Predicting hospital length of stay using machine learning on a large open health dataset.

BACKGROUND: Governments worldwide are facing growing pressure to increase transparency, as citizens demand greater insight into decision-making processes and public spending. An example is the release of open healthcare data to researchers, as healthcare is one of the top economic sectors. Significant information systems development and computational experimentation are required to extract meaning and value from these datasets. We use a large open health dataset provided by the New York State Statewide Planning and Research Cooperative System (SPARCS) containing 2.3 million de-identified patient records. One of the fields in these records is a patient's length of stay (LoS) in a hospital, which is crucial in estimating healthcare costs and planning hospital capacity for future needs. Hence it would be very beneficial for hospitals to be able to predict the LoS early. The area of machine learning offers a potential solution, which is the focus of the current paper. METHODS: We investigated multiple machine learning techniques including feature engineering, regression, and classification trees to predict the length of stay (LoS) of all the hospital procedures currently available in the dataset. Whereas many researchers focus on LoS prediction for a specific disease, a unique feature of our model is its ability to simultaneously handle 285 diagnosis codes from the Clinical Classification System (CCS). We focused on the interpretability and explainability of input features and the resulting models. We developed separate models for newborns and non-newborns. RESULTS: The study yields promising results, demonstrating the effectiveness of machine learning in predicting LoS. The best R2 scores achieved are noteworthy: 0.82 for newborns using linear regression and 0.43 for non-newborns using catboost regression. Focusing on cardiovascular disease refines the predictive capability, achieving an improved R2 score of 0.62. The models not only demonstrate high performance but also provide understandable insights. For instance, birth-weight is employed for predicting LoS in newborns, while diagnostic-related group classification proves valuable for non-newborns. CONCLUSION: Our study showcases the practical utility of machine learning models in predicting LoS during patient admittance. The emphasis on interpretability ensures that the models can be easily comprehended and replicated by other researchers. Healthcare stakeholders, including providers, administrators, and patients, stand to benefit significantly. The findings offer valuable insights for cost estimation and capacity planning, contributing to the overall enhancement of healthcare management and delivery.

Precision diagnosis: a view of the clinical decision support systems (CDSS) landscape through the lens of critical care.

Improving diagnosis and treatment depends on clinical monitoring and computing. Clinical decision support systems (CDSS) have been in existence for over 50 years. While the literature points to positive impacts on quality and patient safety, outcomes, and the avoidance of medical errors, technical and regulatory challenges continue to retard their rate of integration into clinical care processes and thus delay the refinement of diagnoses towards personalized care. We conducted a systematic review of pertinent articles in the MEDLINE, US Department of Health and Human Services, Agency for Health Research and Quality, and US Food and Drug Administration databases, using a Boolean approach to combine terms germane to the discussion (clinical decision support, tools, systems, critical care, trauma, outcome, cost savings, NSQIP, APACHE, SOFA, ICU, and diagnostics). References were selected on the basis of both temporal and thematic relevance, and subsequently aggregated around four distinct themes: the uses of CDSS in the critical and surgical care settings, clinical insertion challenges, utilization leading to cost-savings, and regulatory concerns. Precision diagnosis is the accurate and timely explanation of each patient's health problem and further requires communication of that explanation to patients and surrogate decision-makers. Both accuracy and timeliness are essential to critical care, yet computed decision support systems (CDSS) are scarce. The limitation arises from the technical complexity associated with integrating and filtering large data sets from diverse sources. Provider mistrust and resistance coupled with the absence of clear guidance from regulatory bodies further retard acceptance of CDSS. While challenges to develop and deploy CDSS are substantial, the clinical, quality, and economic impacts warrant the effort, especially in disciplines requiring complex decision-making, such as critical and surgical care. Improving diagnosis in health care requires accumulation, validation and transformation of data into actionable information. The aggregate of those processes-CDSS-is currently primitive. Despite technical and regulatory challenges, the apparent clinical and economic utilities of CDSS must lead to greater engagement. These tools play the key role in realizing the vision of a more 'personalized medicine', one characterized by individualized precision diagnosis rather than population-based risk-stratification.

Perioperative and ICU Healthcare Analytics within a Veterans Integrated System Network: a Qualitative Gap Analysis.

