Utilizing Home Healthcare Electronic Health Records for Telehomecare Patients With Heart Failure: A Decision Tree Approach to Detect Associations With Rehospitalizations

Artificial Intelligence in the Intensive Care Unit: Current Evidence on an Inevitable Future Tool

Artificial intelligence (AI) is a technique that attempts to replicate human intelligence, analytical behavior, and decision-making ability. This includes machine learning, which involves the use of algorithms and statistical techniques to enhance the computer's ability to make decisions more accurately. Due to AI's ability to analyze, comprehend, and interpret considerable volumes of data, it has been increasingly used in the field of healthcare. In critical care medicine, where most of the patient load requires timely interventions due to the perilous nature of the condition, AI's ability to monitor, analyze, and predict unfavorable outcomes is an invaluable asset. It can significantly improve timely interventions and prevent unfavorable outcomes, which, otherwise, is not always achievable owing to the constrained human ability to multitask with optimum efficiency. AI has been implicated in intensive care units over the past many years. In addition to its advantageous applications, this article discusses its disadvantages, prospects, and the changes needed to train future critical care professionals. A comprehensive search of electronic databases was performed using relevant keywords. Data from articles pertinent to the topic was assimilated into this review article.

The Efficacy of Machine Learning Models for Predicting the Prognosis of Heart Failure: A Systematic Review and Meta-Analysis

INTRODUCTION

Heart failure (HF) is a major global public health concern. The application of machine learning (ML) to identify individuals at high risk and enable early intervention is a promising approach for improving HF prognosis. We aim to systematically evaluate the performance and value of ML models for predicting HF prognosis.

METHODS

PubMed, Web of Science, Scopus, and Embase online databases were searched up to April 30, 2023, to identify studies on the use of ML models to predict HF prognosis. HF prognosis primarily encompasses readmission and mortality. The meta-analysis was conducted by MedCalc software. Subgroup analyses include grouping based on types of ML models, time intervals, sample sizes, the number of predictive variables, validation methods, whether to conduct hyperparameter optimization and calibration, data set partitioning methods.

RESULTS

A total of 31 studies were included. The most common ML models were random forest, boosting, support vector machine, neural network. The area under the receiver operating characteristic curve (AUC) for predicting HF readmission was 0.675 (95% CI: 0.651-0.699, p < 0.001), and the AUC for predicting HF mortality was 0.790 (95% CI: 0.765-0.816, p < 0.001). Subgroup analyses revealed that models with the prediction time interval of 1 year, sample sizes ≥10,000, the number of predictive variables ≥100, external validation, hyperparameter tuning, calibration adjustment, and data set partitioning using 10-fold cross-validation exhibited favorable performance within their respective subgroups.

CONCLUSION

The performance of ML models in predicting HF readmission is relatively poor, while its performance in predicting HF mortality is moderate. The quality of the relevant studies is generally low, it is essential to enhance the predictive capabilities of ML models through targeted improvements in practical applications.

Developing 60-Day Readmission Risk Score among Home Healthcare Patients with Heart Failure

Heart failure (HF) readmissions are common, costly, and often preventable. Despite the implementation of HF programs across clinical settings, rehospitalization is still common. Efforts to identify risk factors for 60-day rehospitalization among HF patients exist, but risk scoring has not been utilized in home healthcare. The purpose of this study was to develop a 60-day rehospitalization risk score for home care patients with HF. This study is a secondary data analysis of a retrospective cross-sectional dataset that was composed of data using the Outcome Assessment Information Set (OASIS)-C version for patients with HF. We computed the Charlson Comorbidity Index (CCI) to use as a confounder. The risk score was computed from the final logistic regression model regression coefficients. The median age was 78 years old, 45.4% were male, and 81.0% were White. We identified 10 significant risk factors including CCI score. The risk score achieved a c-statistic of 0.70 in this patient sample. This risk score could prove useful in clinical practice for guiding attention and decision-making for personalized care of patients with unrecognized or under-treated health needs.

