Application and Exploration of Big Data Mining in Clinical Medicine

Machine learning-based prediction model for the efficacy and safety of statins

Objective

The appropriate use of statins plays a vital role in reducing the risk of atherosclerotic cardiovascular disease (ASCVD). However, due to changes in diet and lifestyle, there has been a significant increase in the number of individuals with high cholesterol levels. Therefore, it is crucial to ensure the rational use of statins. Adverse reactions associated with statins, including liver enzyme abnormalities and statin-associated muscle symptoms (SAMS), have impacted their widespread utilization. In this study, we aimed to develop a predictive model for statin efficacy and safety based on real-world clinical data using machine learning techniques.

Methods

We employed various data preprocessing techniques, such as improved random forest imputation and Borderline SMOTE oversampling, to handle the dataset. Boruta method was utilized for feature selection, and the dataset was divided into training and testing sets in a 7:3 ratio. Five algorithms, including logistic regression, naive Bayes, decision tree, random forest, and gradient boosting decision tree, were used to construct the predictive models. Ten-fold cross-validation and bootstrapping sampling were performed for internal and external validation. Additionally, SHAP (SHapley Additive exPlanations) was employed for feature interpretability. Ultimately, an accessible web-based platform for predicting statin efficacy and safety was established based on the optimal predictive model.

Results

The random forest algorithm exhibited the best performance among the five algorithms. The predictive models for LDL-C target attainment (AUC = 0.883, Accuracy = 0.868, Precision = 0.858, Recall = 0.863, F1 = 0.860, AUPRC = 0.906, MCC = 0.761), liver enzyme abnormalities (AUC = 0.964, Accuracy = 0.964, Precision = 0.967, Recall = 0.963, F1 = 0.965, AUPRC = 0.978, MCC = 0.938), and muscle pain/Creatine kinase (CK) abnormalities (AUC = 0.981, Accuracy = 0.980, Precision = 0.987, Recall = 0.975, F1 = 0.981, AUPRC = 0.987, MCC = 0.965) demonstrated favorable performance. The most important features of LDL-C target attainment prediction model was cerebral infarction, TG, PLT and HDL. The most important features of liver enzyme abnormalities model was CRP, CK and number of oral medications. Similarly, AST, ALT, PLT and number of oral medications were found to be important features for muscle pain/CK abnormalities. Based on the best-performing predictive model, a user-friendly web application was designed and implemented.

Conclusion

This study presented a machine learning-based predictive model for statin efficacy and safety. The platform developed can assist in guiding statin therapy decisions and optimizing treatment strategies. Further research and application of the model are warranted to improve the utilization of statin therapy.

Outlier analysis for accelerating clinical discovery: An augmented intelligence framework and a systematic review

Clinical discoveries largely depend on dedicated clinicians and scientists to identify and pursue unique and unusual clinical encounters with patients and communicate these through case reports and case series. This process has remained essentially unchanged throughout the history of modern medicine. However, these traditional methods are inefficient, especially considering the modern-day availability of health-related data and the sophistication of computer processing. Outlier analysis has been used in various fields to uncover unique observations, including fraud detection in finance and quality control in manufacturing. We propose that clinical discovery can be formulated as an outlier problem within an augmented intelligence framework to be implemented on any health-related data. Such an augmented intelligence approach would accelerate the identification and pursuit of clinical discoveries, advancing our medical knowledge and uncovering new therapies and management approaches. We define clinical discoveries as contextual outliers measured through an information-based approach and with a novelty-based root cause. Our augmented intelligence framework has five steps: define a patient population with a desired clinical outcome, build a predictive model, identify outliers through appropriate measures, investigate outliers through domain content experts, and generate scientific hypotheses. Recognizing that the field of obstetrics can particularly benefit from this approach, as it is traditionally neglected in commercial research, we conducted a systematic review to explore how outlier analysis is implemented in obstetric research. We identified two obstetrics-related studies that assessed outliers at an aggregate level for purposes outside of clinical discovery. Our findings indicate that using outlier analysis in clinical research in obstetrics and clinical research, in general, requires further development.