Health care facilities are implementing analytics platforms as a way to document quality of care. However, few gap analyses exist on platforms specifically designed for patients treated in the Operating Room, Post-Anesthesia Care Unit, and Intensive Care Unit (ICU). As part of a quality improvement effort, we undertook a gap analysis of an existing analytics platform within the Veterans Healthcare Administration. The objectives were to identify themes associated with 1) current clinical use cases and stakeholder needs; 2) information flow and pain points; and 3) recommendations for future analytics development. Methods consisted of semi-structured interviews in 2 phases with a diverse set (n = 9) of support personnel and end users from five facilities across a Veterans Integrated Service Network. Phase 1 identified underlying needs and previous experiences with the analytics platform across various roles and operational responsibilities. Phase 2 validated preliminary feedback, lessons learned, and recommendations for improvement. Emerging themes suggested that the existing system met a small pool of national reporting requirements. However, pain points were identified with accessing data in several information system silos and performing multiple manual validation steps of data content. Notable recommendations included enhancing systems integration to create "one-stop shopping" for data, and developing a capability to perform trends analysis. Our gap analysis suggests that analytics platforms designed for surgical and ICU patients should employ approaches similar to those being used for primary care patients.

Automated population of an i2b2 clinical data warehouse from an openEHR-based data repository.

BACKGROUND: Detailed Clinical Model (DCM) approaches have recently seen wider adoption. More specifically, openEHR-based application systems are now used in production in several countries, serving diverse fields of application such as health information exchange, clinical registries and electronic medical record systems. However, approaches to efficiently provide openEHR data to researchers for secondary use have not yet been investigated or established. METHODS: We developed an approach to automatically load openEHR data instances into the open source clinical data warehouse i2b2. We evaluated query capabilities and the performance of this approach in the context of the Hanover Medical School Translational Research Framework (HaMSTR), an openEHR-based data repository. RESULTS: Automated creation of i2b2 ontologies from archetypes and templates and the integration of openEHR data instances from 903 patients of a paediatric intensive care unit has been achieved. In total, it took an average of ∼2527s to create 2.311.624 facts from 141.917 XML documents. Using the imported data, we conducted sample queries to compare the performance with two openEHR systems and to investigate if this representation of data is feasible to support cohort identification and record level data extraction. DISCUSSION: We found the automated population of an i2b2 clinical data warehouse to be a feasible approach to make openEHR data instances available for secondary use. Such an approach can facilitate timely provision of clinical data to researchers. It complements analytics based on the Archetype Query Language by allowing querying on both, legacy clinical data sources and openEHR data instances at the same time and by providing an easy-to-use query interface. However, due to different levels of expressiveness in the data models, not all semantics could be preserved during the ETL process.

Assessing risk of hospital readmissions for improving medical practice.

We compare statistical approaches for predicting the likelihood that individual patients will require readmission to hospital within 30 days of their discharge and for setting quality-control standards in that regard. Logistic regression, neural networks and decision trees are found to have comparable discriminating power when applied to cases that were not used to calibrate the respective models. Significant factors for predicting likelihood of readmission are the patient's medical condition upon admission and discharge, length (days) of the hospital visit, care rendered during the hospital stay, size and role of the medical facility, the type of medical insurance, and the environment into which the patient is discharged. Separately constructed models for major medical specialties (Surgery/Gynecology, Cardiorespiratory, Cardiovascular, Neurology, and Medicine) can improve the ability to identify high-risk patients for possible intervention, while consolidated models (with indicator variables for the specialties) can serve well for assessing overall quality of care.

Model-driven approach to data collection and reporting for quality improvement.

