Identification of patients at risk of new onset heart failure: Utilizing a large statewide health information exchange to train and validate a risk prediction model.

BACKGROUND: New-onset heart failure (HF) is associated with poor prognosis and high healthcare utilization. Early identification of patients at increased risk incident-HF may allow for focused allocation of preventative care resources. Health information exchange (HIE) data span the entire spectrum of clinical care, but there are no HIE-based clinical decision support tools for diagnosis of incident-HF. We applied machine-learning methods to model the one-year risk of incident-HF from the Maine statewide-HIE. METHODS AND RESULTS: We included subjects aged ≥ 40 years without prior HF ICD9/10 codes during a three-year period from 2015 to 2018, and incident-HF defined as assignment of two outpatient or one inpatient code in a year. A tree-boosting algorithm was used to model the probability of incident-HF in year two from data collected in year one, and then validated in year three. 5,668 of 521,347 patients (1.09%) developed incident-HF in the validation cohort. In the validation cohort, the model c-statistic was 0.824 and at a clinically predetermined risk threshold, 10% of patients identified by the model developed incident-HF and 29% of all incident-HF cases in the state of Maine were identified. CONCLUSIONS: Utilizing machine learning modeling techniques on passively collected clinical HIE data, we developed and validated an incident-HF prediction tool that performs on par with other models that require proactively collected clinical data. Our algorithm could be integrated into other HIEs to leverage the EMR resources to provide individuals, systems, and payors with a risk stratification tool to allow for targeted resource allocation to reduce incident-HF disease burden on individuals and health care systems.

Electronic Health Record-Based Prediction of 1-Year Risk of Incident Cardiac Dysrhythmia: Prospective Case-Finding Algorithm Development and Validation Study.

BACKGROUND: Cardiac dysrhythmia is currently an extremely common disease. Severe arrhythmias often cause a series of complications, including congestive heart failure, fainting or syncope, stroke, and sudden death. OBJECTIVE: The aim of this study was to predict incident arrhythmia prospectively within a 1-year period to provide early warning of impending arrhythmia. METHODS: Retrospective (1,033,856 individuals enrolled between October 1, 2016, and October 1, 2017) and prospective (1,040,767 individuals enrolled between October 1, 2017, and October 1, 2018) cohorts were constructed from integrated electronic health records in Maine, United States. An ensemble learning workflow was built through multiple machine learning algorithms. Differentiating features, including acute and chronic diseases, procedures, health status, laboratory tests, prescriptions, clinical utilization indicators, and socioeconomic determinants, were compiled for incident arrhythmia assessment. The predictive model was retrospectively trained and calibrated using an isotonic regression method and was prospectively validated. Model performance was evaluated using the area under the receiver operating characteristic curve (AUROC). RESULTS: The cardiac dysrhythmia case-finding algorithm (retrospective: AUROC 0.854; prospective: AUROC 0.827) stratified the population into 5 risk groups: 53.35% (555,233/1,040,767), 44.83% (466,594/1,040,767), 1.76% (18,290/1,040,767), 0.06% (623/1,040,767), and 0.003% (27/1,040,767) were in the very low-risk, low-risk, medium-risk, high-risk, and very high-risk groups, respectively; 51.85% (14/27) patients in the very high-risk subgroup were confirmed to have incident cardiac dysrhythmia within the subsequent 1 year. CONCLUSIONS: Our case-finding algorithm is promising for prospectively predicting 1-year incident cardiac dysrhythmias in a general population, and we believe that our case-finding algorithm can serve as an early warning system to allow statewide population-level screening and surveillance to improve cardiac dysrhythmia care.

Identification of elders at higher risk for fall with statewide electronic health records and a machine learning algorithm.