Personalized antiseizure medication therapy in critically ill adult patients

Precision medicine has the potential to have a significant impact on both drug development and patient care. It is crucial to not only provide prompt effective antiseizure treatment for critically ill patients after seizures start but also have a proactive mindset and concentrate on epileptogenesis and the underlying cause of the seizures or seizure disorders. Critical illness presents different treatment issues compared with the ambulatory population, which makes it challenging to choose the best antiseizure medications and to administer them at the right time and at the right dose. Since there is a paucity of information available on antiseizure medication dosing in critically ill patients, therapeutic drug monitoring is a useful tool for defining each patient's personal therapeutic range and assisting clinicians in decision-making. Use of pharmacogenomic information relating to pharmacokinetics, hepatic metabolism, and seizure etiology may improve safety and efficacy by individualizing therapy. Studies evaluating the clinical implementation of pharmacogenomic information at the point-of-care and identification of biomarkers are also needed. These studies may make it possible to avoid adverse drug reactions, maximize drug efficacy, reduce drug-drug interactions, and optimize medications for each individual patient. This review will discuss the available literature and provide future insights on precision medicine use with antiseizure therapy in critically ill adult patients.

National data linkage assessment of live births and deaths in Mexico: Estimating under-five mortality rate ratios for vulnerable newborns and trends from 2008 to 2019

BACKGROUND

Linked datasets that enable longitudinal assessments are scarce in low and middle-income countries.

OBJECTIVES

We aimed to assess the linkage of administrative databases of live births and under-five child deaths to explore mortality and trends for preterm, small (SGA) and large for gestational age (LGA) in Mexico.

METHODS

We linked individual-level datasets collected by National statistics from 2008 to 2019. Linkage was performed based on agreement on birthday, sex, residential address. We used the Centre for Data and Knowledge Integration for Health software to identify the best candidate pairs based on similarity. Accuracy was assessed by calculating the area under the receiver operating characteristic curve. We evaluated completeness by comparing the number of linked records with reported deaths. We described the percentage of linked records by baseline characteristics to identify potential bias. Using the linked dataset, we calculated mortality rate ratios (RR) in neonatal, infants, and children under-five according to gestational age, birthweight, and size.

RESULTS

For the period 2008-2019, a total of 24,955,172 live births and 321,165 under-five deaths were available for linkage. We excluded 1,539,046 records (6.2%) with missing or implausible values. We succesfully linked 231,765 deaths (72.2%: range 57.1% in 2009 and 84.3% in 2011). The rate of neonatal mortality was higher for preterm compared with term (RR 3.83, 95% confidence interval, CI 3.78, 3.88) and for SGA compared with appropriate for gestational age (AGA) (RR 1.22 95% CI, 1.19, 1.24). Births at <28 weeks had the highest mortality (RR 35.92, 95%CI, 34.97, 36.88). LGA had no additional risk vs AGA among children under five (RR 0.92, 95%CI, 0.90, 0.93).

CONCLUSIONS

We demonstrated the utility of linked data to understand neonatal vulnerability and child mortality. We created a linked dataset that would be a valuable resource for future population-based research.

Henriques T. Machine learning models based on clinical indices and cardiotocographic features for discriminating asphyxia fetuses—Porto retrospective intrapartum study

Introduction

Perinatal asphyxia is one of the most frequent causes of neonatal mortality, affecting approximately four million newborns worldwide each year and causing the death of one million individuals. One of the main reasons for these high incidences is the lack of consensual methods of early diagnosis for this pathology. Estimating risk-appropriate health care for mother and baby is essential for increasing the quality of the health care system. Thus, it is necessary to investigate models that improve the prediction of perinatal asphyxia. Access to the cardiotocographic signals (CTGs) in conjunction with various clinical parameters can be crucial for the development of a successful model.

Objectives

This exploratory work aims to develop predictive models of perinatal asphyxia based on clinical parameters and fetal heart rate (fHR) indices.

Methods

Single gestations data from a retrospective unicentric study from Centro Hospitalar e Universitário do Porto de São João (CHUSJ) between 2010 and 2018 was probed. The CTGs were acquired and analyzed by Omniview-SisPorto, estimating several fHR features. The clinical variables were obtained from the electronic clinical records stored by ObsCare. Entropy and compression characterized the complexity of the fHR time series. These variables' contribution to the prediction of asphyxia perinatal was probed by binary logistic regression (BLR) and Naive-Bayes (NB) models.

Results

The data consisted of 517 cases, with 15 pathological cases. The asphyxia prediction models showed promising results, with an area under the receiver operator characteristic curve (AUC) &gt;70%. In NB approaches, the best models combined clinical and SisPorto features. The best model was the univariate BLR with the variable compression ratio scale 2 (CR2) and an AUC of 94.93% [94.55; 95.31%].

