Prediction of Bacteremia Based on 12-Year Medical Data Using a Machine Learning Approach: Effect of Medical Data by Extraction Time.

Early detection of bacteremia is important to prevent antibiotic abuse. Therefore, we aimed to develop a clinically applicable bacteremia prediction model using machine learning technology. Data from two tertiary medical centers' electronic medical records during a 12-year-period were extracted. Multi-layer perceptron (MLP), random forest, and gradient boosting algorithms were applied for machine learning analysis. Clinical data within 12 and 24 hours of blood culture were analyzed and compared. Out of 622,771 blood cultures, 38,752 episodes of bacteremia were identified. In MLP with 128 hidden layer nodes, the area under the receiver operating characteristic curve (AUROC) of the prediction performance in 12- and 24-h data models was 0.762 (95% confidence interval (CI); 0.7617-0.7623) and 0.753 (95% CI; 0.7520-0.7529), respectively. AUROC of causative-pathogen subgroup analysis predictive value for Acinetobacter baumannii bacteremia was the highest at 0.839 (95% CI; 0.8388-0.8394). Compared to primary bacteremia, AUROC of sepsis caused by pneumonia was highest. Predictive performance of bacteremia was superior in younger age groups. Bacteremia prediction using machine learning technology appeared possible for acute infectious diseases. This model was more suitable especially to pneumonia caused by Acinetobacter baumannii. From the 24-h blood culture data, bacteremia was predictable by substituting only the continuously variable values.

Development and External Validation of a Deep Learning Algorithm for Prognostication of Cardiovascular Outcomes.

BACKGROUND AND OBJECTIVES: We aim to explore the additional discriminative accuracy of a deep learning (DL) algorithm using repeated-measures data for identifying people at high risk for cardiovascular disease (CVD), compared to Cox hazard regression. METHODS: Two CVD prediction models were developed from National Health Insurance Service-Health Screening Cohort (NHIS-HEALS): a Cox regression model and a DL model. Performance of each model was assessed in the internal and 2 external validation cohorts in Koreans (National Health Insurance Service-National Sample Cohort; NHIS-NSC) and in Europeans (Rotterdam Study). A total of 412,030 adults in the NHIS-HEALS; 178,875 adults in the NHIS-NSC; and the 4,296 adults in Rotterdam Study were included. RESULTS: Mean ages was 52 years (46% women) and there were 25,777 events (6.3%) in NHIS-HEALS during the follow-up. In internal validation, the DL approach demonstrated a C-statistic of 0.896 (95% confidence interval, 0.886-0.907) in men and 0.921 (0.908-0.934) in women and improved reclassification compared with Cox regression (net reclassification index [NRI], 24.8% in men, 29.0% in women). In external validation with NHIS-NSC, DL demonstrated a C-statistic of 0.868 (0.860-0.876) in men and 0.889 (0.876-0.898) in women, and improved reclassification compared with Cox regression (NRI, 24.9% in men, 26.2% in women). In external validation applied to the Rotterdam Study, DL demonstrated a C-statistic of 0.860 (0.824-0.897) in men and 0.867 (0.830-0.903) in women, and improved reclassification compared with Cox regression (NRI, 36.9% in men, 31.8% in women). CONCLUSIONS: A DL algorithm exhibited greater discriminative accuracy than Cox model approaches. TRIAL REGISTRATION: ClinicalTrials.gov Identifier: NCT02931500.

Early Detection of Bacteraemia Using Ten Clinical Variables with an Artificial Neural Network Approach.

An adequate model for predicting bacteraemia has not yet been developed. This study aimed to evaluate the performance of an artificial neural network (ANN)-based prediction model in comparison with previous statistical models. The performance of multi-layer perceptron (MLP), a representative ANN model, was verified via comparison with a non-neural network model. A total of 1260 bacteraemia episodes were identified in 13,402 patients. In MLP with 128 hidden layer nodes, the area under the receiver operating characteristic curve (AUC) of the prediction performance was 0.729 (95% confidence interval [CI]; 0.712-0.728), while in MLP with 256 hidden layer nodes, it was 0.727 (95% CI; 0.713-0.727). In a conventional Bayesian statistical method, the AUC was 0.7. The aforementioned two MLP models exhibited the highest sensitivity (0.810). The ranking of clinical variables was used to describe the influential power of the prediction. Serum alkaline phosphatase was one of the most influential clinical variables, and one-out search was the best ranking method for measuring the influence of the clinical variables. Furthermore, adding variables beyond the 10 top-ranking ones did not significantly affect the prediction of bacteraemia. The ANN model is not inferior to conventional statistical approaches. Bacteraemia can be predicted using only the top 10 clinical variables determined by a ranking method, and the model can be used in clinical practice by applying real-time monitoring.