Continuous data collection and analysis have been shown essential to achieving improvement in healthcare. However, the data required for local improvement initiatives are often not readily available from hospital Electronic Health Record (EHR) systems or not routinely collected. Furthermore, improvement teams are often restricted in time and funding thus requiring inexpensive and rapid tools to support their work. Hence, the informatics challenge in healthcare local improvement initiatives consists of providing a mechanism for rapid modelling of the local domain by non-informatics experts, including performance metric definitions, and grounded in established improvement techniques. We investigate the feasibility of a model-driven software approach to address this challenge, whereby an improvement model designed by a team is used to automatically generate required electronic data collection instruments and reporting tools. To that goal, we have designed a generic Improvement Data Model (IDM) to capture the data items and quality measures relevant to the project, and constructed Web Improvement Support in Healthcare (WISH), a prototype tool that takes user-generated IDM models and creates a data schema, data collection web interfaces, and a set of live reports, based on Statistical Process Control (SPC) for use by improvement teams. The software has been successfully used in over 50 improvement projects, with more than 700 users. We present in detail the experiences of one of those initiatives, Chronic Obstructive Pulmonary Disease project in Northwest London hospitals. The specific challenges of improvement in healthcare are analysed and the benefits and limitations of the approach are discussed.

Insights into the nutritional prevention of macular degeneration based on a comparative topic modeling approach.

Topic modeling and text mining are subsets of natural language processing (NLP) with relevance for conducting meta-analysis (MA) and systematic review (SR). For evidence synthesis, the above NLP methods are conventionally used for topic-specific literature searches or extracting values from reports to automate essential phases of SR and MA. Instead, this work proposes a comparative topic modeling approach to analyze reports of contradictory results on the same general research question. Specifically, the objective is to identify topics exhibiting distinct associations with significant results for an outcome of interest by ranking them according to their proportional occurrence in (and consistency of distribution across) reports of significant effects. Macular degeneration (MD) is a disease that affects millions of people annually, causing vision loss. Augmenting evidence synthesis to provide insight into MD prevention is therefore of central interest in this article. The proposed method was tested on broad-scope studies addressing whether supplemental nutritional compounds significantly benefit macular degeneration. Six compounds were identified as having a particular association with reports of significant results for benefiting MD. Four of these were further supported in terms of effectiveness upon conducting a follow-up literature search for validation (omega-3 fatty acids, copper, zeaxanthin, and nitrates). The two not supported by the follow-up literature search (niacin and molybdenum) also had scores in the lowest range under the proposed scoring system. Results therefore suggest that the proposed method's score for a given topic may be a viable proxy for its degree of association with the outcome of interest, and can be helpful in the systematic search for potentially causal relationships. Further, the compounds identified by the proposed method were not simultaneously captured as salient topics by state-of-the-art topic models that leverage document and word embeddings (Top2Vec) and transformer models (BERTopic). These results underpin the proposed method's potential to add specificity in understanding effects from broad-scope reports, elucidate topics of interest for future research, and guide evidence synthesis in a scalable way. All of this is accomplished while yielding valuable and actionable insights into the prevention of MD.

An Enhanced Standardization and Qualification Mechanism for Heterogeneous Healthcare Data.

Given the challenge that healthcare related data are being obtained from various sources and in divergent formats there is an emerging need for providing improved and automated techniques and technologies that perform qualification and standardization of these data. The approach presented in this paper introduces a novel mechanism for the cleaning, qualification, and standardization of the collected primary and secondary data types. The latter is realized through the design and implementation of three (3) integrated subcomponents, the Data Cleaner, the Data Qualifier, and the Data Harmonizer that are further evaluated by performing data cleaning, qualification, and harmonization on top of data related to Pancreatic Cancer to further develop enhanced personalized risk assessment and recommendations to individuals.

Successful operational integration of healthcare analytics at Seattle Children's.

