Standard Medical Data Research Articles

Predicting Lifestyle-Related Diseases Early: The NNSVM Methodology

Chronic conditions including diabetes, heart disease, and hypertension are becoming major worldwide health issues, and a growing number of them are related to lifestyle decisions. Even though conventional medical statistics like blood pressure and glucose levels are significant markers, they only provide a portion of the picture. The key to early disease identification and prevention is frequently found in lifestyle choices, such as what we eat, how much exercise we get, and whether or not we smoke. In this work, we explore how machine learning might be used to anticipate these illnesses by including a person's everyday routines and behaviors in addition to reviewing medical records. In doing so, we developed a prediction model that is more accurate and comprehensive, revolutionizing the way we approach illness prevention in a society that is becoming more and more data-driven. The study develops a more thorough method of illness prediction by combining standard medical data with lifestyle habits. Algorithms like Support Vector Machine (SVM), Random Forest, Decision Trees, and Artificial Neural Networks (ANNs) are evaluated for their accuracy, precision, recall, and F1-score. According to the study's findings, lifestyle decisions have a significant impact on the development of chronic illnesses, and including them in disease prediction models increases the accuracy of those predictions overall. Combining many data sources is crucial for more accurate health outcomes, as the Random Forest model shows to be the most effective in forecasting diseases connected to lifestyle choices due to its capacity to manage intricate, non-linear interactions between variables. Early detection lowers the chance of serious health consequences by enabling prompt medical intervention, lifestyle modifications, and preventive measures. This strategy lowers healthcare expenses by reducing the need for costly follow-up therapies, while also improving patient outcomes.

IMPROVE THE EFFECTIVENESS OF PREDICTIVE MODELS FOR LENGTH OF HOSPITAL STAY (LOS) BY ADDING ELECTRONIC HEALTH RECORDS DATA: A RETROSPECTIVE STUDY IN PATIENTS WITH HEART FAILURE

Abstract Background Length of hospital stay (LOS) is considered a key process that has a clinical, economic, and organizational impact representative of the quality of care. In particular, in patients with heart failure (HF), which is a life–threatening multifactorial syndrome and a major public health problem, when a prolonged LOS (PLOS) occurs, frequent readmission and high mortality are common, with worrying consequences for health systems. Although the LOS is often explained by standard medical data (e.g., comorbidities), it may depend on many other patient characteristics. Therefore, considering additional elements collected in electronic health records (EHRs) could be crucial to predict the occurrence of a LOS and correctly estimating this risk. The aim of this study is to demonstrate the predictive power of clinical and organizational data collected through an EHR on LOS in HF patients. Methods A descriptive, retrospective study was conducted in an Italian university hospital. Data related to HF inpatients consecutively admitted across 1 year were collected from the hospital’s HER. PLOS was defined as a stay ≥ 14 days. Sociodemographic data, administrative data, and clinical data (such as the number of active medical problems, the number of medications, frailty, and nursing dependency), were tested in a predictive model as potential determinants of LOS. Results A total of 608 HF patients were included. The mean age of patients was 76 ± 13.06 years (range: 23–102); 61.5% were male. Prolonged LOS was found in 25.2% of patients. The univariable linear regression model explained 10.2% of LOS variance. Being female, living without social support, having an increased number of previous admissions and nursing dependency, being dependent on functional status, having a worse behavior pattern and mobility, and experiencing a sensory deficit were significant determinants (p < .05) of LOS. Conclusion The inclusion of EHRs data in addition to clinical variables, can help clinicians and researchers to improve the predictive ability on LOS, ensuring its early identification and ultimately enhancing the patients’ health outcomes through the implementation of targeted interventions.