Prediction model of quality of life using the decision tree model in older adult single-person households: a secondary data analysis

Background

Attention is drawn to the subjective health status and quality of life of older adult single-person households, whose number is gradually increasing as factors including low fertility, increased life expectancy, aging, and household miniaturization interact.

Objective

The study was to identify predictors that affect the quality of life of single-person households aged 65 years or older and living in South Korea.

Methods

A secondary data analysis design was used. Data included physical, mental, social, and demographic characteristics, subjective health status, and quality of life parameters of 1,029 older adult single-person households surveyed by the Korea Health Panel in 2019. For analysis, the predictive model was evaluated using split-sample validation and the ROC curve. The area under the curve after the decision tree analysis was calculated. Final nodes predicting the quality of life of older adult single-person households were derived.

Results

Significant predictors were identified in this order: subjective health status, chronic disease, income, and age. Subjective health status was the most important factor influencing quality of life (△ p < 0.001, x2 = 151.774). The first combination that perceived high quality of life of older adult single-person households was the case of high subjective health status and no chronic disease, followed by the case of high subjective health status, presence of chronic disease, and high income.

Conclusion

This study confirmed that subjective health status and chronic disease are essential factors for quality of life among the four related indicators of quality of life presented by the OECD. In nursing practice, nurses need to pay attention the factors influencing quality of life of older adult single-person households. Especially, nursing practice for older adult single-person households needs to be focused on improving subjective health status and on relieving chronic disease.

Machine learning decision tree models for multiclass classification of common malignant brain tumors using perfusion and spectroscopy MRI data

Background

To investigate the contribution of machine learning decision tree models applied to perfusion and spectroscopy MRI for multiclass classification of lymphomas, glioblastomas, and metastases, and then to bring out the underlying key pathophysiological processes involved in the hierarchization of the decision-making algorithms of the models.

Methods

From 2013 to 2020, 180 consecutive patients with histopathologically proved lymphomas (n = 77), glioblastomas (n = 45), and metastases (n = 58) were included in machine learning analysis after undergoing MRI. The perfusion parameters (rCBVmax, PSRmax) and spectroscopic concentration ratios (lac/Cr, Cho/NAA, Cho/Cr, and lip/Cr) were applied to construct Classification and Regression Tree (CART) models for multiclass classification of these brain tumors. A 5-fold random cross validation was performed on the dataset.

Results

The decision tree model thus constructed successfully classified all 3 tumor types with a performance (AUC) of 0.98 for PCNSLs, 0.98 for GBM and 1.00 for METs. The model accuracy was 0.96 with a RSquare of 0.887. Five rules of classifier combinations were extracted with a predicted probability from 0.907 to 0.989 for that end nodes of the decision tree for tumor multiclass classification. In hierarchical order of importance, the root node (Cho/NAA) in the decision tree algorithm was primarily based on the proliferative, infiltrative, and neuronal destructive characteristics of the tumor, the internal node (PSRmax), on tumor tissue capillary permeability characteristics, and the end node (Lac/Cr or Cho/Cr), on tumor energy glycolytic (Warburg effect), or on membrane lipid tumor metabolism.

Conclusion

Our study shows potential implementation of machine learning decision tree model algorithms based on a hierarchical, convenient, and personalized use of perfusion and spectroscopy MRI data for multiclass classification of these brain tumors.

Evaluating the comparability of patient-level social risk data extracted from electronic health records: A systematic scoping review

Objective: To evaluate how and from where social risk data are extracted from EHRs for research purposes, and how observed differences may impact study generalizability. Methods: Systematic scoping review of peer-reviewed literature that used patient-level EHR data to assess 1 ± 6 social risk domains: housing, transportation, food, utilities, safety, social support/isolation. Results: 111/9022 identified articles met inclusion criteria. By domain, social support/isolation was most often included (N = 68/111), predominantly defined by marital/partner status (N = 48/68) and extracted from structured sociodemographic data (N = 45/48). Housing risk was defined primarily by homelessness (N = 39/49). Structured housing data was extracted most from billing codes and screening tools (N = 15/30, 13/30, respectively). Across domains, data were predominantly sourced from structured fields (N = 89/111) versus unstructured free text (N = 32/111). Conclusion: We identified wide variability in how social domains are defined and extracted from EHRs for research. More consistency, particularly in how domains are operationalized, would enable greater insights across studies.