Conclusion

Both BLR and Bayesian models have advantages and disadvantages. The model with the best performance predicting perinatal asphyxia was the univariate BLR with the CR2 variable, demonstrating the importance of non-linear indices in perinatal asphyxia detection. Future studies should explore decision support systems to detect sepsis, including clinical and CTGs features (linear and non-linear).

Clinical decision support system for quality of life among the elderly: an approach using artificial neural network

Background

Due to advancements in medicine and the elderly population’s growth with various disabilities, attention to QoL among this age group is crucial. Early prediction of the QoL among the elderly by multiple care providers leads to decreased physical and mental disorders and increased social and environmental participation among them by considering all factors affecting it. So far, it is not designed the prediction system for QoL in this regard. Therefore, this study aimed to develop the CDSS based on ANN as an ML technique by considering the physical, psychiatric, and social factors.

Methods

In this developmental and applied study, we investigated the 980 cases associated with pleasant and unpleasant elderlies QoL cases. We used the BLR and simple correlation coefficient methods to attain the essential factors affecting the QoL among the elderly. Then three BP configurations, including CF-BP, FF-BP, and E-BP, were compared to get the best model for predicting the QoL.

Results

Based on the BLR, the 13 factors were considered the best factors affecting the elderly’s QoL at P < 0.05. Comparing all ANN configurations showed that the CF-BP with the 13-16-1 structure with sensitivity = 0.95, specificity  =  0.97, accuracy = 0.96, F-Score = 0.96, PPV = 0.95, and NPV = 0.97 gained the best performance for QoL among the elderly.

Conclusion

The results of this study showed that the designed CDSS based on the CFBP could be considered an efficient tool for increasing the QoL among the elderly.

Early prediction of diabetes by applying data mining techniques: A retrospective cohort study

BACKGROUND

Saudi Arabia ranks 7th globally in terms of diabetes prevalence, and its prevalence is expected to reach 45.36% by 2030. The cost of diabetes is expected to increase to 27 billion Saudi riyals in cases where undiagnosed individuals are also documented. Prevention and early detection can effectively address these challenges.

OBJECTIVE

To improve healthcare services and assist in building predictive models to estimate the probability of diabetes in patients.

METHODS

A chart review, which was a retrospective cohort study, was conducted at the National Guard Health Affairs in Riyadh, Saudi Arabia. Data were collected from 5 hospitals using National Guard Health Affairs databases. We used 38 attributes of 21431 patients between 2015 and 2019. The following phases were performed: (1) data collection, (2) data preparation, (3) data mining and model building, and (4) model evaluation and validation. Subsequently, 6 algorithms were compared with and without the synthetic minority oversampling technique.

RESULTS

The highest performance was found in the Bayesian network, which had an area under the curve of 0.75 and 0.71.

CONCLUSION

Although the results were acceptable, they could be improved. In this context, missing data owing to technical issues played a major role in affecting the performance of our model. Nevertheless, the model could be used in prevention, health monitoring programs, and as an automated mass population screening tool without the need for extra costs compared to traditional methods.

Different Data Mining Approaches Based Medical Text Data

The amount of medical text data is increasing dramatically. Medical text data record the progress of medicine and imply a large amount of medical knowledge. As a natural language, they are characterized by semistructured, high-dimensional, high data volume semantics and cannot participate in arithmetic operations. Therefore, how to extract useful knowledge or information from the total available data is very important task. Using various techniques of data mining can extract valuable knowledge or information from data. In the current study, we reviewed different approaches to apply for medical text data mining. The advantages and shortcomings for each technique compared to different processes of medical text data were analyzed. We also explored the applications of algorithms for providing insights to the users and enabling them to use the resources for the specific challenges in medical text data. Further, the main challenges in medical text data mining were discussed. Findings of this paper are benefit for helping the researchers to choose the reasonable techniques for mining medical text data and presenting the main challenges to them in medical text data mining.

Transformation and Evaluation of the MIMIC Database in the OMOP Common Data Model: Development and Usability Study

Background

In the era of big data, the intensive care unit (ICU) is likely to benefit from real-time computer analysis and modeling based on close patient monitoring and electronic health record data. The Medical Information Mart for Intensive Care (MIMIC) is the first open access database in the ICU domain. Many studies have shown that common data models (CDMs) improve database searching by allowing code, tools, and experience to be shared. The Observational Medical Outcomes Partnership (OMOP) CDM is spreading all over the world.

Objective

The objective was to transform MIMIC into an OMOP database and to evaluate the benefits of this transformation for analysts.