Hybrid optimized temporal convolutional networks with long short-term memory for heart disease prediction with deep features

A heart attack is intended as top prevalent among all ruinous ailments. Day by day, the number of affected people count is increasing globally. The medical field is struggling to detect heart disease in the initial step. Early prediction can help patients to save their life. Thus, this paper implements a novel heart disease prediction model with the help of a hybrid deep learning strategy. The developed framework consists of various steps like (i) Data collection, (ii) Deep feature extraction, and (iii) Disease prediction. Initially, the standard medical data from various patients are acquired from the clinical standard datasets. Here, a One-Dimensional Convolutional Neural Network (1DCNN) is utilized for extracting the deep features from the acquired medical data to minimize the number of redundant data from the gathered large-scale data. The acquired deep features are directly fed to the Hybrid Optimized Deep Classifier (HODC) with the integration of Temporal Convolutional Networks (TCN) with Long Short-Term Memory (LSTM), where the parameters in both classifiers are optimized using the newly suggested Enhanced Forensic-Based Investigation (EFBI) inspired meta-optimization algorithm. Throughout the result analysis, the accuracy and precision rate of the offered approach is 98.67% and 99.48%. The evaluation outcomes show that the recommended system outperforms the extant systems in terms of performance metrics examination.

Predicting the Demand for Medical Care in Disaster-Affected Areas using the Minimum Data Set and Machine Learning

Background/Introduction:The Minimum Data Set (MDS) has allowed governments of disaster-affected countries to collect, examine, and evaluate standardized medical data from Emergency Medical Teams in real-time. However, little study has been conducted on the use of MDS data to predict health care needs.Objectives:This research proposes an outlook on the use of machine learning and MDS data to predict the need for medical care in disaster-affected areas.Method/Description:The characteristics of the data collected by MDS and the optimal machine learning model were discussed.Results/Outcomes:The primary causes of disease after disasters are trauma (MDS Nos. 4–8), which frequently occurs immediately after a disaster, and infectious diseases (MDS Nos. 9–18), which can increase due to decreasing hygiene conditions. Furthermore, certain infectious diseases can spread quickly because of living in congested evacuation centers, and early detection is crucial.Therefore, predicting the need for medical care in a disaster area is complicated and requires a combination of many machine-learning models. Data-driven methods are mostly linear approaches and cannot capture the dynamics of infectious disease transmission. Additionally, statistical models depend heavily on assumptions, making real-time infection prediction challenging. Thus, deep learning is employed to model without losing the temporal component.Conclusion:Real-time prediction of health care needs using machine learning and MDS can be useful to policymakers by enabling them to better deploy and allocate health care resources, which is useful to patients and front-line health care providers. More detailed predictions for regions and diseases are also anticipated.

Machine learning for classification of postoperative patient status using standardized medical data

Background and objective: Real-world evidence is defined as clinical evidence regarding the use and potential benefits or risks of a medical product derived from real-world data analyses. Standardization and structuring of data are necessary to analyze medical real-world data collected from different medical institutions. An electronic message and repository have been developed to link electronic medical records in this research project, which has simplified the data integration. Therefore, this paper proposes an analysis method and learning health systems to determine the priority of clinical intervention by clustering and visualizing time-series and prioritizing patient outcomes and status during hospitalization.Methods: Common data items for reimbursement (Diagnosis Procedure Combination [DPC]) and clinical pathway data were examined in this project at each participating institution that runs the verification test. Long-term hospitalization data were analyzed using the data stored in the cloud platform of the institutions’ repositories using multiple machine learning methods for classification, visualization, and interpretation.Results: The ePath platform contributed to integrate the standardized data from multiple institutions. The distribution of DPC items or variances could be confirmed by clustering, temporal tendency through the directed graph, and extracting variables that contributed to the prediction and evaluation of SHapley Additive Explanation effects. Constipation was determined to be the risk factor most strongly related to long-term hospitalization. Drainage management was identified as a factor that can improve long-term hospitalization. These analyses effectively extracted patient status to provide feedback to the learning health system.Conclusions: We successfully generated evidence of medical processes by gathering patient status, medical purposes, and patient outcomes with high data quality from multiple institutions, which were difficult with conventional electronic medical records. Regarding the significant analysis results, the learning health system will be used on this project to provide feedback to each institution, operate it for a certain period, and analyze and re-evaluate it.

Development of a General Statistical Analytical System Using Nationally Standardized Medical Information.