Identifying unmet needs of older adults transitioning from home health care to independence at home: A qualitative study

Health care practices to prepare older adults and their family caregivers for transitions from home health care (HHC) to independence at home are rarely studied. The objective of this multiple case study was to describe HHC patient and clinician perceptions of unmet needs after HHC discharge and recommendations to address them in future research. In this qualitative study, data were collected using chart-reviews and semi-structured interviews with paired patients (or caregivers as proxy) and HHC clinicians (N=17 pairs). We identified three themes: (1) low patient and caregiver engagement in care planning increased risk for preventable health events after HHC discharge, (2) limited continuity of care restricted patient and caregiver access to community-based services, and (3) gaps in patient and caregiver education influenced independent care of chronic illnesses after discharge. Findings suggest opportunities to improve care practices to prepare older adults and their caregivers for transitions from HHC to independence at home.

Machine learning applied to electronic health record data in home healthcare: A scoping review

OBJECTIVE

Despite recent calls for home healthcare (HHC) to integrate informatics, the application of machine learning in HHC is relatively unknown. Thus, this study aimed to synthesize and appraise the literature describing the application of machine learning to predict adverse outcomes (e.g., hospitalization, mortality) using electronic health record (EHR) data in the HHC setting. Our secondary aim was to evaluate the comprehensiveness of predictors used in the machine learning algorithms guided by the Biopsychosocial Model.

METHODS

During March 2022 we conducted a literature search in four databases: PubMed, Embase, CINAHL, and Scopus. Inclusion criteria were 1) describing services provided in the HHC setting, 2) applying machine learning algorithms to predict adverse outcomes, defined as outcomes related to patient deterioration, 3) using EHR data and 4) focusing on the adult population. Predictors were mapped to the Biopsychosocial Model. A risk of bias analysis was conducted using the Prediction Model Risk Of Bias Assessment Tool.

RESULTS

The final sample included 20 studies. Eighteen studies used predictors from standardized assessments integrated in the EHR. The most common outcome of interest was hospitalization (55%), followed by mortality (25%). Psychological predictors were frequently excluded (35%). Tree based algorithms were most frequently applied (75%). Most studies demonstrated high or unclear risk of bias (75%).

CONCLUSION

Future studies in HHC should consider incorporating machine learning algorithms into clinical decision support systems to identify patients at risk. Based on the Biopsychosocial model, psychological and interpersonal characteristics should be used along with biological characteristics to enhance risk prediction. To facilitate the widespread adoption of machine learning, stakeholders should encourage standardization in the HHC setting.

Modern Approaches for the Treatment of Heart Failure: Recent Advances and Future Perspectives

Heart failure (HF) is a progressively deteriorating medical condition that significantly reduces both the patients’ life expectancy and quality of life. Even though real progress was made in the past decades in the discovery of novel pharmacological treatments for HF, the prevention of premature deaths has only been marginally alleviated. Despite the availability of a plethora of pharmaceutical approaches, proper management of HF is still challenging. Thus, a myriad of experimental and clinical studies focusing on the discovery of new and provocative underlying mechanisms of HF physiopathology pave the way for the development of novel HF therapeutic approaches. Furthermore, recent technological advances made possible the development of various interventional techniques and device-based approaches for the treatment of HF. Since many of these modern approaches interfere with various well-known pathological mechanisms in HF, they have a real ability to complement and or increase the efficiency of existing medications and thus improve the prognosis and survival rate of HF patients. Their promising and encouraging results reported to date compel the extension of heart failure treatment beyond the classical view. The aim of this review was to summarize modern approaches, new perspectives, and future directions for the treatment of HF.