Methods

We transformed MIMIC (version 1.4.21) into OMOP format (version 5.3.3.1) through semantic and structural mapping. The structural mapping aimed at moving the MIMIC data into the right place in OMOP, with some data transformations. The mapping was divided into 3 phases: conception, implementation, and evaluation. The conceptual mapping aimed at aligning the MIMIC local terminologies to OMOP's standard ones. It consisted of 3 phases: integration, alignment, and evaluation. A documented, tested, versioned, exemplified, and open repository was set up to support the transformation and improvement of the MIMIC community's source code. The resulting data set was evaluated over a 48-hour datathon.

Results

With an investment of 2 people for 500 hours, 64% of the data items of the 26 MIMIC tables were standardized into the OMOP CDM and 78% of the source concepts mapped to reference terminologies. The model proved its ability to support community contributions and was well received during the datathon, with 160 participants and 15,000 requests executed with a maximum duration of 1 minute.

Conclusions

The resulting MIMIC-OMOP data set is the first MIMIC-OMOP data set available free of charge with real disidentified data ready for replicable intensive care research. This approach can be generalized to any medical field.

Fast prototyping of a local fuzzy search system for decision support and retraining of hospital staff during pandemic

PURPOSE

The COVID-19 pandemic showed an urgent need for decision support systems to help doctors at a time of stress and uncertainty. However, significant differences in hospital conditions, as well as skepticism of doctors about machine learning algorithms, limit their introduction into clinical practice. Our goal was to test and apply the principle of "patient-like-mine" decision support in rapidly changing conditions of a pandemic.

METHODS

In the developed system we implemented a fuzzy search that allows a doctor to compare their medical case with similar cases recorded in their medical center since the beginning of the pandemic. Various distance metrics were tried for obtaining clinically relevant search results. With the use of R programming language, we designed the first version of the system in approximately a week. A set of features for the comparison of the cases was selected with the use of random forest algorithm implemented in Caret. Shiny package was chosen for the design of GUI.

RESULTS

The deployed tool allowed doctors to quickly estimate the current conditions of their patients by means of studying the most similar previous cases stored in the local health information system. The extensive testing of the system during the first wave of COVID-19 showed that this approach helps not only to draw a conclusion about the optimal treatment tactics and to train medical staff in real-time but also to optimize patients' individual testing plans.

CONCLUSIONS

This project points to the possibility of rapid prototyping and effective usage of "patient-like-mine" search systems at the time of a pandemic caused by a poorly known pathogen.

Decision Tree-Based Classification for Maintaining Normal Blood Pressure Throughout Early Adulthood and Middle Age: Findings From the Coronary Artery Risk Development in Young Adults (CARDIA) Study

BACKGROUND

For most individuals, blood pressure (BP) is related to multiple risk factors. By utilizing the decision tree analysis technique, this study aimed to identify the best discriminative risk factors and interactions that are associated with maintaining normal BP over 30 years and to reveal segments of a population with a high probability of maintaining normal BP.

METHODS

Participants from the Coronary Artery Risk Development in Young Adults study aged 18-30 years with normal BP level at baseline visit (Y0, 1985-1986) were included in this study.

RESULTS

Of 3,156 participants, 1,132 (35.9%) maintained normal BP during the follow-up period and 2,024 (64.1%) developed higher BP. Systolic BP (SBP) within the normal range, race, and body mass index (BMI) were the most discriminative factors between participants who maintained normal BP throughout midlife and those who developed higher BP. Participants with a baseline SBP level ≤92 mm Hg and White women with baseline BMI < 23 kg/m2 were the two segments of the population with the highest probability for maintaining normal BP throughout midlife (69.2% and 59.9%, respectively). Among Black participants aged >26.5 years with BMI > 27 kg/m2, only 5.4% of participants maintained normal BP throughout midlife.

CONCLUSIONS

This study emphasizes the importance of early life factors to later life SBP and support efforts to maintain ideal levels of risk factors for hypertension at young ages. Whether policies to maintain lower BMI and SBP well below the clinical thresholds throughout young adulthood and middle age can reduce later age hypertension should be examined in future studies.

Data mining in clinical big data: the frequently used databases, steps, and methodological models

Many high quality studies have emerged from public databases, such as Surveillance, Epidemiology, and End Results (SEER), National Health and Nutrition Examination Survey (NHANES), The Cancer Genome Atlas (TCGA), and Medical Information Mart for Intensive Care (MIMIC); however, these data are often characterized by a high degree of dimensional heterogeneity, timeliness, scarcity, irregularity, and other characteristics, resulting in the value of these data not being fully utilized. Data-mining technology has been a frontier field in medical research, as it demonstrates excellent performance in evaluating patient risks and assisting clinical decision-making in building disease-prediction models. Therefore, data mining has unique advantages in clinical big-data research, especially in large-scale medical public databases. This article introduced the main medical public database and described the steps, tasks, and models of data mining in simple language. Additionally, we described data-mining methods along with their practical applications. The goal of this work was to aid clinical researchers in gaining a clear and intuitive understanding of the application of data-mining technology on clinical big-data in order to promote the production of research results that are beneficial to doctors and patients.

