-based prediction model for gait recovery after SCI upon discharge from an acute rehabilitation facility. Data were collected from 405 patients with acute SCI admitted to the acute rehabilitation facility of Korea University Anam Hospital between June 2008 and December 2022. The dependent variable was Functional Ambulation Category at the time of discharge (FAC-DC). Seventy-one independent variables were selected from the existing literature: basic information, International Standards for Neurological Classification of SCI scores, neurogenic bladders, initial FAC, and somatosensory-evoked potentials of the lower extremity. Recurrent neural network (RNN), linear regression (LR), Ridge, and Lasso methods were compared for FAC-DC prediction in terms of the root-mean-squared error (RMSE). RNN variable importance, which is the RMSE gap between a complete RNN model and an RNN model excluding a certain variable, was used to evaluate the contribution of this variable. Based on the results of this study, the performance of the RNN was far better than that of LR, Ridge, and Lasso. The respective RMSEs were 0.3738, 2.2831, 1.3161, and 1.0246 for all the participants; 0.3727, 1.7176, 1.3914, and 1.3524 for those with trauma; and 0.3728, 1.7516, 1.1012, and 0.8889 for those without trauma. In terms of RNN variable importance, lower-extremity motor strength (right and left ankle dorsiflexors, right knee extensors, and left long toe extensors) and the neurological level of injury were ranked among the top five across the boards. Therefore, initial FAC was the seventh, third, and ninth most important predictor for all participants, those with trauma, and those without trauma, respectively. In conclusion, this study developed a deep learning-based prediction model with excellent performance for gait recovery after SCI at the time of discharge from an acute rehabilitation facility. This study also demonstrated the strength of deep learning as an explainable artificial intelligence method for identifying the most important predictors.

Machine learning analysis for the association between breast feeding and metabolic syndrome in women.

This cross-sectional study aimed to develop and validate population-based machine learning models for examining the association between breastfeeding and metabolic syndrome in women. The artificial neural network, the decision tree, logistic regression, the Naïve Bayes, the random forest and the support vector machine were developed and validated to predict metabolic syndrome in women. Data came from 30,204 women, who aged 20 years or more and participated in the Korean National Health and Nutrition Examination Surveys 2010-2019. The dependent variable was metabolic syndrome. The 86 independent variables included demographic/socioeconomic determinants, cardiovascular disease, breastfeeding duration and other medical/obstetric information. The random forest had the best performance in terms of the area under the receiver-operating-characteristic curve, e.g., 90.7%. According to random forest variable importance, the top predictors of metabolic syndrome included body mass index (0.1032), medication for hypertension (0.0552), hypertension (0.0499), cardiovascular disease (0.0453), age (0.0437) and breastfeeding duration (0.0191). Breastfeeding duration is a major predictor of metabolic syndrome for women together with body mass index, diagnosis and medication for hypertension, cardiovascular disease and age.

Explainable artificial intelligence for predicting red blood cell transfusion in geriatric patients undergoing hip arthroplasty: Machine learning analysis using national health insurance data.

This study uses machine learning and population data to analyze major determinants of blood transfusion among patients with hip arthroplasty. Retrospective cohort data came from Korea National Health Insurance Service claims data for 19,110 patients aged 65 years or more with hip arthroplasty in 2019. The dependent variable was blood transfusion (yes vs no) in 2019 and its 31 predictors were included. Random forest variable importance and Shapley Additive Explanations were used for identifying major predictors and the directions of their associations with blood transfusion. The random forest registered the area under the curve of 73.6%. Based on random forest variable importance, the top-10 predictors were anemia (0.25), tranexamic acid (0.17), age (0.16), socioeconomic status (0.05), spinal anesthesia (0.05), general anesthesia (0.04), sex (female) (0.04), dementia (0.03), iron (0.02), and congestive heart failure (0.02). These predictors were followed by their top-20 counterparts including cardiovascular disease, statin, chronic obstructive pulmonary disease, diabetes mellitus, chronic kidney disease, peripheral vascular disease, liver disease, solid tumor, myocardial infarction and hypertension. In terms of max Shapley Additive Explanations values, these associations were positive, e.g., anemia (0.09), tranexamic acid (0.07), age (0.09), socioeconomic status (0.05), spinal anesthesia (0.05), general anesthesia (0.04), sex (female) (0.02), dementia (0.03), iron (0.04), and congestive heart failure (0.03). For example, the inclusion of anemia, age, tranexamic acid or spinal anesthesia into the random forest will increase the probability of blood transfusion among patients with hip arthroplasty by 9%, 7%, 9% or 5%. Machine learning is an effective prediction model for blood transfusion among patients with hip arthroplasty. The high-risk group with anemia, age and comorbid conditions need to be treated with tranexamic acid, iron and/or other appropriate interventions.