Introduction: As the quantity and complexity of health data grows, it is critical for healthcare organizations to devise analytic strategies that power data innovation so they can take advantage of new opportunities and improve outcomes. Seattle Children's Healthcare System (Seattle Children's) is an example of an organization that has built an operating model that integrates analytics into their business and daily operations. We present a roadmap for how Seattle Children's consolidated its fragmented analytics operations into a unified cohesive ecosystem capable of supporting advanced analytics capabilities and operational integration to transform care and accelerate research. Methods: In-depth interviews were conducted with ten leaders at Seattle Children's who have been instrumental in developing their enterprise analytics program. Interviews included the following leadership roles: Chief Data & Analytics Officer, Director of Research Informatics, Principal Systems Architect, Manager of Bioinformatics and High Throughput Analytics, Director of Neurocritical Care, Strategic Program Manager & Neuron Product Development Lead, Director of Dev Ops,Director of Clinical Analytics, Data Science Manager, and Advance Analytics Product Engineer. The interviews were unstructured and consisted of conversations intended to gather information from leadership about their experiences in building out Enterprise Analytics at Seattle Children's. Results: Seattle Children's has built an advanced enterprise analytics ecosystem that is integrated into its daily operations by applying an entrepreneurial mindset and agile development practices that are common in a startup environment. Analytics efforts were approached iteratively by selecting high-value projects that were delivered through Multidisciplinary Delivery Teams that were integrated into service lines. Service line leadership, in partnership with the Delivery Team leads, were responsible for the success of the team by setting project priorities, determining project budgets, and maintaining overall governance of their analytics endeavors. This organizational structure has led to the development of a wide range of analytic products that have been used to improve both operations and clinical care at Seattle Children's. Conclusions: Seattle Children's has demonstrated how a leading healthcare system can successfully create a robust, scalable, near real-time analytics ecosystem- one that delivers significant value to the organization from the ever-expanding volume of health data we see today.

An AI-based Decision Support System for Predicting Mental Health Disorders.

Approximately one billion individuals suffer from mental health disorders, such as depression, bipolar disorder, schizophrenia, and anxiety. Mental health professionals use various assessment tools to detect and diagnose these disorders. However, these tools are complex, contain an excessive number of questions, and require a significant amount of time to administer, leading to low participation and completion rates. Additionally, the results obtained from these tools must be analyzed and interpreted manually by mental health professionals, which may yield inaccurate diagnoses. To this extent, this research utilizes advanced analytics and artificial intelligence to develop a decision support system (DSS) that can efficiently detect and diagnose various mental disorders. As part of the DSS development process, the Network Pattern Recognition (NEPAR) algorithm is first utilized to build the assessment tool and identify the questions that participants need to answer. Then, various machine learning models are trained using participants' answers to these questions and other historical data as inputs to predict the existence and the type of their mental disorder. The results show that the proposed DSS can automatically diagnose mental disorders using only 28 questions without any human input, to an accuracy level of 89%. Furthermore, the proposed mental disorder diagnostic tool has significantly fewer questions than its counterparts; hence, it provides higher participation and completion rates. Therefore, mental health professionals can use this proposed DSS and its accompanying assessment tool for improved clinical decision-making and diagnostic accuracy.

Leveraging Deep Learning for Designing Healthcare Analytics Heuristic for Diagnostics.

Healthcare Informatics is a phenomenon being talked about from the early 21st century in the era in which we are living. With evolution of new computing technologies huge amount of data in healthcare is produced opening several research areas. Managing the massiveness of this data is required while extracting knowledge for decision making is the main concern of today. For this task researchers are doing explorations in big data analytics, deep learning (advanced form of machine learning known as deep neural nets), predictive analytics and various other algorithms to bring innovation in healthcare. Through all these innovations happening it is not wrong to establish that disease prediction with anticipation of its cure is no longer unrealistic. First, Dengue Fever (DF) and then Covid-19 likewise are new outbreak in infectious lethal diseases and diagnosing at all stages is crucial to decrease mortality rate. In case of Diabetes, clinicians and experts are finding challenging the timely diagnosis and analyzing the chances of developing underlying diseases. In this paper, Louvain Mani-Hierarchical Fold Learning healthcare analytics, a hybrid deep learning technique is proposed for medical diagnostics and is tested and validated using real-time dataset of 104 instances of patients with dengue fever made available by Holy Family Hospital, Pakistan and 810 instances found for infectious diseases including prognosis of; Covid-19, SARS, ARDS, Pneumocystis, Streptococcus, Chlamydophila, Klebsiella, Legionella, Lipoid, etc. on GitHub. Louvain Mani-Hierarchical Fold Learning healthcare analytics showed maximum 0.952 correlations between two clusters with Spearman when applied on 240 instances extracted from comorbidities diagnostic data model derived from 15696 endocrine records of multiple visits of 100 patients identified by a unique ID. Accuracy for induced rules is evaluated by Laplace (Fig. 8) as 0.727, 0.701 and 0.203 for 41, 18 and 24 rules, respectively. Endocrine diagnostic data is made available by Shifa International Hospital, Islamabad, Pakistan. Our results show that in future this algorithm may be tested for diagnostics on healthcare big data.