In Japan, since the Next Generation Medical Infrastructure Act regarding anonymized medical data contributing to R&D came into force in 2018, it is expected to exploit medical data for R&D. The Millennial Medical Record Project has been collected a large amount of standardized medical data of a number of hospitals stored in a database under the act. In order for users to widely exploit the medical data when carrying out trial-and-error, there is a difficulty of data access because of a highly secured management of non-anonymous medical data. To solve the data access problem, we develop a general statistical analytical system for executing a variety of statistical significance tests with statistical power analysis in an environment of trial-and-error for users' analyses without programming. In the analytical system, the front-end is a registration form as the input and the analysis results as the output on Microsoft Excel, and the back-end is based on Python, R and SQL. Although the fixed registration form covers limited application for the analysis, since the analysis results using the stored Millennial Medical Record data is provided in a short time without collecting the necessary data for the analysis, the exploitation of medical data could widely and rapidly promote by medical experts/researchers in the manner of trial-and-error. The developed system could apply to make protocols for clinical research and clinical trial, and the potential to discover real-world evidence could be increased.

Book review of artificial intelligence in medicine Edited by LeiXing, MaryellenGiger, and JamesMin

Book review of artificial intelligence in medicine Edited by LeiXing, MaryellenGiger, and JamesMin

Health Data Collection Before, During and After Emergencies and Disasters-The Result of the Kobe Expert Meeting.

In October 2018, the World Health Organization (WHO) convened a meeting to identify key research needs, bringing together leading experts from WHO, WHO Thematic Platform for Health Emergency and Disaster Risk Management (Health-EDRM) Research Network (TPRN), World Association for Disaster and Emergency Medicine (WADEM), the Japan International Cooperation Agency (JICA), and delegates to the Asia Pacific Conference for Disaster Medicine (APCDM) 2018. The meeting identified key research needs in five major research areas for Health-EDRM. One of the five major research areas was “Health data collection during emergency and disaster”. Experts for this research area highlighted WHO Emergency Medical Team Minimum Data Set (EMT MDS), a standardized medical data collection method during and after disasters, as an example of substantial progress, with knowledge gaps and challenges in implementation in some regions and countries (i.e., information collection methodology in medical facilities of affected local areas, seamless and practical connection between acute phase data collection and post-acute phase local surveillance). The discussion on this research area also identified key research needs in standardization of broader health-related data to inform effective Health EDRM (i.e., community vulnerabilities, hospital functional status, infrastructure, lifelines and health workforce).

Enhancing the performance of predictive models for Hospital mortality by adding nursing data

BackgroundMortality is the most considered outcome for assessing the quality of hospital care. However, hospital mortality depends on diverse patient characteristics; thus, complete risk stratification is crucial to correctly estimate a patient’s prognosis. Electronic health records include standard medical data; however, standard nursing data, such as nursing diagnoses (which were considered essential for a complete picture of the patient condition) are seldom included. ObjectiveTo explore the independent predictive power of nursing diagnoses on patient hospital mortality and to investigate whether the inclusion of this variable in addition to medical diagnostic data can enhance the performance of risk adjustment tools. MethodsProspective observational study in one Italian university hospital. Data were collected for six months from a clinical nursing information system and the hospital discharge register. The number of nursing diagnoses identified by nurses within 24 h after admission was used to express the nursing dependency index (NDI). Eight logistic regression models were tested to predict patient mortality, by adding to a first basic model considering patient’s age, sex, and modality of hospital admission, the level of comorbidity (CCI), and the nursing and medical condition as expressed by the NDI and the All Patient Refined-Diagnosis Related Group weight (APR-DRGw), respectively. ResultsOverall, 2301 patients were included. The addition of the NDI to the model increased the explained variance by 20%. The explained variance increased by 56% when the APR-DRGw, CCI, and NDI were included. Thus, the latter model was nearly highly accurate (c = 0.89, 95% confidence interval: 0.87–0.92). ConclusionNursing diagnoses have an independent power in predicting hospital mortality. The explained variance in the predictive models improved when nursing data were included in addition to medical data. These findings strengthen the need to include standardized nursing data in electronic health records.