Explainable Model Using Shapley Additive Explanations Approach on Wound Infection after Wide Soft Tissue Sarcoma Resection: "Big Data" Analysis Based on Health Insurance Review and Assessment Service Hub.

Background and Objectives: Soft tissue sarcomas represent a heterogeneous group of malignant mesenchymal tissues. Despite their low prevalence, soft tissue sarcomas present clinical challenges for orthopedic surgeons owing to their aggressive nature, and perioperative wound infections. However, the low prevalence of soft tissue sarcomas has hindered the availability of large-scale studies. This study aimed to analyze wound infections after wide resection in patients with soft tissue sarcomas by employing big data analytics from the Hub of the Health Insurance Review and Assessment Service (HIRA). Materials and Methods: Patients who underwent wide excision of soft tissue sarcomas between 2010 and 2021 were included. Data were collected from the HIRA database of approximately 50 million individuals' information in the Republic of Korea. The data collected included demographic information, diagnoses, prescribed medications, and surgical procedures. Random forest has been used to analyze the major associated determinants. A total of 10,906 observations with complete data were divided into training and validation sets in an 80:20 ratio (8773 vs. 2193 cases). Random forest permutation importance was employed to identify the major predictors of infection and Shapley Additive Explanations (SHAP) values were derived to analyze the directions of associations with predictors. Results: A total of 10,969 patients who underwent wide excision of soft tissue sarcomas were included. Among the study population, 886 (8.08%) patients had post-operative infections requiring surgery. The overall transfusion rate for wide excision was 20.67% (2267 patients). Risk factors among the comorbidities of each patient with wound infection were analyzed and dependence plots of individual features were visualized. The transfusion dependence plot reveals a distinctive pattern, with SHAP values displaying a negative trend for individuals without blood transfusions and a positive trend for those who received blood transfusions, emphasizing the substantial impact of blood transfusions on the likelihood of wound infection. Conclusions: Using the machine learning random forest model and the SHAP values, the perioperative transfusion, male sex, old age, and low SES were important features of wound infection in soft-tissue sarcoma patients.

Machine learning analysis with population data for the associations of preterm birth with temporomandibular disorder and gastrointestinal diseases.

This study employs machine learning analysis with population data for the associations of preterm birth (PTB) with temporomandibular disorder (TMD) and gastrointestinal diseases. The source of the population-based retrospective cohort was Korea National Health Insurance claims for 489,893 primiparous women with delivery at the age of 25-40 in 2017. The dependent variable was PTB in 2017. Twenty-one predictors were included, i.e., demographic, socioeconomic, disease and medication information during 2002-2016. Random forest variable importance was derived for finding important predictors of PTB and evaluating its associations with the predictors including TMD and gastroesophageal reflux disease (GERD). Shapley Additive Explanation (SHAP) values were calculated to analyze the directions of these associations. The random forest with oversampling registered a much higher area under the receiver-operating-characteristic curve compared to logistic regression with oversampling, i.e., 79.3% vs. 53.1%. According to random forest variable importance values and rankings, PTB has strong associations with low socioeconomic status, GERD, age, infertility, irritable bowel syndrome, diabetes, TMD, salivary gland disease, hypertension, tricyclic antidepressant and benzodiazepine. In terms of max SHAP values, these associations were positive, e.g., low socioeconomic status (0.29), age (0.21), GERD (0.27) and TMD (0.23). The inclusion of low socioeconomic status, age, GERD or TMD into the random forest will increase the probability of PTB by 0.29, 0.21, 0.27 or 0.23. A cutting-edge approach of explainable artificial intelligence highlights the strong associations of preterm birth with temporomandibular disorder, gastrointestinal diseases and antidepressant medication. Close surveillance is needed for pregnant women regarding these multiple risks at the same time.