Artificial Intelligence for Screening Chinese Electronic Medical Record and Biobank Information

Objective: To establish a structured and integrated platform of clinical data and biobank data, and a client to retrieve these data. Study Design: Initially, the hospital information system (HIS) and biobank information system (BIS) were integrated through the patients' ID numbers. Then, natural language processing (NLP) was used to process the integrated unstructured clinical information. A query interface was designed for this system, which enabled researchers to retrieve clinical or biobank data. Finally, several queries were listed and manually checked to test the retrieval performance of the system. Results: The construction of the biobank screening system (BSS) was completed, and the data were structured. The BSS took an average of 2 seconds to perform a search for target patients/samples. The retrieval results were consistent with the HIS and BIS. For complex queries, we manually checked the retrieved patients/samples, and the system's accuracy was 100%. Conclusion: This NLP-based system improved biological sample screening and using of clinical data. We will continue to improve this system, enhance resource sharing, and promote the development of translational medicine.

Using a risk model for probability of cancer in pulmonary nodules

Background

Considering the high morbidity and mortality of lung cancer and the high incidence of pulmonary nodules, clearly distinguishing benign from malignant lung nodules at an early stage is of great significance. However, determining the kind of lung nodule which is more prone to lung cancer remains a problem worldwide.

Methods

A total of 480 patients with pulmonary nodule data were collected from Shandong, China. We assessed the clinical characteristics and computed tomography (CT) imaging features among pulmonary nodules in patients who had undergone video‐assisted thoracoscopic surgery (VATS) lobectomy from 2013 to 2018. Preliminary selection of features was based on a statistical analysis using SPSS. We used WEKA to assess the machine learning models using its multiple algorithms and selected the best decision tree model using its optimization algorithm.

Results

The combination of decision tree and logistics regression optimized the decision tree without affecting its AUC. The decision tree structure showed that lobulation was the most important feature, followed by spiculation, vessel convergence sign, nodule type, satellite nodule, nodule size and age of patient.

Conclusions

Our study shows that decision tree analyses can be applied to screen individuals for early lung cancer with CT. Our decision tree provides a new way to help clinicians establish a logical diagnosis by a stepwise progression method, but still needs to be validated for prospective trials in a larger patient population.

Using data mining techniques to fight and control epidemics: A scoping review

The main objective of this survey is to study the published articles to determine the most favorite data mining methods and gap of knowledge. Since the threat of pandemics has raised concerns for public health, data mining techniques were applied by researchers to reveal the hidden knowledge. Web of Science, Scopus, and PubMed databases were selected for systematic searches. Then, all of the retrieved articles were screened in the stepwise process according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses checklist to select appropriate articles. All of the results were analyzed and summarized based on some classifications. Out of 335 citations were retrieved, 50 articles were determined as eligible articles through a scoping review. The review results showed that the most favorite DM belonged to Natural language processing (22%) and the most commonly proposed approach was revealing disease characteristics (22%). Regarding diseases, the most addressed disease was COVID-19. The studies show a predominance of applying supervised learning techniques (90%). Concerning healthcare scopes, we found that infectious disease (36%) to be the most frequent, closely followed by epidemiology discipline. The most common software used in the studies was SPSS (22%) and R (20%). The results revealed that some valuable researches conducted by employing the capabilities of knowledge discovery methods to understand the unknown dimensions of diseases in pandemics. But most researches will need in terms of treatment and disease control.

Prevalence of Hepatitis A Immunity and Decision-tree Analysis Among Men Who Have Sex With Men and Are Living With Human Immunodeficiency Virus in Tokyo

BACKGROUND

Hepatitis A virus (HAV) can be sexually transmitted. However, the level of HAV immunity among patients living with human immunodeficiency virus (HIV) in Japan is unknown. Determining the epidemiology of HAV infections among men who have sex with men (MSM) and who are living with HIV is essential for an HAV vaccination program. This study examined HAV immunity in patients living with HIV and applied the decision-tree analysis to explore the factors of immunoglobulin G (IgG)-hepatitis A (HA) antibodies in MSM living with HIV.