A rule-based semantic approach for data integration, standardization and dimensionality reduction utilizing the UMLS: Application to predicting bariatric surgery outcomes

Utilization of existing clinical data for improving patient outcomes poses a number of challenging and complex problems involving lack of data integration, the absence of standardization across inhomogeneous data sources and computationally-demanding and time-consuming exploration of very large datasets. In this paper, we will present a robust semantic data integration, standardization and dimensionality reduction method to tackle and solve these problems. Our approach enables the integration of clinical data from diverse sources by resolving canonical inconsistencies and semantic heterogeneity as required by the National Library of Medicine's Unified Medical Language System (UMLS) to produce standardized medical data. Through a combined application of rule-based semantic networks and machine learning, our approach enables a large reduction in dimensionality of the data and thus allows for fast and efficient application of data mining techniques to large clinical datasets. An example application of the techniques developed in our study is presented for the prediction of bariatric surgery outcomes.

Conversion between 2 military combat-related injury coding systems.

Deployable medical systems(DEPMEDS) patient conditions (PCs) and Military Combat Injury Scale (MCIS) are 2 important military medical coding systems. However, both of them have defects when applied in military medical planning. Although each PC code contains information about treatment, intensity of care, treatment time, length of stay, and probability of disposition that is relevant to simulation, its description is too comprehensive and ambiguous to code historical military medical records. Therefore, conversion between PC and other medical coding systems applied in standard medical data is required when validity is required following simulation. The information linked to each PC code is based on subject matter expert opinion instead of standard medical data from the theater that need to be continuously updated depending on the results of medical data analysis. MCIS, a combat-related injury coding system, shows significant promise in coding real medical data, but it does not seek detailed information important for prediction and simulation unlike PCs. Therefore, MCIS cannot be used in planning tools directly. Thus, the effort to map MCIS to PCs is significant for medical logistic planning. We aim to identify whether conversion between PCs and MCIS is possible and to evaluate inter-coder reliability.Three senior coders assigned all possible MCIS codes to 187 combat-related PC codes. The data records were structured based on an earlier study. Inter-rater reliability was measured by using Cohen's k statistic and percent agreement.Low inter-rater reliability indicated the difficulty in conversion between PCs and MCIS.The injury descriptors of PCs should be expanded by referring to new standard medical data. The existing MCIS codes need to be modified to include more information on treatment brief, treatment time, length of stay, and other key information, and historical data statistics need to be developed.

Analyse microbiologique de plus de 600 infections urinaires fébriles prises en charge dans un réseau de soin

Community-acquired febrile urinary tract infections (UTI) in adult has received little attention in the literature. The objective of our study was to determinate the distribution of bacterial strains isolated from adults with community-acquired febrile UTI and antibiotic susceptibility patterns of Escherichia coli. We studied the SPHERES's databank. SPHERES is a Parisian medical community network aimed at securing and facilitating the ambulatory management of potentially serious acute illnesses. Each patient is included in the network according to specific clinical criteria and standardized medical data are recorded. We retrospectively studied the medical records of all patients treated for a pyelonephritis or a prostatitis between April 2005 and October 2008. Five hundred and sixty-eight patients were enrolled: 410 women and 158 men. The overall bacteria's distribution was similar to that observed in previous strictly microbiological studies with a more prominent role of E. coli (87.5%) to the detriment of other species. The overall susceptibility of E. coli to antibiotics recommended in the empiric treatment of pyelonephritis and prostatitis was preserved: ciprofloxacin (95.8%), cefotaxime (98%), gentamicin (99.4%). In women over 65 years, the susceptibility of E. coli to systemic fluoroquinolones fell up 89.7%. This could affect the empiric oral treatment of pyelonephritis in older women. We report the bacterial distribution and the resistance pattern of bacteria implicated in febrile urinary infections diagnosed and treated in a health network. It seems that E. coli resistance increased more in women more than 65 years than in men.

A database medical diagnostic support system using standardized medical data: a pilot study

In the past two decades a wide variety of information systems have been developed to facilitate medical diagnosis, better known as medical expert systems. These systems can be divided into several methodological categories, one of which is the database approach. A problem with this approach is the difficulty in filling the knowledge base directly from the source text because of complexities of natural language. This paper discusses the development of a computer-aided medical di agnostic system using standardized symptom codes as its input. based upon the results of a comprehensive questionnaire that is filled out by the patient. Subsequently, the patient's potential disease is predicted by linking symptoms with most likely diseases. The methodology of the system is discussed and a few examples are presented, as well as directions for further devel opment of this approach to medical information processing and decision making.