Risk Prediction Model for Chronic Kidney Disease in Thailand Using Artificial Intelligence and SHAP.

Chronic kidney disease (CKD) is a multifactorial, complex condition that requires proper management to slow its progression. In Thailand, 11.6 million people (17.5%) have CKD, with 5.7 million (8.6%) in the advanced stages and >100,000 requiring hemodialysis (2020 report). This study aimed to develop a risk prediction model for CKD in Thailand. Data from 17,100 patients were collected to screen for 14 independent variables selected as risk factors, using the IBK, Random Tree, Decision Table, J48, and Random Forest models to train the predictive models. In addition, we address the unbalanced category issue using the synthetic minority oversampling technique (SMOTE). The indicators of performance include classification accuracy, sensitivity, specificity, and precision. This study achieved an accuracy rate of 92.1% with the top-performing Random Forest model. Moreover, our empirical findings substantiate previous research through highlighting the significance of serum albumin, blood urea nitrogen, age, direct bilirubin, and glucose. Furthermore, this study used the SHapley Additive exPlanations approach to analyze the attributes of the top six critical factors and then extended the comparison to include dual-attribute factors. Finally, our proposed machine learning technique can be used to evaluate the effectiveness of these risk factors and assist in the development of future personalized treatment.

A comparison of performance between a deep learning model with residents for localization and classification of intracranial hemorrhage.

Intracranial hemorrhage (ICH) from traumatic brain injury (TBI) requires prompt radiological investigation and recognition by physicians. Computed tomography (CT) scanning is the investigation of choice for TBI and has become increasingly utilized under the shortage of trained radiology personnel. It is anticipated that deep learning models will be a promising solution for the generation of timely and accurate radiology reports. Our study examines the diagnostic performance of a deep learning model and compares the performance of that with detection, localization and classification of traumatic ICHs involving radiology, emergency medicine, and neurosurgery residents. Our results demonstrate that the high level of accuracy achieved by the deep learning model, (0.89), outperforms the residents with regard to sensitivity (0.82) but still lacks behind in specificity (0.90). Overall, our study suggests that the deep learning model may serve as a potential screening tool aiding the interpretation of head CT scans among traumatic brain injury patients.

Automatic hemorrhage segmentation on head CT scan for traumatic brain injury using 3D deep learning model.

The most common cause of long-term disability and death in young adults is a traumatic brain injury. The decision for surgical intervention for craniotomy is dependent on the injury type and the patient's neurologic exam. The potential subtypes of intracranial hemorrhage that may necessitate surgical intervention include subdural hemorrhage, epidural hemorrhage, and intraparenchymal hemorrhage. We proposed a novel automatic method for segmenting the hemorrhage subtypes on a CT scan by integrated CT scan with bone window as input of a deep learning model. Brain CT scans were collected from adult patients and annotated regions of subdural hemorrhage, epidural hemorrhage, and intraparenchymal hemorrhage by neuroradiologists. Their raw DICOM images were preprocessed by two different window settings i.e., subdural and bone windows. The collected CT scans were divided into two datasets namely training and test datasets. A deep-learning model was modified to segment regions of each hemorrhage subtype. The model is a three-dimensional convolutional neural network including four parallel pathways that process the input at different resolutions. It was trained by a training dataset. After the segmentation result was produced by the deep-learning model, it was then improved in the post-processing step. The size of the segmented lesion was considered, and a region-growing algorithm was applied. We evaluated the performance of the proposed method on the test dataset. The method reached the median Dice similarity coefficients higher than 0.37 for each hemorrhage subtype. The proposed method demonstrates higher Dice similarity coefficients and improved segmentation performance compared to previously published literature.

AUTOMATIC ICD-10 CODING USING PRESCRIBED DRUGS DATA.

This article discusses the emerging trends and challenges related to automatic clinical coding. We introduce an automatic coding system, which assigns short ICD-10 codes (restricted to the first three symbols, which define the category of the disease) based only on drugs prescribed to patients. We show that even with limited input data, the accuracy levels are comparable to those achieved by entry-level clinical coders as depicted by Seyed Nouraei et al.1 We also examine the standard method for performance estimation and speculate that the actual accuracy of our coding system is even higher than estimated.

High alert drugs screening using gradient boosting classifier.

Prescription errors in high alert drugs (HAD), a group of drugs that have a high risk of complications and potential negative consequences, are a major and serious problem in medicine. Standardized hospital interventions, protocols, or guidelines were implemented to reduce the errors but were not found to be highly effective. Machine learning driven clinical decision support systems (CDSS) show a potential solution to address this problem. We developed a HAD screening protocol with a machine learning model using Gradient Boosting Classifier and screening parameters to identify the events of HAD prescription errors from the drug prescriptions of out and inpatients at Maharaj Nakhon Chiang Mai hospital in 2018. The machine learning algorithm was able to screen drug prescription events with a risk of HAD inappropriate use and identify over 98% of actual HAD mismatches in the test set and 99% in the evaluation set. This study demonstrates that machine learning plays an important role and has potential benefit to screen and reduce errors in HAD prescriptions.

Auto-mapping Clinical Documents to ICD-10 using SNOMED-CT.