METHODS

We examined the presence of IgG-HA antibodies among patients living with HIV from January to December 2017 in The Hospital of The Institute of Medical Science, The University of Tokyo. We recorded each patient's age, sex, mode of HIV transmission, year of HIV diagnosis, HAV vaccine status, history of HAV infection, and history of other infectious diseases. A decision-tree algorithm was used to reveal the factors and profiles most relevant to the anti-HAV prevalence.

RESULTS

Overall, 378 MSM patients living with HIV were examined for IgG-HA antibodies. After excluding 24 patients who had received a HAV vaccine, the data of 354 MSM were analyzed (median age 45 years, interquartile range 39-51 years). Of the 354 patients, 60 (16.9%) were positive for IgG-HA antibodies. The HA positivity rate increased with patients' age, and age (> 63.5 years) was extracted as the most important variable by classification of the decision-tree algorithm.

CONCLUSIONS

Our study, conducted just before the HAV outbreak among MSM in Tokyo, showed that age was the most relevant factor in anti-HAV prevalences. An extensive HAV vaccination program for MSM patients living with HIV is urgently needed, particularly for younger people.

Pharmacokinetic-pharmacodynamic modeling for Moutan Cortex/Moutan Cortex charcoal and the contributions of the chemical component using support vector regression with particle swarm optimization

Moutan Cortex (MC) and Moutan Cortex charcoal (MCC) are two kinds of Chinese medicinal materials widely used in traditional Chinese medicine (TCM) with opposite drug efficacy. And the contributions of the chemical component to the drug efficacy are still not clear. In our study, a support vector regression (SVR) model with particle swarm optimization (PSO) has been developed for simultaneously characterizing the pharmacokinetics (PK) and pharmacodynamics (PD) of MC/MCC. Then the contributions of the chemical component to the drug efficacy of MC/MCC are calculated by the weight analysis of SVR. The experimental results show that the effective substances found by the PSO-SVR model in MC and MCC are consistent with TCM theory. And the PSO-SVR model is a better model for PK-PD compared with the back-propagation neural network (BPNN). In conclusion, the PSO-SVR is a valuable tool that linked PK and PD profiles of MC/MCC with multiple components and identified the contributions of multiple therapeutic materials to the drug efficacy.

Prediction of Suicidal Ideation among Korean Adults Using Machine Learning: A Cross-Sectional Study

OBJECTIVE

Suicidal ideation (SI) precedes actual suicidal event. Thus, it is important for the prevention of suicide to screen the individuals with SI. This study aimed to identify the factors associated with SI and to build prediction models in Korean adults using machine learning methods.

METHODS

The 2010-2013 dataset of the Korea National Health and Nutritional Examination Survey was used as the training dataset (n=16,437), and the subset collected in 2015 was used as the testing dataset (n=3,788). Various machine learning algorithms were applied and compared to the conventional logistic regression (LR)-based model.

RESULTS

Common risk factors for SI included stress awareness, experience of continuous depressive mood, EQ-5D score, depressive disorder, household income, educational status, alcohol abuse, and unmet medical service needs. The prediction performances of the machine learning models, as measured by the area under receiver-operating curve, ranged from 0.794 to 0.877, some of which were better than that of the conventional LR model (0.867). The Bayesian network, LogitBoost with LR, and ANN models outperformed the conventional LR model.

CONCLUSION

A machine learning-based approach could provide better SI prediction performance compared to a conventional LR-based model. These may help primary care physicians to identify patients at risk of SI and will facilitate the early prevention of suicide.

Can Artificial Intelligence Improve the Management of Pneumonia

The use of artificial intelligence (AI) to support clinical medical decisions is a rather promising concept. There are two important factors that have driven these advances: the availability of data from electronic health records (EHR) and progress made in computational performance. These two concepts are interrelated with respect to complex mathematical functions such as machine learning (ML) or neural networks (NN). Indeed, some published articles have already demonstrated the potential of these approaches in medicine. When considering the diagnosis and management of pneumonia, the use of AI and chest X-ray (CXR) images primarily have been indicative of early diagnosis, prompt antimicrobial therapy, and ultimately, better prognosis. Coupled with this is the growing research involving empirical therapy and mortality prediction, too. Maximizing the power of NN, the majority of studies have reported high accuracy rates in their predictions. As AI can handle large amounts of data and execute mathematical functions such as machine learning and neural networks, AI can be revolutionary in supporting the clinical decision-making processes. In this review, we describe and discuss the most relevant studies of AI in pneumonia.