OBJECTIVE: Predicting the risk of falls in advance can benefit the quality of care and potentially reduce mortality and morbidity in the older population. The aim of this study was to construct and validate an electronic health record-based fall risk predictive tool to identify elders at a higher risk of falls. METHODS: The one-year fall prediction model was developed using the machine-learning-based algorithm, XGBoost, and tested on an independent validation cohort. The data were collected from electronic health records (EHR) of Maine from 2016 to 2018, comprising 265,225 older patients (≥65 years of age). RESULTS: This model attained a validated C-statistic of 0.807, where 50 % of the identified high-risk true positives were confirmed to fall during the first 94 days of next year. The model also captured in advance 58.01 % and 54.93 % of falls that happened within the first 30 and 30-60 days of next year. The identified high-risk patients of fall showed conditions of severe disease comorbidities, an enrichment of fall-increasing cardiovascular and mental medication prescriptions and increased historical clinical utilization, revealing the complexity of the underlying fall etiology. The XGBoost algorithm captured 157 impactful predictors into the final predictive model, where cognitive disorders, abnormalities of gait and balance, Parkinson's disease, fall history and osteoporosis were identified as the top-5 strongest predictors of the future fall event. CONCLUSIONS: By using the EHR data, this risk assessment tool attained an improved discriminative ability and can be immediately deployed in the health system to provide automatic early warnings to older adults with increased fall risk and identify their personalized risk factors to facilitate customized fall interventions.

Development of an early-warning system for high-risk patients for suicide attempt using deep learning and electronic health records.

Suicide is the tenth leading cause of death in the United States (US). An early-warning system (EWS) for suicide attempt could prove valuable for identifying those at risk of suicide attempts, and analyzing the contribution of repeated attempts to the risk of eventual death by suicide. In this study we sought to develop an EWS for high-risk suicide attempt patients through the development of a population-based risk stratification surveillance system. Advanced machine-learning algorithms and deep neural networks were utilized to build models with the data from electronic health records (EHRs). A final risk score was calculated for each individual and calibrated to indicate the probability of a suicide attempt in the following 1-year time period. Risk scores were subjected to individual-level analysis in order to aid in the interpretation of the results for health-care providers managing the at-risk cohorts. The 1-year suicide attempt risk model attained an area under the curve (AUC ROC) of 0.792 and 0.769 in the retrospective and prospective cohorts, respectively. The suicide attempt rate in the "very high risk" category was 60 times greater than the population baseline when tested in the prospective cohorts. Mental health disorders including depression, bipolar disorders and anxiety, along with substance abuse, impulse control disorders, clinical utilization indicators, and socioeconomic determinants were recognized as significant features associated with incident suicide attempt.

A Real-Time Early Warning System for Monitoring Inpatient Mortality Risk: Prospective Study Using Electronic Medical Record Data.

BACKGROUND: The rapid deterioration observed in the condition of some hospitalized patients can be attributed to either disease progression or imperfect triage and level of care assignment after their admission. An early warning system (EWS) to identify patients at high risk of subsequent intrahospital death can be an effective tool for ensuring patient safety and quality of care and reducing avoidable harm and costs. OBJECTIVE: The aim of this study was to prospectively validate a real-time EWS designed to predict patients at high risk of inpatient mortality during their hospital episodes. METHODS: Data were collected from the system-wide electronic medical record (EMR) of two acute Berkshire Health System hospitals, comprising 54,246 inpatient admissions from January 1, 2015, to September 30, 2017, of which 2.30% (1248/54,246) resulted in intrahospital deaths. Multiple machine learning methods (linear and nonlinear) were explored and compared. The tree-based random forest method was selected to develop the predictive application for the intrahospital mortality assessment. After constructing the model, we prospectively validated the algorithms as a real-time inpatient EWS for mortality. RESULTS: The EWS algorithm scored patients' daily and long-term risk of inpatient mortality probability after admission and stratified them into distinct risk groups. In the prospective validation, the EWS prospectively attained a c-statistic of 0.884, where 99 encounters were captured in the highest risk group, 69% (68/99) of whom died during the episodes. It accurately predicted the possibility of death for the top 13.3% (34/255) of the patients at least 40.8 hours before death. Important clinical utilization features, together with coded diagnoses, vital signs, and laboratory test results were recognized as impactful predictors in the final EWS. CONCLUSIONS: In this study, we prospectively demonstrated the capability of the newly-designed EWS to monitor and alert clinicians about patients at high risk of in-hospital death in real time, thereby providing opportunities for timely interventions. This real-time EWS is able to assist clinical decision making and enable more actionable and effective individualized care for patients' better health outcomes in target medical facilities.