Machine learning-based outcome prediction and novel hypotheses generation for substance use disorder treatment.

OBJECTIVE: Substance use disorder is a critical public health issue. Discovering the synergies among factors impacting treatment program success can help governments and treatment facilities develop effective policies. In this work, we propose a novel data analytics approach using machine learning models to discover interaction effects that might be neglected by traditional hypothesis-generating approaches. MATERIALS AND METHODS: A patient-episode-level substance use treatment discharge dataset and a Federal Bureau of Investigation crime dataset were joined using core-based statistical area codes. Random forests, artificial neural networks, and extreme gradient boosting were applied with a nested cross-validation methodology. Interaction effects were identified based on the machine learning model with the best performance. These interaction effects were analyzed and tested using traditional logistic regression models on unseen data. RESULTS: In predicting patient completion of a treatment program, extreme gradient boosting performed the best with an area under the curve of 89.31%. Based on our procedure, 73 interaction effects were identified. Among these, 14 were tested using traditional logistic regression models where 12 were statistically significant (P<.05). CONCLUSIONS: We identified new interaction effects among the length of stay, frequency of substance use, changes in self-help group attendance frequency, and other factors. This work provides insights into the interactions between factors impacting treatment completion. Further traditional statistical analysis can be employed by practitioners and policy makers to test the effects discovered by our novel machine learning approach.

A Survey of Healthcare Internet-of-Things (HIoT): A Clinical Perspective.

In combination with current sociological trends, the maturing development of IoT devices is projected to revolutionize healthcare. A network of body-worn sensors, each with a unique ID, can collect health data that is orders-of-magnitude richer than what is available today from sporadic observations in clinical/hospital environments. When databased, analyzed, and compared against information from other individuals using data analytics, HIoT data enables the personalization and modernization of care with radical improvements in outcomes and reductions in cost. In this paper, we survey existing and emerging technologies that can enable this vision for the future of healthcare, particularly in the clinical practice of healthcare. Three main technology areas underlie the development of this field: (a) sensing, where there is an increased drive for miniaturization and power efficiency; (b) communications, where the enabling factors are ubiquitous connectivity, standardized protocols, and the wide availability of cloud infrastructure, and (c) data analytics and inference, where the availability of large amounts of data and computational resources is revolutionizing algorithms for individualizing inference and actions in health management. Throughout the paper, we use a case study to concretely illustrate the impact of these trends. We conclude our paper with a discussion of the emerging directions, open issues, and challenges.

A decision tree-based classifier for E-visit service provision.

This study proposes a decision tree-based e-visit classification approach (DTEVCA) to determine clinic visits qualified as e-visits using clinics' medical records and patients' demographic data. This study assumes that health care insurance will subsidise e-visit service costs, in which case, identifying patients who benefit most from e-visit service is essential. Using a large data set from Taiwan's National Health Insurance, this study verifies the efficiency and validity of the DTEVCA. Results indicate that this approach can accurately classify in-office clinic visits that could switch to e-visit services. The straightforward rules of this decision tree also give insurance agencies a clear guideline to understand the circumstances of using e-visits and predict the effects of implementing e-visits in Taiwan. Result of this study can help countries improve the policy formulation process for physicians' use, or for academic research. The DTEVCA can update classification rules using new data to correct biases and ensure the stability of the e-visit system. In addition, the concept of this approach is feasible not only for e-visit service but also for other 'new services' such as new products or new policies.

COVID-19 Patient Health Prediction Using Boosted Random Forest Algorithm.