Artificial Intelligence in Cardiovascular Medicine: Current Insights and Future Prospects

Cardiovascular disease (CVD) represents a significant and increasing burden on healthcare systems. Artificial intelligence (AI) is a rapidly evolving transdisciplinary field employing machine learning (ML) techniques, which aim to simulate human intuition to offer cost-effective and scalable solutions to better manage CVD. ML algorithms are increasingly being developed and applied in various facets of cardiovascular medicine, including and not limited to heart failure, electrophysiology, valvular heart disease and coronary artery disease. Within heart failure, AI algorithms can augment diagnostic capabilities and clinical decision-making through automated cardiac measurements. Occult cardiac disease is increasingly being identified using ML from diagnostic data. Improved diagnostic and prognostic capabilities using ML algorithms are enhancing clinical care of patients with valvular heart disease and coronary artery disease. The growth of AI techniques is not without inherent challenges, most important of which is the need for greater external validation through multicenter, prospective clinical trials.

The Utility of Nursing Notes Among Medicare Patients With Heart Failure to Predict 30-Day Rehospitalization: A Pilot Study

BACKGROUND

For patients with heart failure (HF), there have been efforts to reduce the risk of 30-day rehospitalization, such as developing predictive models using electronic health records. Few previous studies used clinical notes to predict 30-day rehospitalization.

OBJECTIVE

The aim of this study was to assess the utility of nursing notes versus discharge summaries to predict 30-day rehospitalization among patients with HF.

METHODS

In this pilot study, we used free-text discharge summaries and nursing notes collected from a tertiary hospital. We randomly selected 500 Medicare patients with HF. We followed the natural language processing and machine learning pipeline for data analysis.

RESULTS

Thirty-day rehospitalization risk prediction using discharge summaries (n = 500) produced an area under the receiver operating characteristic curve of 0.74 (Bag of Words + Neural Network). Thirty-day rehospitalization risk prediction using nursing notes (n = 2046) resulted in an area under the receiver operating characteristic curve of 0.85 (Bag of Words + Neural Network).

CONCLUSION

Nursing notes provide a superior input to risk models for 30-day rehospitalization in Medicare patients with HF compared with discharge summaries.

Mobility and Self-Care are Associated With Discharge to Community After Home Health for People With Dementia

OBJECTIVES

A priority health outcome for patients, families, and the Centers for Medicare & Medicaid Services (CMS) is a patient's ability to return home and remain in the community without adverse events following discharge from post-acute care services. Successful discharge to community (DTC) is defined as being discharged to the community and not experiencing a readmission or death within 30 days of discharge. The objective of this study was to determine the association between patient factors and successful DTC after home health for individuals with Alzheimer's disease and related dementias (ADRD).

DESIGN

This retrospective study derived data from 100% national CMS data files from October 1, 2016, through September 30, 2017.

SETTINGS AND PARTICIPANTS

Criteria from the Home Health Quality Reporting program were used to identify a cohort of 790,439 Medicare home health beneficiaries, 143,164 (18.0%) with ADRD.

MEASURES

Successful DTC rates with associated 95% confidence intervals (CIs) were calculated for each patient characteristic. Multilevel logistic regression was used to estimate the relative risk (RR) of successful DTC after home health, by ADRD diagnosis, mobility, self-care, caregiver support, and medication management, adjusted for patient demographics and clinical characteristics.

RESULTS

Overall, 79.4% of beneficiaries had a successful DTC. Beneficiaries with ADRD had a significantly lower odds of successful DTC than those without ADRD (RR=0.947, 95% CI=0.944-0.950). This association remained significant after adjustment for caregiver support, assistance with medications, independence in mobility, and level of self-care. Greater need for caregiver support, greater need for assistance with medications, greater dependence in mobility, and greater self-care dependence were all associated with decreased risk of successful DTC.

CONCLUSIONS AND IMPLICATIONS

Older adults with ADRD receiving home health had decreased RR of successful DTC. To have a successful DTC, older adults with ADRD need sufficient support from caregivers and independence in functioning.

Application of machine learning in predicting hospital readmissions: a scoping review of the literature

Background

Advances in machine learning (ML) provide great opportunities in the prediction of hospital readmission. This review synthesizes the literature on ML methods and their performance for predicting hospital readmission in the US.