Prediction of the 1-Year Risk of Incident Lung Cancer: Prospective Study Using Electronic Health Records from the State of Maine.

BACKGROUND: Lung cancer is the leading cause of cancer death worldwide. Early detection of individuals at risk of lung cancer is critical to reduce the mortality rate. OBJECTIVE: The aim of this study was to develop and validate a prospective risk prediction model to identify patients at risk of new incident lung cancer within the next 1 year in the general population. METHODS: Data from individual patient electronic health records (EHRs) were extracted from the Maine Health Information Exchange network. The study population consisted of patients with at least one EHR between April 1, 2016, and March 31, 2018, who had no history of lung cancer. A retrospective cohort (N=873,598) and a prospective cohort (N=836,659) were formed for model construction and validation. An Extreme Gradient Boosting (XGBoost) algorithm was adopted to build the model. It assigned a score to each individual to quantify the probability of a new incident lung cancer diagnosis from October 1, 2016, to September 31, 2017. The model was trained with the clinical profile in the retrospective cohort from the preceding 6 months and validated with the prospective cohort to predict the risk of incident lung cancer from April 1, 2017, to March 31, 2018. RESULTS: The model had an area under the curve (AUC) of 0.881 (95% CI 0.873-0.889) in the prospective cohort. Two thresholds of 0.0045 and 0.01 were applied to the predictive scores to stratify the population into low-, medium-, and high-risk categories. The incidence of lung cancer in the high-risk category (579/53,922, 1.07%) was 7.7 times higher than that in the overall cohort (1167/836,659, 0.14%). Age, a history of pulmonary diseases and other chronic diseases, medications for mental disorders, and social disparities were found to be associated with new incident lung cancer. CONCLUSIONS: We retrospectively developed and prospectively validated an accurate risk prediction model of new incident lung cancer occurring in the next 1 year. Through statistical learning from the statewide EHR data in the preceding 6 months, our model was able to identify statewide high-risk patients, which will benefit the population health through establishment of preventive interventions or more intensive surveillance.

Assessing Statewide All-Cause Future One-Year Mortality: Prospective Study With Implications for Quality of Life, Resource Utilization, and Medical Futility.

BACKGROUND: For many elderly patients, a disproportionate amount of health care resources and expenditures is spent during the last year of life, despite the discomfort and reduced quality of life associated with many aggressive medical approaches. However, few prognostic tools have focused on predicting all-cause 1-year mortality among elderly patients at a statewide level, an issue that has implications for improving quality of life while distributing scarce resources fairly. OBJECTIVE: Using data from a statewide elderly population (aged ≥65 years), we sought to prospectively validate an algorithm to identify patients at risk for dying in the next year for the purpose of minimizing decision uncertainty, improving quality of life, and reducing futile treatment. METHODS: Analysis was performed using electronic medical records from the Health Information Exchange in the state of Maine, which covered records of nearly 95% of the statewide population. The model was developed from 125,896 patients aged at least 65 years who were discharged from any care facility in the Health Information Exchange network from September 5, 2013, to September 4, 2015. Validation was conducted using 153,199 patients with same inclusion and exclusion criteria from September 5, 2014, to September 4, 2016. Patients were stratified into risk groups. The association between all-cause 1-year mortality and risk factors was screened by chi-squared test and manually reviewed by 2 clinicians. We calculated risk scores for individual patients using a gradient tree-based boost algorithm, which measured the probability of mortality within the next year based on the preceding 1-year clinical profile. RESULTS: The development sample included 125,896 patients (72,572 women, 57.64%; mean 74.2 [SD 7.7] years). The final validation cohort included 153,199 patients (88,177 women, 57.56%; mean 74.3 [SD 7.8] years). The c-statistic for discrimination was 0.96 (95% CI 0.93-0.98) in the development group and 0.91 (95% CI 0.90-0.94) in the validation cohort. The mortality was 0.99% in the low-risk group, 16.75% in the intermediate-risk group, and 72.12% in the high-risk group. A total of 99 independent risk factors (n=99) for mortality were identified (reported as odds ratios; 95% CI). Age was on the top of list (1.41; 1.06-1.48); congestive heart failure (20.90; 15.41-28.08) and different tumor sites were also recognized as driving risk factors, such as cancer of the ovaries (14.42; 2.24-53.04), colon (14.07; 10.08-19.08), and stomach (13.64; 3.26-86.57). Disparities were also found in patients' social determinants like respiratory hazard index (1.24; 0.92-1.40) and unemployment rate (1.18; 0.98-1.24). Among high-risk patients who expired in our dataset, cerebrovascular accident, amputation, and type 1 diabetes were the top 3 diseases in terms of average cost in the last year of life. CONCLUSIONS: Our study prospectively validated an accurate 1-year risk prediction model and stratification for the elderly population (≥65 years) at risk of mortality with statewide electronic medical record datasets. It should be a valuable adjunct for helping patients to make better quality-of-life choices and alerting care givers to target high-risk elderly for appropriate care and discussions, thus cutting back on futile treatment.