Integration of artificial intelligence (AI) techniques in wireless infrastructure, real-time collection, and processing of end-user devices is now in high demand. It is now superlative to use AI to detect and predict pandemics of a colossal nature. The Coronavirus disease 2019 (COVID-19) pandemic, which originated in Wuhan China, has had disastrous effects on the global community and has overburdened advanced healthcare systems throughout the world. Globally; over 4,063,525 confirmed cases and 282,244 deaths have been recorded as of 11th May 2020, according to the European Centre for Disease Prevention and Control agency. However, the current rapid and exponential rise in the number of patients has necessitated efficient and quick prediction of the possible outcome of an infected patient for appropriate treatment using AI techniques. This paper proposes a fine-tuned Random Forest model boosted by the AdaBoost algorithm. The model uses the COVID-19 patient's geographical, travel, health, and demographic data to predict the severity of the case and the possible outcome, recovery, or death. The model has an accuracy of 94% and a F1 Score of 0.86 on the dataset used. The data analysis reveals a positive correlation between patients' gender and deaths, and also indicates that the majority of patients are aged between 20 and 70 years.

The State of Data in Healthcare: Path Towards Standardization.

Coupled with the rise of data science and machine learning, the increasing availability of digitized health and wellness data has provided an exciting opportunity for complex analyses of problems throughout the healthcare domain. Whereas many early works focused on a particular aspect of patient care, often drawing on data from a specific clinical or administrative source, it has become clear such a single-source approach is insufficient to capture the complexity of the human condition. Instead, adequately modeling health and wellness problems requires the ability to draw upon data spanning multiple facets of an individual's biology, their care, and the social aspects of their life. Although such an awareness has greatly expanded the breadth of health and wellness data collected, the diverse array of data sources and intended uses often leave researchers and practitioners with a scattered and fragmented view of any particular patient. As a result, there exists a clear need to catalogue and organize the range of healthcare data available for analysis. This work represents an effort at developing such an organization, presenting a patient-centric framework deemed the Healthcare Data Spectrum (HDS). Comprised of six layers, the HDS begins with the innermost micro-level omics and macro-level demographic data that directly characterize a patient, and extends at its outermost to aggregate population-level data derived from attributes of care for each individual patient. For each level of the HDS, this manuscript will examine the specific types of constituent data, provide examples of how the data aid in a broad set of research problems, and identify the primary terminology and standards used to describe the data.

Healthcare predictive analytics: An overview with a focus on Saudi Arabia.

Despite a newfound wealth of data and information, the healthcare sector is lacking in actionable knowledge. This is largely because healthcare data, though plentiful, tends to be inherently complex and fragmented. Health data analytics, with an emphasis on predictive analytics, is emerging as a transformative tool that can enable more proactive and preventative treatment options. This review considers the ways in which predictive analytics has been applied in the for-profit business sector to generate well-timed and accurate predictions of key outcomes, with a focus on key features that may be applicable to healthcare-specific applications. Published medical research presenting assessments of predictive analytics technology in medical applications are reviewed, with particular emphasis on how hospitals have integrated predictive analytics into their day-to-day healthcare services to improve quality of care. This review also highlights the numerous challenges of implementing predictive analytics in healthcare settings and concludes with a discussion of current efforts to implement healthcare data analytics in the developing country, Saudi Arabia.

Preference-Sensitive Management of Post-Mammography Decisions in Breast Cancer Diagnosis.

Decision models representing the clinical situations where treatment options entail a significant risk of morbidity or mortality should consider the variations in risk preferences of individuals. In this study, we develop a stochastic modeling framework that optimizes risk-sensitive diagnostic decisions after a mammography exam. For a given patient, our objective is to find the utility maximizing diagnostic decisions where we define the utility over quality-adjusted survival duration. We use real data from a private mammography database to numerically solve our model for various utility functions. Our choice of utility functions for the numerical analysis is driven by actual patient behavior encountered in clinical practice. We find that invasive diagnostic procedures such as biopsies are more aggressively used than what the optimal risk-neutral policy would suggest, implying a far-sighted (or equivalently risk-seeking) behavior. When risk preferences are incorporated into the clinical practice, policy makers should bear in mind that a welfare loss in terms of survival duration is inevitable as evidenced by our structural and empirical results.

Big Data in Neonatal Health Care: Big Reach, Big Reward?

Analog-to-digital data conversion has created massive amounts of historical and real-time health care data. Costs associated with neonatal health issues are high. Big data use in the neonatal intensive care unit has the potential to facilitate earlier detection of clinical deterioration, expedite application of efficient clinical decision-making algorithms based on real-time and historical data mining, and yield significant cost-savings.