Methods

This review was performed according to the Preferred Reporting Items for Systematic Reviews and Meta-Analysis Extension for Scoping Reviews (PRISMA-ScR) Statement. The extraction of items was also guided by the Critical Appraisal and Data Extraction for Systematic Reviews of Prediction Modelling Studies (CHARMS). Electronic databases PUBMED, MEDLINE, and EMBASE were systematically searched from January 1, 2015, through December 10, 2019. The articles were imported into COVIDENCE online software for title/abstract screening and full-text eligibility. Observational studies using ML techniques for hospital readmissions among US patients were eligible for inclusion. Articles without a full text available in the English language were excluded. A qualitative synthesis included study characteristics, ML algorithms utilized, and model validation, and quantitative analysis assessed model performance. Model performances in terms of Area Under the Curve (AUC) were analyzed using R software. Quality in Prognosis Studies (QUIPS) tool was used to assess the quality of the reviewed studies.

Results

Of 522 citations reviewed, 43 studies met the inclusion criteria. A majority of the studies used electronic health records (24, 56%), followed by population-based data sources (15, 35%) and administrative claims data (4, 9%). The most common algorithms were tree-based methods (23, 53%), neural network (NN) (14, 33%), regularized logistic regression (12, 28%), and support vector machine (SVM) (10, 23%). Most of these studies (37, 85%) were of high quality. A majority of these studies (28, 65%) reported ML algorithms with an AUC above 0.70. There was a range of variability within AUC reported by these studies with a median of 0.68 (IQR: 0.64–0.76; range: 0.50–0.90).

Conclusions

The ML algorithms involving tree-based methods, NN, regularized logistic regression, and SVM are commonly used to predict hospital readmission in the US. Further research is needed to compare the performance of ML algorithms for hospital readmission prediction.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12874-021-01284-z.

Identifying Targets to Improve Heart Failure Outcomes for Patients Receiving Home Healthcare Services: The Relationship of Functional Status and Pain

Heart failure (HF) is one of the leading causes of rehospitalization in the United States. Due to the complex nature of HF, the provision of Medicare-certified home healthcare services has increased. Medicare-certified home healthcare agencies measure and report patients' outcomes such as functional status, activities of daily living (ADL), and instrumental activities of daily living to the Centers for Medicare and Medicaid Services. These metrics are assessed using the Outcome and Assessment Information Set (OASIS). As a large data set, OASIS has been used to advance care quality in multiple ways including identifying risk factors for negative patient outcomes. However, there is a lack of OASIS analyses to assess the relationship between functional status and the role of other factors, such as pain, in impeding recovery after hospitalization among HF patients. Therefore, the purpose of this study is to identify the relationship between functional status and pain using the OASIS database. Among 489 HF patients admitted to home healthcare, 83% were White, 57% were female, and the median age was 80. Patients who reported daily but not constant activity-interfering pain at discharge demonstrated the least improvement in functional performance as measured by ADLs, whereas patients without activity-interfering pain demonstrated the greatest improvement in ADL performance (p value = 0.0284). Tracking individual patient ADL scores, particularly the frequency of activity-interfering pain, could be a key indicator for clinical focus for patients with HF in the home healthcare setting.

Function and Caregiver Support Associated With Readmissions During Home Health for Individuals With Dementia

OBJECTIVE

The purpose of this study was to determine the association between mobility, self-care, cognition, and caregiver support and 30-day potentially preventable readmissions (PPR) for individuals with dementia.

DESIGN

This retrospective study derived data from 100% national Centers for Medicare and Medicaid Services data files from July 1, 2013, through June 1, 2015.

PARTICIPANTS

Criteria from the Home Health Claims-Based Rehospitalization Measure and the Potentially Preventable 30-Day Post Discharge Readmission Measure for the Home Health Quality Reporting Program were used to identify a cohort of 118,171 Medicare beneficiaries.

MAIN OUTCOME MEASURE

The 30-day PPR rates with associated 95% CIs were calculated for each patient characteristic. Multilevel logistic regression was used to study the relationship between mobility, self-care, caregiver support, and cognition domains and 30-day PPR during home health, adjusting for patient demographics and clinical characteristics.