Prediction of Incident Hypertension Within the Next Year: Prospective Study Using Statewide Electronic Health Records and Machine Learning.

BACKGROUND: As a high-prevalence health condition, hypertension is clinically costly, difficult to manage, and often leads to severe and life-threatening diseases such as cardiovascular disease (CVD) and stroke. OBJECTIVE: The aim of this study was to develop and validate prospectively a risk prediction model of incident essential hypertension within the following year. METHODS: Data from individual patient electronic health records (EHRs) were extracted from the Maine Health Information Exchange network. Retrospective (N=823,627, calendar year 2013) and prospective (N=680,810, calendar year 2014) cohorts were formed. A machine learning algorithm, XGBoost, was adopted in the process of feature selection and model building. It generated an ensemble of classification trees and assigned a final predictive risk score to each individual. RESULTS: The 1-year incident hypertension risk model attained areas under the curve (AUCs) of 0.917 and 0.870 in the retrospective and prospective cohorts, respectively. Risk scores were calculated and stratified into five risk categories, with 4526 out of 381,544 patients (1.19%) in the lowest risk category (score 0-0.05) and 21,050 out of 41,329 patients (50.93%) in the highest risk category (score 0.4-1) receiving a diagnosis of incident hypertension in the following 1 year. Type 2 diabetes, lipid disorders, CVDs, mental illness, clinical utilization indicators, and socioeconomic determinants were recognized as driving or associated features of incident essential hypertension. The very high risk population mainly comprised elderly (age>50 years) individuals with multiple chronic conditions, especially those receiving medications for mental disorders. Disparities were also found in social determinants, including some community-level factors associated with higher risk and others that were protective against hypertension. CONCLUSIONS: With statewide EHR datasets, our study prospectively validated an accurate 1-year risk prediction model for incident essential hypertension. Our real-time predictive analytic model has been deployed in the state of Maine, providing implications in interventions for hypertension and related diseases and hopefully enhancing hypertension care.

Estimating One-Year Risk of Incident Chronic Kidney Disease: Retrospective Development and Validation Study Using Electronic Medical Record Data From the State of Maine.