Real-time Classification of Fetal Status Based on Deep Learning and Cardiotocography Data.

This study uses convolutional neural networks (CNNs) and cardiotocography data for the real-time classification of fetal status in the mobile application of a pregnant woman and the computer server of a data expert at the same time (The sensor is connected with the smartphone, which is linked with the web server for the woman and the computer server for the expert). Data came from 5249 (or 4833) cardiotocography traces in Anam Hospital for the mobile application (or the computer server). 150 data cases of 5-minute duration were extracted from each trace with 141,001 final cases for the mobile application and for the computer server alike. The dependent variable was fetal status with two categories (Normal, Abnormal) for the mobile application and three categories (Normal, Middle, Abnormal) for the computer server. The fetal heart rate served as a predictor for the mobile application and the computer server, while uterus contraction for the computer server only. The 1-dimension (or 2-dimension) Resnet CNN was trained for the mobile application (or the computer server) during 800 epochs. The sensitivity, specificity and their harmonic mean of the 1-dimension CNN for the mobile application were 94.9%, 91.2% and 93.0%, respectively. The corresponding statistics of the 2-dimension CNN for the computer server were 98.0%, 99.5% and 98.7%. The average inference time per 1000 images was 6.51 micro-seconds. Deep learning provides an efficient model for the real-time classification of fetal status in the mobile application and the computer server at the same time.

Association between early preterm birth and maternal exposure to fine particular matter (PM10): A nation-wide population-based cohort study using machine learning.

Although preterm birth (PTB), a birth before 34 weeks of gestation accounts for only less than 3% of total births, it is a critical cause of various perinatal morbidity and mortality. Several studies have been conducted on the association between maternal exposure to PM and PTB, but the results were inconsistent. Moreover, no study has analyzed the risk of PM on PTB among women with cardiovascular diseases, even though those were thought to be highly susceptible to PM considering the cardiovascular effect of PM. Therefore, we aimed to evaluate the effect of PM10 on early PTB according to the period of exposure, using machine learning with data from Korea National Health Insurance Service (KNHI) claims. Furthermore, we conducted subgroup analysis to compare the risk of PM on early PTB among pregnant women with cardiovascular diseases and those without. A total of 149,643 primiparous singleton women aged 25 to 40 years who delivered babies in 2017 were included. Random forest feature importance and SHAP (Shapley additive explanations) value were used to identify the effect of PM10 on early PTB in comparison with other well-known contributing factors of PTB. AUC and accuracy of PTB prediction model using random forest were 0.9988 and 0.9984, respectively. Maternal exposure to PM10 was one of the major predictors of early PTB. PM10 concentration of 5 to 7 months before delivery, the first and early second trimester of pregnancy, ranked high in feature importance. SHAP value showed that higher PM10 concentrations before 5 to 7 months before delivery were associated with an increased risk of early PTB. The probability of early PTB was increased by 7.73%, 10.58%, or 11.11% if a variable PM10 concentration of 5, 6, or 7 months before delivery was included to the prediction model. Furthermore, women with cardiovascular diseases were more susceptible to PM10 concentration in terms of risk for early PTB than those without cardiovascular diseases. Maternal exposure to PM10 has a strong association with early PTB. In addition, in the context of PTB, pregnant women with cardiovascular diseases are a high-risk group of PM10 and the first and early second trimester is a high-risk period of PM10.

Explainable artificial intelligence on life satisfaction, diabetes mellitus and its comorbid condition.

This study uses artificial intelligence for testing (1) whether the comorbidity of diabetes and its comorbid condition is very strong in the middle-aged or old (hypothesis 1) and (2) whether major determinants of the comorbidity are similar for different pairs of diabetes and its comorbid condition (hypothesis 2). Three pairs are considered, diabetes-cancer, diabetes-heart disease and diabetes-mental disease. Data came from the Korean Longitudinal Study of Ageing (2016-2018), with 5527 participants aged 56 or more. The evaluation of the hypotheses were based on (1) whether diabetes and its comorbid condition in 2016 were top-5 determinants of the comorbidity in 2018 (hypothesis 1) and (2) whether top-10 determinants of the comorbidity in 2018 were similar for different pairs of diabetes and its comorbid condition (hypothesis 2). Based on random forest variable importance, diabetes and its comorbid condition in 2016 were top-2 determinants of the comorbidity in 2018. Top-10 determinants of the comorbidity in 2018 were the same for different pairs of diabetes and its comorbid condition: body mass index, income, age, life satisfaction-health, life satisfaction-economic, life satisfaction-overall, subjective health and children alive in 2016. In terms of SHAP values, the probability of the comorbidity is expected to decrease by 0.02-0.03 in case life satisfaction overall is included to the model. This study supports the two hypotheses, highlighting the importance of preventive measures for body mass index, socioeconomic status, life satisfaction and family support to manage diabetes and its comorbid condition.