Development and verification of prediction models for preventing cardiovascular diseases.

OBJECTIVES: Cardiovascular disease (CVD) is one of the major causes of death worldwide. For improved accuracy of CVD prediction, risk classification was performed using national time-series health examination data. The data offers an opportunity to access deep learning (RNN-LSTM), which is widely known as an outstanding algorithm for analyzing time-series datasets. The objective of this study was to show the improved accuracy of deep learning by comparing the performance of a Cox hazard regression and RNN-LSTM based on survival analysis. METHODS AND FINDINGS: We selected 361,239 subjects (age 40 to 79 years) with more than two health examination records from 2002-2006 using the National Health Insurance System-National Health Screening Cohort (NHIS-HEALS). The average number of health screenings (from 2002-2013) used in the analysis was 2.9 ± 1.0. Two CVD prediction models were developed from the NHIS-HEALS data: a Cox hazard regression model and a deep learning model. In an internal validation of the NHIS-HEALS dataset, the Cox regression model showed a highest time-dependent area under the curve (AUC) of 0.79 (95% CI 0.70 to 0.87) for in females and 0.75 (95% CI 0.70 to 0.80) in males at 2 years. The deep learning model showed a highest time-dependent AUC of 0.94 (95% CI 0.91 to 0.97) for in females and 0.96 (95% CI 0.95 to 0.97) in males at 2 years. Layer-wise Relevance Propagation (LRP) revealed that age was the variable that had the greatest effect on CVD, followed by systolic blood pressure (SBP) and diastolic blood pressure (DBP), in that order. CONCLUSION: The performance of the deep learning model for predicting CVD occurrences was better than that of the Cox regression model. In addition, it was confirmed that the known risk factors shown to be important by previous clinical studies were extracted from the study results using LRP.

Cox Proportional Hazard Regression Versus a Deep Learning Algorithm in the Prediction of Dementia: An Analysis Based on Periodic Health Examination.

BACKGROUND: With the increase in the world's aging population, there is a growing need to prevent and predict dementia among the general population. The availability of national time-series health examination data in South Korea provides an opportunity to use deep learning algorithm, an artificial intelligence technology, to expedite the analysis of mass and sequential data. OBJECTIVE: This study aimed to compare the discriminative accuracy between a time-series deep learning algorithm and conventional statistical methods to predict all-cause dementia and Alzheimer dementia using periodic health examination data. METHODS: Diagnostic codes in medical claims data from a South Korean national health examination cohort were used to identify individuals who developed dementia or Alzheimer dementia over a 10-year period. As a result, 479,845 and 465,081 individuals, who were aged 40 to 79 years and without all-cause dementia and Alzheimer dementia, respectively, were identified at baseline. The performance of the following 3 models was compared with predictions of which individuals would develop either type of dementia: Cox proportional hazards model using only baseline data (HR-B), Cox proportional hazards model using repeated measurements (HR-R), and deep learning model using repeated measurements (DL-R). RESULTS: The discrimination indices (95% CI) for the HR-B, HR-R, and DL-R models to predict all-cause dementia were 0.84 (0.83-0.85), 0.87 (0.86-0.88), and 0.90 (0.90-0.90), respectively, and those to predict Alzheimer dementia were 0.87 (0.86-0.88), 0.90 (0.88-0.91), and 0.91 (0.91-0.91), respectively. The DL-R model showed the best performance, followed by the HR-R model, in predicting both types of dementia. The DL-R model was superior to the HR-R model in all validation groups tested. CONCLUSIONS: A deep learning algorithm using time-series data can be an accurate and cost-effective method to predict dementia. A combination of deep learning and proportional hazards models might help to enhance prevention strategies for dementia.

Colon Transit Time May Predict Inadequate Bowel Preparation in Patients With Chronic Constipation.