Imaging Examination and Quantitative Detection and Analysis of Gastrointestinal Diseases Based on Data Mining Technology

The medical image storage and transmission system completes the collection, storage, management, diagnosis and information processing of digital medical image information generated from digital medical devices, accumulates a large amount of data resources, and uses these valuable data resources to extract corresponding diseases. Diagnostic rules that help improve the accuracy of clinical disease diagnosis have always been the subject of medical research and management. Gastrointestinal diseases are common high-risk digestive diseases. This paper studies the imaging detection and quantitative detection and analysis of gastrointestinal diseases based on data mining, aiming to improve the accuracy of doctors' clinical diagnosis, reduce the misdiagnosis and misdiagnosis of patients' diseases, and reduce the burden on patients. With the high computing speed and computational accuracy of the computer, combined with the flexible analysis and judgment ability of the human body, the doctor can help the semi-structured and unstructured diagnosis problems. Experiments demonstrate the effectiveness and robustness of the proposed method.

[Construction of multi-parameter emergency database and preliminary application research]

The analysis of big data in medical field cannot be isolated from the high quality clinical database, and the construction of first aid database in our country is still in the early stage of exploration. This paper introduces the idea and key technology of the construction of multi-parameter first aid database. By combining emergency business flow with information flow, an emergency data integration model was designed with reference to the architecture of the Medical Information Mart for Intensive Care III (MIMIC-III), created by Computational Physiology Laboratory of Massachusetts Institute of Technology (MIT), and a high-quality first-aid database was built. The database currently covers 22 941 medical records for 19 814 different patients from May 2015 to October 2017, including relatively complete information on physiology, biochemistry, treatment, examination, nursing, etc. And based on the database, the first First-Aid Big Data Datathon event, which 13 teams from all over the country participated in, was launched. The First-Aid database provides a reference for the construction and application of clinical database in China. And it could provide powerful data support for scientific research, clinical decision making and the improvement of medical quality, which will further promote secondary analysis of clinical data in our country.

Optimization of Electronic Medical Records for Data Mining Using a Common Data Model

The increasing use of electronic health records (EHRs) in veterinary medicine creates an opportunity to utilize the high volume of electronic patient data for mining and data-driven analytics with the goal of improving patient care and outcomes. A central focus of the Clinical and Translational Science Award One Health Alliance (COHA) is to integrate efforts across multiple disciplines to better understand shared diseases in animals and people. The ability to combine veterinary and human medical data provides a unique resource to study the interactions and relationships between animals, humans, and the environment. However, to effectively answer these questions, veterinary EHR data must first be prepared in the same way it is now commonly being done in human medicine to enable data mining and development of analytics to facilitate knowledge formation and solutions that advance our understanding of disease processes, with the ultimate goal of improving outcomes for veterinary patients and their owners. As a first step, COHA member institutions implemented a Common Data Model to standardize EHR data. Herein we present the approach executed within the COHA framework to prepare and optimize veterinary EHRs for data mining and knowledge formation based on the adoption of the Observational Health Data Sciences and Informatics' Observational Medical Outcomes Partnership Common Data Model.

TRANSLATOR Database-A Vision for a Multi-Institutional Research Network

The formation of the CTSI One Health Alliance (COHA) network has generated the infrastructure necessary to support "Big Data" collaborative comparative and translational research in veterinary medicine. We describe the first step in the design, implementation, and dissemination of a collaborative information technology infrastructure that will serve the public and clinicians (COHA public/member based web site at https://ctsaonehealthalliance.org/) and its research focused COHA Research Workbench application. The core research infrastructure, TRANSLATOR (TRanslational ANimal Shared ColLAboraTive Observational Research), represents the foundation of a federated research-capable network to enable pooling large datasets from both electronic health records and publications. The public facing COHA website is a mechanism for both the dissemination of knowledge to the public and to foster collaborations amongst veterinary clinician scientists and the greater medical research community.

Predictive data mining for diagnosing periodontal disease: the Korea National Health and Nutrition Examination Surveys (KNHANES V and VI) from 2010 to 2015

OBJECTIVES

This study aimed to identify patients with the highest risk of periodontal disease (PD), and to provide recommendations for the effective use and application of data mining (DM) techniques when establishing evidence-based dental-care policies for vulnerable groups at a high risk of PD.