Relationships of Antidepressant Medication With Its Various Factors Including Nitrogen Dioxides Seasonality: Machine Learning Analysis Using National Health Insurance Data.

OBJECTIVE: This study employs machine learning and population-based data to examine major factors of antidepressant medication including nitrogen dioxides (NO2) seasonality. METHODS: Retrospective cohort data came from Korea National Health Insurance Service claims data for 43,251 participants with the age of 15-79 years, residence in the same districts of Seoul and no history of antidepressant medication during 2002-2012. The dependent variable was antidepressant-free months during 2013-2015 and the 103 independent variables for 2012 or 2015 were considered, e.g., particulate matter less than 2.5 micrometer in diameter (PM2.5), PM10, NO2, ozone (O3), sulphur dioxide (SO2) and carbon monoxide (CO) in each of 12 months in 2015. RESULTS: It was found that the Cox hazard ratios of NO2 were statistically significant and registered values larger than 10 for every three months: March, June-July, October, and December. Based on random forest variable importance and Cox hazard ratios in brackets, indeed, the top 20 factors of antidepressant medication included age (0.0041 [1.69-2.25]), migraine and sleep disorder (0.0029 [1.82]), liver disease (0.0017 [1.33-1.34]), exercise (0.0014), thyroid disease (0.0013), cardiovascular disease (0.0013 [1.20]), asthma (0.0008 [1.19-1.20]), September NO2 (0.0008 [0.01]), alcohol consumption (0.0008 [1.31-1.32]), gender - woman (0.0007 [1.80-1.81]), July NO2 (0.0007 [14.93]), July PM10 (0.0007), the proportion of the married (0.0005), January PM2.5 (0.0004), September PM2.5 (0.0004), chronic obstructive pulmonary disease (0.0004), economic satisfaction (0.0004), January PM10 (0.0003), residents in welfare facilities per 1,000 (0.0003 [0.97]), and October NO2 (0.0003). CONCLUSION: Antidepressant medication has strong associations with neighborhood conditions including NO2 seasonality and welfare support.

Preterm birth and maternal heart disease: A machine learning analysis using the Korean national health insurance database.

BACKGROUND: Maternal heart disease is suspected to affect preterm birth (PTB); however, validated studies on the association between maternal heart disease and PTB are still limited. This study aimed to build a prediction model for PTB using machine learning analysis and nationwide population data, and to investigate the association between various maternal heart diseases and PTB. METHODS: A population-based, retrospective cohort study was conducted using data obtained from the Korea National Health Insurance claims database, that included 174,926 primiparous women aged 25-40 years who delivered in 2017. The random forest variable importance was used to identify the major determinants of PTB and test its associations with maternal heart diseases, i.e., arrhythmia, ischemic heart disease (IHD), cardiomyopathy, congestive heart failure, and congenital heart disease first diagnosed before or during pregnancy. RESULTS: Among the study population, 12,701 women had PTB, and 12,234 women had at least one heart disease. The areas under the receiver-operating-characteristic curves of the random forest with oversampling data were within 88.53 to 95.31. The accuracy range was 89.59 to 95.22. The most critical variables for PTB were socioeconomic status and age. The random forest variable importance indicated the strong associations of PTB with arrhythmia and IHD among the maternal heart diseases. Within the arrhythmia group, atrial fibrillation/flutter was the most significant risk factor for PTB based on the Shapley additive explanation value. CONCLUSIONS: Careful evaluation and management of maternal heart disease during pregnancy would help reduce PTB. Machine learning is an effective prediction model for PTB and the major predictors of PTB included maternal heart disease such as arrhythmia and IHD.