BACKGROUND: Chronic kidney disease (CKD) is a major public health concern in the United States with high prevalence, growing incidence, and serious adverse outcomes. OBJECTIVE: We aimed to develop and validate a model to identify patients at risk of receiving a new diagnosis of CKD (incident CKD) during the next 1 year in a general population. METHODS: The study population consisted of patients who had visited any care facility in the Maine Health Information Exchange network any time between January 1, 2013, and December 31, 2015, and had no history of CKD diagnosis. Two retrospective cohorts of electronic medical records (EMRs) were constructed for model derivation (N=1,310,363) and validation (N=1,430,772). The model was derived using a gradient tree-based boost algorithm to assign a score to each individual that measured the probability of receiving a new diagnosis of CKD from January 1, 2014, to December 31, 2014, based on the preceding 1-year clinical profile. A feature selection process was conducted to reduce the dimension of the data from 14,680 EMR features to 146 as predictors in the final model. Relative risk was calculated by the model to gauge the risk ratio of the individual to population mean of receiving a CKD diagnosis in next 1 year. The model was tested on the validation cohort to predict risk of CKD diagnosis in the period from January 1, 2015, to December 31, 2015, using the preceding 1-year clinical profile. RESULTS: The final model had a c-statistic of 0.871 in the validation cohort. It stratified patients into low-risk (score 0-0.005), intermediate-risk (score 0.005-0.05), and high-risk (score ≥ 0.05) levels. The incidence of CKD in the high-risk patient group was 7.94%, 13.7 times higher than the incidence in the overall cohort (0.58%). Survival analysis showed that patients in the 3 risk categories had significantly different CKD outcomes as a function of time (P<.001), indicating an effective classification of patients by the model. CONCLUSIONS: We developed and validated a model that is able to identify patients at high risk of having CKD in the next 1 year by statistically learning from the EMR-based clinical history in the preceding 1 year. Identification of these patients indicates care opportunities such as monitoring and adopting intervention plans that may benefit the quality of care and outcomes in the long term.

Defining and characterizing the critical transition state prior to the type 2 diabetes disease.

BACKGROUND: Type 2 diabetes mellitus (T2DM), with increased risk of serious long-term complications, currently represents 8.3% of the adult population. We hypothesized that a critical transition state prior to the new onset T2DM can be revealed through the longitudinal electronic medical record (EMR) analysis. METHOD: We applied the transition-based network entropy methodology which previously identified a dynamic driver network (DDN) underlying the critical T2DM transition at the tissue molecular biological level. To profile pre-disease phenotypical changes that indicated a critical transition state, a cohort of 7,334 patients was assembled from the Maine State Health Information Exchange (HIE). These patients all had their first confirmative diagnosis of T2DM between January 1, 2013 and June 30, 2013. The cohort's EMRs from the 24 months preceding their date of first T2DM diagnosis were extracted. RESULTS: Analysis of these patients' pre-disease clinical history identified a dynamic driver network (DDN) and an associated critical transition state six months prior to their first confirmative T2DM state. CONCLUSIONS: This 6-month window before the disease state provides an early warning of the impending T2DM, warranting an opportunity to apply proactive interventions to prevent or delay the new onset of T2DM.

Web-based Real-Time Case Finding for the Population Health Management of Patients With Diabetes Mellitus: A Prospective Validation of the Natural Language Processing-Based Algorithm With Statewide Electronic Medical Records.

BACKGROUND: Diabetes case finding based on structured medical records does not fully identify diabetic patients whose medical histories related to diabetes are available in the form of free text. Manual chart reviews have been used but involve high labor costs and long latency. OBJECTIVE: This study developed and tested a Web-based diabetes case finding algorithm using both structured and unstructured electronic medical records (EMRs). METHODS: This study was based on the health information exchange (HIE) EMR database that covers almost all health facilities in the state of Maine, United States. Using narrative clinical notes, a Web-based natural language processing (NLP) case finding algorithm was retrospectively (July 1, 2012, to June 30, 2013) developed with a random subset of HIE-associated facilities, which was then blind tested with the remaining facilities. The NLP-based algorithm was subsequently integrated into the HIE database and validated prospectively (July 1, 2013, to June 30, 2014). RESULTS: Of the 935,891 patients in the prospective cohort, 64,168 diabetes cases were identified using diagnosis codes alone. Our NLP-based case finding algorithm prospectively found an additional 5756 uncodified cases (5756/64,168, 8.97% increase) with a positive predictive value of .90. Of the 21,720 diabetic patients identified by both methods, 6616 patients (6616/21,720, 30.46%) were identified by the NLP-based algorithm before a diabetes diagnosis was noted in the structured EMR (mean time difference = 48 days). CONCLUSIONS: The online NLP algorithm was effective in identifying uncodified diabetes cases in real time, leading to a significant improvement in diabetes case finding. The successful integration of the NLP-based case finding algorithm into the Maine HIE database indicates a strong potential for application of this novel method to achieve a more complete ascertainment of diagnoses of diabetes mellitus.