RESULTS

The overall rate of 30-day PPR was 7.6%. In the fully adjusted models, patients who were most dependent in mobility (odds ratio [OR], 1.59; 95% CI, 1.47-1.71) and self-care (OR, 1.73; 95% CI, 1.61-1.87) had higher odds for 30-day PPR. Patients with unmet caregiving needs had 1.11 (95% CI, 1.05-1.17) higher odds for 30-day PPR than patients whose caregiving needs were met. Patients with cognitive impairment had 1.23 (95% CI, 1.16-1.30) higher odds of readmission than those with minimal to no cognitive impairment.

CONCLUSIONS

Decreased independence in mobility and self-care tasks, unmet caregiver needs, and impaired cognitive processing at admission to home health are associated with risk of 30-day PPR during home health for individuals with dementia. Our findings indicate that deficits in mobility and self-care tasks have the greatest effect on the risk for PPR.

A decision tree model of cerebral palsy based on risk factors

Objective: A risk prediction model of cerebral palsy (CP) was established by a decision tree model to predict the individual risk of CP.Methods: A hospital-based case-control study was conducted with 109 cases of CP and 327 controls without CP. The cases and the controls were obtained from Hunan Children's Hospital. A questionnaire was administered to collect the variables relevant to CP by face to face interviews. Chi-square test was used to identify the factors associated with CP, and a decision tree model was used to construct the prediction model.Results: Univariate analysis showed that there were significant differences between cases group and controls group on maternal age, weight gain during pregnancy, medical treatment during pregnancy, preterm birth, low birth weight and birth asphyxia (all p-values <.05). Three factors, including preterm birth, birth asphyxia, and maternal age >35 years old, entered the decision tree model. The area under the receiver operating characteristic curve (AUC) was 0.722 (95%CI: 0.659-0.784, p < .001).Conclusion: The decision tree prediction model can be used for predicting the individual risk of CP. Further large-scale, population-based cerebral palsy studies are needed to improve the model.

The Future of Data-Driven Wound Care

Care for patients with chronic wounds can be complex, and the chances of poor outcomes are high if wound care is not optimized through evidence-based protocols. Tracking and managing every variable and comorbidity in patients with wounds is difficult despite the increasing use of wound-specific electronic medical records. Harnessing the power of big data analytics to help nurses and physicians provide optimized care based on the care provided to millions of patients can result in better outcomes. Numerous applications of machine learning toward workflow improvements, inpatient monitoring, outpatient communication, and hospital operations can improve overall efficiency and efficacy of care delivery in and out of the hospital, while reducing adverse events and complications. This article provides an overview of the application of big data analytics and machine learning in health care, highlights important recent advances, and discusses how these technologies may revolutionize advanced wound care.

Hospitalization risk factors of older cohorts of home health care patients: A systematic review

Nearly one million Medicare home health care beneficiaries are hospitalized annually of which one-quarter are considered preventable. Older hospitalized patients are at risk for nosocomial complications and poorer outcomes and incur higher health care costs. This paper reports the results of a systematic review of 28 studies on hospitalization risk factors of older home health care patients. It found that males, Blacks, and non-Asian minorities are at greater hospitalization risk. Factors associated with higher risk included skin ulcers, psychiatric conditions, dyspnea/COPD, cardiovascular conditions, diabetes, functional deficits, more comorbidities, and higher medication usage. These findings can inform practice, research, and policy.

Patient factors associated with the initiation of telehealth services among heart failure patients at home

Telehealth is an intervention that can assist patients with heart failure to manage their symptoms at home. However, it is reported that between 24-70% of eligible patients do not receive telehealth. This study aimed to explore factors associated with the initiation of telehealth among home care patients with heart failure using the Outcome and Assessment Information Set data (N = 2,832). The findings indicate patients who received high-risk drugs education by visiting nurses had an 80% increase in the odds of receiving telehealth, and patients who received no assistance from caregivers had a 46% decrease in odds compared to those who were assisted at least daily.