BACKGROUND/AIMS: We evaluated whether colonic transit time (CTT) can predict the degree of bowel preparation in patients with chronic constipation undergoing scheduled colonoscopy in order to assist in the development of better bowel preparation strategies for these patients. METHODS: We analyzed the records of 160 patients with chronic constipation from March 2007 to November 2012. We enrolled patients who had undergone a CTT test followed by colonoscopy. We defined patients with a CTT ≥30 hours as the slow transit time (STT) group, and patients with a CTT <30 hours as the normal transit time (NTT) group. Boston Bowel Preparation Scale (BBPS) scores were compared between the STT and NTT groups. RESULTS: Of 160 patients with chronic constipation, 82 (51%) were included in the STT group and 78 (49%) were included in the NTT group. Patients with a BBPS score of <6 were more prevalent in the STT group than in the NTT group (31.7% vs. 10.3%, P=0.001). Multivariate analysis showed that slow CTT was an independent predictor of inadequate bowel preparation (odds ratio, 0.261; 95% confidence interval, 0.107-0.634; P=0.003). The best CTT cut-off value for predicting inadequate bowel preparation in patients with chronic constipation was 37 hours, as determined by receiver operator characteristic (ROC) curve analysis (area under the ROC curve: 0.676, specificity: 0.735, sensitivity: 0.643). CONCLUSIONS: Patients with chronic constipation and a CTT >30 hours were at risk for inadequate bowel preparation. CTT measured prior to colonoscopy could be useful for developing individualized strategies for bowel preparation in patients with slow CTT, as these patients are likely to have inadequate bowel preparation.

Relationship between tetrahydrobiopterin and portal hypertension in patients with chronic liver disease.

Tetrahydrobiopterin (BH4) is an essential cofactor in NO synthesis by endothelial nitric oxide synthase (eNOS) enzymes. It has been previously suggested that reduced intrahepatic BH4 results in a decrease in intrahepatic NO and contributes to increased hepatic vascular resistance and portal pressure in animal models of cirrhosis. The main aim of the present study was to evaluate the relationship between BH4 and portal hypertension (PHT). One hundred ninety-three consecutive patients with chronic liver disease were included in the study. Liver biopsy, measurement of BH4 and hepatic venous pressure gradient (HVPG) were performed. Hepatic fibrosis was classified using the Laennec fibrosis scoring system. BH4 levels were determined in homogenized liver tissues of patients using a high performance liquid chromatography (HPLC) system. Statistical analysis was performed to evaluate the relationship between BH4 and HVPG, grade of hepatic fibrosis, clinical stage of cirrhosis, Child-Pugh class. A positive relationship between HVPG and hepatic fibrosis grade, clinical stage of cirrhosis and Child-Pugh class was observed. However, the BH4 level showed no significant correlation with HVPG or clinical features of cirrhosis. BH4 concentration in liver tissue has little relation to the severity of portal hypertension in patients with chronic liver disease.

The usefulness of non-invasive liver stiffness measurements in predicting clinically significant portal hypertension in cirrhotic patients: Korean data.

BACKGROUND/AIMS: Liver stiffness measurement (LSM) has been proposed as a non-invasive method for estimating the severity of fibrosis and the complications of cirrhosis. Measurement of the hepatic venous pressure gradient (HVPG) is the gold standard for assessing the presence of portal hypertension, but its invasiveness limits its clinical application. In this study we evaluated the relationship between LSM and HVPG, and the predictive value of LSM for clinically significant portal hypertension (CSPH) and severe portal hypertension in cirrhosis. METHODS: LSM was performed with transient elastography in 59 consecutive cirrhotic patients who underwent hemodynamic HVPG investigations. CSPH and severe portal hypertension were defined as HVPG ≥10 and ≥12 mmHg, respectively. Linear regression analysis was performed to evaluate the relationship between LSM and HVPG. Diagnostic values were analyzed based on receiver operating characteristic (ROC) curves. RESULTS: A strong positive correlation between LSM and HVPG was observed in the overall population (r(2)=0.496, P<0.0001). The area under the ROC curve (AUROC) for the prediction of CSPH (HVPG ≥10 mmHg) was 0.851, and the sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) for an LSM cutoff value of 21.95 kPa were 82.5%, 73.7%, 86.8%, and 66.7%, respectively. The AUROC at prediction of severe portal hypertension (HVPG ≥12 mmHg) was 0.877, and the sensitivity, specificity, PPV, and NPV at LSM cutoff value of 24.25 kPa were 82.9%, 70.8%, 80.6%, and 73.9%, respectively. CONCLUSIONS: LSM exhibited a significant correlation with HVPG in patients with cirrhosis. LSM could be a non-invasive method for predicting CSPH and severe portal hypertension in Korean patients with liver cirrhosis.

Complete endoscopic resection of very early stage gastric plasmacytoma.

Gastric plasmacytomas are very rare, and most are not detected until the disease has progressed to an advanced stage. However, there have been recent reports of cases of early-stage gastric plasmacytoma, in which neoplastic cells are confined to the mucosa or submucosa. Here we report a case of a very early stage gastric plasmacytoma that was confined to the lamina propria of the gastric mucosa. The lesion was successfully and completely removed by endoscopic submucosal dissection, and the surveillance endoscopy showed no recurrence during the follow-up of 40 months. This report appears to be the first documented case of complete endoscopic removal of a primary gastric plasmacytoma.