Associations of Preterm Birth with Dental and Gastrointestinal Diseases: Machine Learning Analysis Using National Health Insurance Data.

BACKGROUND: This study uses machine learning with large-scale population data to assess the associations of preterm birth (PTB) with dental and gastrointestinal diseases. METHODS: Population-based retrospective cohort data came from Korea National Health Insurance claims for 124,606 primiparous women aged 25-40 and delivered in 2017. The 186 independent variables included demographic/socioeconomic determinants, disease information, and medication history. Machine learning analysis was used to establish the prediction model of PTB. Random forest variable importance was used for identifying major determinants of PTB and testing its associations with dental and gastrointestinal diseases, medication history, and socioeconomic status. RESULTS: The random forest with oversampling data registered an accuracy of 84.03, and the areas under the receiver-operating-characteristic curves with the range of 84.03-84.04. Based on random forest variable importance with oversampling data, PTB has strong associations with socioeconomic status (0.284), age (0.214), year 2014 gastroesophageal reflux disease (GERD) (0.026), year 2015 GERD (0.026), year 2013 GERD (0.024), progesterone (0.024), year 2012 GERD (0.023), year 2011 GERD (0.021), tricyclic antidepressant (0.020) and year 2016 infertility (0.019). For example, the accuracy of the model will decrease by 28.4%, 2.6%, or 1.9% if the values of socioeconomic status, year 2014 GERD, or year 2016 infertility are randomly permutated (or shuffled). CONCLUSION: By using machine learning, we established a valid prediction model for PTB. PTB has strong associations with GERD and infertility. Pregnant women need close surveillance for gastrointestinal and obstetric risks at the same time.

Blood Transfusion, All-Cause Mortality and Hospitalization Period in COVID-19 Patients: Machine Learning Analysis of National Health Insurance Claims Data.

This study presents the most comprehensive machine-learning analysis for the predictors of blood transfusion, all-cause mortality, and hospitalization period in COVID-19 patients. Data came from Korea National Health Insurance claims data with 7943 COVID-19 patients diagnosed during November 2019−May 2020. The dependent variables were all-cause mortality and the hospitalization period, and their 28 independent variables were considered. Random forest variable importance (GINI) was introduced for identifying the main factors of the dependent variables and evaluating their associations with these predictors, including blood transfusion. Based on the results of this study, blood transfusion had a positive association with all-cause mortality. The proportions of red blood cell, platelet, fresh frozen plasma, and cryoprecipitate transfusions were significantly higher in those with death than in those without death (p-values < 0.01). Likewise, the top ten factors of all-cause mortality based on random forest variable importance were the Charlson Comorbidity Index (53.54), age (45.68), socioeconomic status (45.65), red blood cell transfusion (27.08), dementia (19.27), antiplatelet (16.81), gender (14.60), diabetes mellitus (13.00), liver disease (11.19) and platelet transfusion (10.11). The top ten predictors of the hospitalization period were the Charlson Comorbidity Index, socioeconomic status, dementia, age, gender, hemiplegia, antiplatelet, diabetes mellitus, liver disease, and cardiovascular disease. In conclusion, comorbidity, red blood cell transfusion, and platelet transfusion were the major factors of all-cause mortality based on machine learning analysis. The effective management of these predictors is needed in COVID-19 patients.

Machine learning-based risk factor analysis of necrotizing enterocolitis in very low birth weight infants.

This study used machine learning and a national prospective cohort registry database to analyze the major risk factors of necrotizing enterocolitis (NEC) in very low birth weight (VLBW) infants, including environmental factors. The data consisted of 10,353 VLBW infants from the Korean Neonatal Network database from January 2013 to December 2017. The dependent variable was NEC. Seventy-four predictors, including ambient temperature and particulate matter, were included. An artificial neural network, decision tree, logistic regression, naïve Bayes, random forest, and support vector machine were used to evaluate the major predictors of NEC. Among the six prediction models, logistic regression and random forest had the best performance (accuracy: 0.93 and 0.93, area under the receiver-operating-characteristic curve: 0.73 and 0.72, respectively). According to random forest variable importance, major predictors of NEC were birth weight, birth weight Z-score, maternal age, gestational age, average birth year temperature, birth year, minimum birth year temperature, maximum birth year temperature, sepsis, and male sex. To the best of our knowledge, the performance of random forest in this study was among the highest in this line of research. NEC is strongly associated with ambient birth year temperature, as well as maternal and neonatal predictors.