Mining telemonitored physiological data and patient-reported outcomes of congestive heart failure patients

This paper addresses patient-reported outcomes (PROs) and telemonitoring in congestive heart failure (CHF), both increasingly important topics. The interest in CHF trials is shifting from hard end-points such as hospitalization and mortality, to softer end-points such health-related quality of life. However, the relation of these softer end-points to objective parameters is not well studied. Telemonitoring is suitable for collecting both patient-reported outcomes and objective parameters. Most telemonitoring studies, however, do not take full advantage of the available sensor technology and intelligent data analysis. The Chiron clinical observational study was performed among 24 CHF patients (17 men and 7 women, age 62.9 ± 9.4 years, 15 NYHA class II and 9 class III, 10 of ishaemic, aetiology, 6 dilated, 2 valvular, and 6 of multiple aetiologies or cardiomyopathy) in Italy and UK. A large number of physiological and ambient parameters were collected by wearable and other devices, together with PROs describing how well the patients felt, over 1,086 days of observation. The resulting data were mined for relations between the objective parameters and the PROs. The objective parameters (humidity, ambient temperature, blood pressure, SpO2, and sweeting intensity) could predict the PROs with accuracies up to 86% and AUC up to 0.83, making this the first report providing evidence for ambient and physiological parameters to be objectively related to PROs in CHF patients. We also analyzed the relations in the predictive models, gaining some insights into what affects the feeling of health, which was also generally not attempted in previous investigations. The paper strongly points to the possibility of using PROs as primary end-points in future trials.

Applying of Decision Tree Analysis to Risk Factors Associated with Pressure Ulcers in Long-Term Care Facilities

OBJECTIVES

The purpose of this study was to use decision tree analysis to explore the factors associated with pressure ulcers (PUs) among elderly people admitted to Korean long-term care facilities.

METHODS

The data were extracted from the 2014 National Inpatient Sample (NIS)-data of Health Insurance Review and Assessment Service (HIRA). A MapReduce-based program was implemented to join and filter 5 tables of the NIS. The outcome predicted by the decision tree model was the prevalence of PUs as defined by the Korean Standard Classification of Disease-7 (KCD-7; code L89^*). Using R 3.3.1, a decision tree was generated with the finalized 15,856 cases and 830 variables.

RESULTS

The decision tree displayed 15 subgroups with 8 variables showing 0.804 accuracy, 0.820 sensitivity, and 0.787 specificity. The most significant primary predictor of PUs was length of stay less than 0.5 day. Other predictors were the presence of an infectious wound dressing, followed by having diagnoses numbering less than 3.5 and the presence of a simple dressing. Among diagnoses, "injuries to the hip and thigh" was the top predictor ranking 5th overall. Total hospital cost exceeding 2,200,000 Korean won (US $2,000) rounded out the top 7.

CONCLUSIONS

These results support previous studies that showed length of stay, comorbidity, and total hospital cost were associated with PUs. Moreover, wound dressings were commonly used to treat PUs. They also show that machine learning, such as a decision tree, could effectively predict PUs using big data.

Heart Failure: Diagnosis, Severity Estimation and Prediction of Adverse Events Through Machine Learning Techniques

Heart failure is a serious condition with high prevalence (about 2% in the adult population in developed countries, and more than 8% in patients older than 75 years). About 3-5% of hospital admissions are linked with heart failure incidents. Heart failure is the first cause of admission by healthcare professionals in their clinical practice. The costs are very high, reaching up to 2% of the total health costs in the developed countries. Building an effective disease management strategy requires analysis of large amount of data, early detection of the disease, assessment of the severity and early prediction of adverse events. This will inhibit the progression of the disease, will improve the quality of life of the patients and will reduce the associated medical costs. Toward this direction machine learning techniques have been employed. The aim of this paper is to present the state-of-the-art of the machine learning methodologies applied for the assessment of heart failure. More specifically, models predicting the presence, estimating the subtype, assessing the severity of heart failure and predicting the presence of adverse events, such as destabilizations, re-hospitalizations, and mortality are presented. According to the authors' knowledge, it is the first time that such a comprehensive review, focusing on all aspects of the management of heart failure, is presented.