Prospective stratification of patients at risk for emergency department revisit: resource utilization and population management strategy implications.

BACKGROUND: Estimating patient risk of future emergency department (ED) revisits can guide the allocation of resources, e.g. local primary care and/or specialty, to better manage ED high utilization patient populations and thereby improve patient life qualities. METHODS: We set to develop and validate a method to estimate patient ED revisit risk in the subsequent 6 months from an ED discharge date. An ensemble decision-tree-based model with Electronic Medical Record (EMR) encounter data from HealthInfoNet (HIN), Maine's Health Information Exchange (HIE), was developed and validated, assessing patient risk for a subsequent 6 month return ED visit based on the ED encounter-associated demographic and EMR clinical history data. A retrospective cohort of 293,461 ED encounters that occurred between January 1, 2012 and December 31, 2012, was assembled with the associated patients' 1-year clinical histories before the ED discharge date, for model training and calibration purposes. To validate, a prospective cohort of 193,886 ED encounters that occurred between January 1, 2013 and June 30, 2013 was constructed. RESULTS: Statistical learning that was utilized to construct the prediction model identified 152 variables that included the following data domains: demographics groups (12), different encounter history (104), care facilities (12), primary and secondary diagnoses (10), primary and secondary procedures (2), chronic disease condition (1), laboratory test results (2), and outpatient prescription medications (9). The c-statistics for the retrospective and prospective cohorts were 0.742 and 0.730 respectively. Total medical expense and ED utilization by risk score 6 months after the discharge were analyzed. Cluster analysis identified discrete subpopulations of high-risk patients with distinctive resource utilization patterns, suggesting the need for diversified care management strategies. CONCLUSIONS: Integration of our method into the HIN secure statewide data system in real time prospectively validated its performance. It promises to provide increased opportunity for high ED utilization identification, and optimized resource and population management.

Development, Validation and Deployment of a Real Time 30 Day Hospital Readmission Risk Assessment Tool in the Maine Healthcare Information Exchange.

OBJECTIVES: Identifying patients at risk of a 30-day readmission can help providers design interventions, and provide targeted care to improve clinical effectiveness. This study developed a risk model to predict a 30-day inpatient hospital readmission for patients in Maine, across all payers, all diseases and all demographic groups. METHODS: Our objective was to develop a model to determine the risk for inpatient hospital readmission within 30 days post discharge. All patients within the Maine Health Information Exchange (HIE) system were included. The model was retrospectively developed on inpatient encounters between January 1, 2012 to December 31, 2012 from 24 randomly chosen hospitals, and then prospectively validated on inpatient encounters from January 1, 2013 to December 31, 2013 using all HIE patients. RESULTS: A risk assessment tool partitioned the entire HIE population into subgroups that corresponded to probability of hospital readmission as determined by a corresponding positive predictive value (PPV). An overall model c-statistic of 0.72 was achieved. The total 30-day readmission rates in low (score of 0-30), intermediate (score of 30-70) and high (score of 70-100) risk groupings were 8.67%, 24.10% and 74.10%, respectively. A time to event analysis revealed the higher risk groups readmitted to a hospital earlier than the lower risk groups. Six high-risk patient subgroup patterns were revealed through unsupervised clustering. Our model was successfully integrated into the statewide HIE to identify patient readmission risk upon admission and daily during hospitalization or for 30 days subsequently, providing daily risk score updates. CONCLUSIONS: The risk model was validated as an effective tool for predicting 30-day readmissions for patients across all payer, disease and demographic groups within the Maine HIE. Exposing the key clinical, demographic and utilization profiles driving each patient's risk of readmission score may be useful to providers in developing individualized post discharge care plans.

Online Prediction of Health Care Utilization in the Next Six Months Based on Electronic Health Record Information: A Cohort and Validation Study.