Explainable Artificial Intelligence in the Early Diagnosis of Gastrointestinal Disease.

This study reviews the recent progress of explainable artificial intelligence for the early diagnosis of gastrointestinal disease (GID). The source of data was eight original studies in PubMed. The search terms were "gastrointestinal" (title) together with "random forest" or "explainable artificial intelligence" (abstract). The eligibility criteria were the dependent variable of GID or a strongly associated disease, the intervention(s) of artificial intelligence, the outcome(s) of accuracy and/or the area under the receiver operating characteristic curve (AUC), the outcome(s) of variable importance and/or the Shapley additive explanations (SHAP), a publication year of 2020 or later, and the publication language of English. The ranges of performance measures were reported to be 0.70-0.98 for accuracy, 0.04-0.25 for sensitivity, and 0.54-0.94 for the AUC. The following factors were discovered to be top-10 predictors of gastrointestinal bleeding in the intensive care unit: mean arterial pressure (max), bicarbonate (min), creatinine (max), PMN, heart rate (mean), Glasgow Coma Scale, age, respiratory rate (mean), prothrombin time (max) and aminotransferase aspartate (max). In a similar vein, the following variables were found to be top-10 predictors for the intake of almond, avocado, broccoli, walnut, whole-grain barley, and/or whole-grain oat: Roseburia undefined, Lachnospira spp., Oscillibacter undefined, Subdoligranulum spp., Streptococcus salivarius subsp. thermophiles, Parabacteroides distasonis, Roseburia spp., Anaerostipes spp., Lachnospiraceae ND3007 group undefined, and Ruminiclostridium spp. Explainable artificial intelligence provides an effective, non-invasive decision support system for the early diagnosis of GID.

Machine learning-based risk factor analysis of adverse birth outcomes in very low birth weight infants.

This study aimed to analyze major predictors of adverse birth outcomes in very low birth weight (VLBW) infants including particulate matter concentration (PM10), using machine learning and the national prospective cohort. Data consisted of 10,423 VLBW infants from the Korean Neonatal Network database during January 2013-December 2017. Five adverse birth outcomes were considered as the dependent variables, i.e., gestational age less than 28 weeks, gestational age less than 26 weeks, birth weight less than 1000 g, birth weight less than 750 g and small-for-gestational age. Thirty-three predictors were included and the artificial neural network, the decision tree, the logistic regression, the Naïve Bayes, the random forest and the support vector machine were used for predicting the dependent variables. Among the six prediction models, the random forest had the best performance (accuracy 0.79, area under the receiver-operating-characteristic curve 0.72). According to the random forest variable importance, major predictors of adverse birth outcomes were maternal age (0.2131), birth-month (0.0767), PM10 month (0.0656), sex (0.0428), number of fetuses (0.0424), primipara (0.0395), maternal education (0.0352), pregnancy-induced hypertension (0.0347), chorioamnionitis (0.0336) and antenatal steroid (0.0318). In conclusion, adverse birth outcomes had strong associations with PM10 month as well as maternal and fetal factors.

Machine Learning on Early Diagnosis of Depression.

To review the recent progress of machine learning for the early diagnosis of depression (major depressive disorder). The source of data was 32 original studies in the Web of Science. The search terms were "depression" (title) and "random forest" (abstract). The eligibility criteria were the dependent variable of depression, the interventions of machine learning (the decision tree, the naïve Bayesian, the random forest, the support vector machine and/or the artificial neural network), the outcomes of accuracy and/or the area under the receiver operating characteristic curve (AUC) for the early diagnosis of depression, the publication year of 2000 or later, the publication language of English and the publication journal of SCIE/SSCI. Different machine learning methods would be appropriate for different types of data for the early diagnosis of depression, e.g., logistic regression, the random forest, the support vector machine and/or the artificial neural network in the case of numeric data, the random forest in the case of genomic data. Their performance measures reported varied within 60.1-100.0 for accuracy and 64.0-96.0 for the AUC. Machine learning provides an effective, non-invasive decision support system for early diagnosis of depression.