Excessive paperwork is a considerable issue that leads to additional burdens for health-care professionals. In Thai health-care systems, physicians manually review medical records to select an appropriate principle diagnosis and other co-morbidities and convert them into ICD-10s to claim financial support from the government. Accordingly, 160,000 ICD-10 codes and 46,000 in-patient discharge summaries are documented by physicians at Maharaj Nakorn Chiang Mai hospital each year. As a result, to decrease physicians' burden of manual paper-work, we created a new approach to automatically analyse discharge summary notes and map the diagnoses to ICD-10s. We combined SNOMED-CT and natural language processing techniques within the approach through 3 steps: cleaning data; extracting keywords from discharge summary notes; and matching keywords to ICD-10. In this paper, we present that mapping clinical documents by using approximate matching and SNOMED-CT shows potential to be used for automating the ICD-10 mapping process.

Bone mineral density response prediction following osteoporosis treatment using machine learning to aid personalized therapy.

Osteoporosis is a global health problem for ageing populations. The goals of osteoporosis treatment are to improve bone mineral density (BMD) and prevent fractures. One major obstacle that remains a great challenge to achieve the goals is how to select the best treatment regimen for individual patients. We developed a computational model from 8981 clinical variables, including demographic data, diagnoses, laboratory results, medications, and initial BMD results, taken from 10-year period of electronic medical records to predict BMD response after treatment. We trained 7 machine learning models with 13,562 osteoporosis treatment instances [comprising 5080 (37.46%) inadequate treatment responses and 8482 (62.54%) adequate responses] and selected the best model (Random Forests with area under the receiver operating curve of 0.70, accuracy of 0.69, precision of 0.70, and recall of 0.89) to individually predict treatment responses of 11 therapeutic regimens, then selected the best predicted regimen to compare with the actual regimen. The results showed that the average treatment response of the recommended regimens was 9.54% higher than the actual regimens. In summary, our novel approach using a machine learning-based decision support system is capable of predicting BMD response after osteoporosis treatment and personalising the most appropriate treatment regimen for an individual patient.

DrKnow: A Diagnostic Learning Tool with Feedback from Automated Clinical Decision Support.

Providing medical trainees with effective feedback is critical to the successful development of their diagnostic reasoning skills. We present the design of DrKnow, a web-based learning application that utilises a clinical decision support system (CDSS) and virtual cases to support the development of problem-solving and decision-making skills in medical students. Based on the clinical information they request and prioritise, DrKnow provides personalised feedback to help students develop differential and provisional diagnoses at key decision points as they work through the virtual cases. Once students make a final diagnosis, DrKnow presents students with information about their overall diagnostic performance as well as recommendations for diagnosing similar cases. This paper argues that designing DrKnow around a task-sensitive CDSS provides a suitable approach enabling positive student learning outcomes, while simultaneously overcoming the resource challenges of expert clinician-supported bedside teaching.

Diagnostic Machine Learning Models for Acute Abdominal Pain: Towards an e-Learning Tool for Medical Students.

Computer-aided learning systems (e-learning systems) can help medical students gain more experience with diagnostic reasoning and decision making. Within this context, providing feedback that matches students' needs (i.e. personalised feedback) is both critical and challenging. In this paper, we describe the development of a machine learning model to support medical students' diagnostic decisions. Machine learning models were trained on 208 clinical cases presenting with abdominal pain, to predict five diagnoses. We assessed which of these models are likely to be most effective for use in an e-learning tool that allows students to interact with a virtual patient. The broader goal is to utilise these models to generate personalised feedback based on the specific patient information requested by students and their active diagnostic hypotheses.

Implementation of integrated heterogeneous electronic electrocardiography data into Maharaj Nakorn Chiang Mai Hospital Information System.

Electrocardiography is one of the most important non-invasive diagnostic tools for diagnosing coronary heart disease. The electrocardiography information system in Maharaj Nakorn Chiang Mai Hospital required a massive manual labor effort. In this article, we propose an approach toward the integration of heterogeneous electrocardiography data and the implementation of an integrated electrocardiography information system into the existing Hospital Information System. The system integrates different electrocardiography formats into a consistent electrocardiography rendering by using Java software. The interface acts as middleware to seamlessly integrate different electrocardiography formats. Instead of using a common electrocardiography protocol, we applied a central format based on Java classes for mapping different electrocardiography formats which contains a specific parser for each electrocardiography format to acquire the same information. Our observations showed that the new system improved the effectiveness of data management, work flow, and data quality; increased the availability of information; and finally improved quality of care.

Effective ECG reference ranges for Northern Thai people.

BACKGROUND: The numerical values and ranges of the ECG are used as criteria for classifying types of arrhythmia. However, one criterion cannot be generically applied for all patient groups. Several studies have shown that age, gender, and race are the major key factors which produce variations in ECG values. METHODS: From May 2013 to February 2014, we collected 12 993 normal ECG data from 9853 Northern Thai patients at Maharaj Nakorn Chiang Mai Hospital, Chiang Mai, Thailand, to analyse their ECG reference ranges. RESULTS: The results showed that the average heart rate decreased, while the PR interval and QTcB increased with increasing age in both genders. The normal range of heart rate was lower than the standard interval. QRS duration was stable in all age groups but longer in males than females. QRS axis deviated to the left with increasing age. SV1+RV5 amplitude slightly changed in both genders, but the upper limit crossed over the criteria of ventricular hypertrophy. CONCLUSIONS: We observed that the general trend of data was mainly similar to that found in other studies in Chinese, American, and African populations. However, some minor differences should be considered specifically for the Northern Thai population. Flexible criteria on conditions depending on age and gender should be adjusted for Northern Thai patients according to the results of this research.