METHODS

This study used the SEMMA (Sample, Explore, Modify, Model, and Assess) methodology to construct DM models based on data acquired from the fifth and sixth Korea National Health and Nutrition Examination Surveys (2000-2015). We analyzed the sociodemographic and comorbidity variables that influence PD by applying the popular DM techniques of decision-tree, neural-network, and regression models, and also attempted to improve the predictive power and reliability by comparing the results obtained by these three models.

RESULTS

Our comparisons of the three DM algorithms confirmed that the average squared error, misclassification rate, receiver operating characteristic index, Gini coefficient, and Kolmogorov-Smirnov test results were the most appropriate for the decision-tree model. The analysis of the decision-tree model revealed that age and smoking status exert major effects on the risk of PD, and that stress and education level exert effects in rural areas, whereas education level, sex, hyperlipidemia, and alcohol intake exert effects in urban areas.

CONCLUSIONS

We demonstrated that the decision-tree model is an effective DM technique for identifying the complex risk factors for PD. These results are expected to be helpful in improving the equality and efficacy of dental-care policies for vulnerable groups at a high risk of PD.

Paving the way for precision medicine v2.0 in intensive care by profiling necroinflammation in biofluids

Current clinical diagnosis is typically based on a combination of approaches including clinical examination of the patient, clinical experience, physiologic and/or genetic parameters, high-tech diagnostic medical imaging, and an extended list of laboratory values mostly determined in biofluids such as blood and urine. One could consider this as precision medicine v1.0. However, recent advances in technology and better understanding of molecular mechanisms underlying disease will allow us to better characterize patients in the future. These improvements will enable us to distinguish patients who have similar clinical presentations but different cellular and molecular responses. Treatments will be able to be chosen more “precisely”, resulting in more appropriate therapy, precision medicine v2.0. In this review, we will reflect on the potential added value of recent advances in technology and a better molecular understanding of necrosis and inflammation for improving diagnosis and treatment of critically ill patients. We give a brief overview on the mutual interplay between necrosis and inflammation, which are two crucial detrimental factors in organ and/or systemic dysfunction. One of the challenges for the future will thus be the cellular and molecular profiling of necroinflammation in biofluids. The huge amount of data generated by profiling biomolecules and single cells through, for example, different omic-approaches is needed for data mining methods to allow patient-clustering and identify novel biomarkers. The real-time monitoring of biomarkers will allow continuous (re)evaluation of treatment strategies using machine learning models. Ultimately, we may be able to offer precision therapies specifically designed to target the molecular set-up of an individual patient, as has begun to be done in cancer therapeutics.

Critical care mostly implies life-threatening situations involving systemic infection, inflammation and necrosis. Biofluids are an easily accessible source of liquid biopsies that can be used to monitor the evolution of the patient’s critical illness. The cellular and molecular profiling of necrosis and inflammation in biofluids using cutting-edge technologies such as realtime immunodiagnostics, next-generation sequencing and mass spectrometry will pave the way for precision medicine v2.0 in critical care. This is needed for data mining approaches to allow patientclustering, identify novel biomarkers and develop novel intervention strategies controlling necrosis and inflammation. The real-time monitoring of biomarkers will allow continued (re)evaluation of treatment strategies using machine learning models.

Visualizing the knowledge structure and evolution of big data research in healthcare informatics

BACKGROUND

In recent years, the literature associated with healthcare big data has grown rapidly, but few studies have used bibliometrics and a visualization approach to conduct deep mining and reveal a panorama of the healthcare big data field.

METHODS

To explore the foundational knowledge and research hotspots of big data research in the field of healthcare informatics, this study conducted a series of bibliometric analyses on the related literature, including papers' production trends in the field and the trend of each paper's co-author number, the distribution of core institutions and countries, the core literature distribution, the related information of prolific authors and innovation paths in the field, a keyword co-occurrence analysis, and research hotspots and trends for the future.

RESULTS

By conducting a literature content analysis and structure analysis, we found the following: (a) In the early stage, researchers from the United States, the People's Republic of China, the United Kingdom, and Germany made the most contributions to the literature associated with healthcare big data research and the innovation path in this field. (b) The innovation path in healthcare big data consists of three stages: the disease early detection, diagnosis, treatment, and prognosis phase, the life and health promotion phase, and the nursing phase. (c) Research hotspots are mainly concentrated in three dimensions: the disease dimension (e.g., epidemiology, breast cancer, obesity, and diabetes), the technical dimension (e.g., data mining and machine learning), and the health service dimension (e.g., customized service and elderly nursing).

CONCLUSION

This study will provide scholars in the healthcare informatics community with panoramic knowledge of healthcare big data research, as well as research hotspots and future research directions.