BACKGROUND: The increasing rate of health care expenditures in the United States has placed a significant burden on the nation's economy. Predicting future health care utilization of patients can provide useful information to better understand and manage overall health care deliveries and clinical resource allocation. OBJECTIVE: This study developed an electronic medical record (EMR)-based online risk model predictive of resource utilization for patients in Maine in the next 6 months across all payers, all diseases, and all demographic groups. METHODS: In the HealthInfoNet, Maine's health information exchange (HIE), a retrospective cohort of 1,273,114 patients was constructed with the preceding 12-month EMR. Each patient's next 6-month (between January 1, 2013 and June 30, 2013) health care resource utilization was retrospectively scored ranging from 0 to 100 and a decision tree-based predictive model was developed. Our model was later integrated in the Maine HIE population exploration system to allow a prospective validation analysis of 1,358,153 patients by forecasting their next 6-month risk of resource utilization between July 1, 2013 and December 31, 2013. RESULTS: Prospectively predicted risks, on either an individual level or a population (per 1000 patients) level, were consistent with the next 6-month resource utilization distributions and the clinical patterns at the population level. Results demonstrated the strong correlation between its care resource utilization and our risk scores, supporting the effectiveness of our model. With the online population risk monitoring enterprise dashboards, the effectiveness of the predictive algorithm has been validated by clinicians and caregivers in the State of Maine. CONCLUSIONS: The model and associated online applications were designed for tracking the evolving nature of total population risk, in a longitudinal manner, for health care resource utilization. It will enable more effective care management strategies driving improved patient outcomes.

NLP based congestive heart failure case finding: A prospective analysis on statewide electronic medical records.

BACKGROUND: In order to proactively manage congestive heart failure (CHF) patients, an effective CHF case finding algorithm is required to process both structured and unstructured electronic medical records (EMR) to allow complementary and cost-efficient identification of CHF patients. METHODS AND RESULTS: We set to identify CHF cases from both EMR codified and natural language processing (NLP) found cases. Using narrative clinical notes from all Maine Health Information Exchange (HIE) patients, the NLP case finding algorithm was retrospectively (July 1, 2012-June 30, 2013) developed with a random subset of HIE associated facilities, and blind-tested with the remaining facilities. The NLP based method was integrated into a live HIE population exploration system and validated prospectively (July 1, 2013-June 30, 2014). Total of 18,295 codified CHF patients were included in Maine HIE. Among the 253,803 subjects without CHF codings, our case finding algorithm prospectively identified 2411 uncodified CHF cases. The positive predictive value (PPV) is 0.914, and 70.1% of these 2411 cases were found to be with CHF histories in the clinical notes. CONCLUSIONS: A CHF case finding algorithm was developed, tested and prospectively validated. The successful integration of the CHF case findings algorithm into the Maine HIE live system is expected to improve the Maine CHF care.

Real-time web-based assessment of total population risk of future emergency department utilization: statewide prospective active case finding study.

BACKGROUND: An easily accessible real-time Web-based utility to assess patient risks of future emergency department (ED) visits can help the health care provider guide the allocation of resources to better manage higher-risk patient populations and thereby reduce unnecessary use of EDs. OBJECTIVE: Our main objective was to develop a Health Information Exchange-based, next 6-month ED risk surveillance system in the state of Maine. METHODS: Data on electronic medical record (EMR) encounters integrated by HealthInfoNet (HIN), Maine's Health Information Exchange, were used to develop the Web-based surveillance system for a population ED future 6-month risk prediction. To model, a retrospective cohort of 829,641 patients with comprehensive clinical histories from January 1 to December 31, 2012 was used for training and then tested with a prospective cohort of 875,979 patients from July 1, 2012, to June 30, 2013. RESULTS: The multivariate statistical analysis identified 101 variables predictive of future defined 6-month risk of ED visit: 4 age groups, history of 8 different encounter types, history of 17 primary and 8 secondary diagnoses, 8 specific chronic diseases, 28 laboratory test results, history of 3 radiographic tests, and history of 25 outpatient prescription medications. The c-statistics for the retrospective and prospective cohorts were 0.739 and 0.732 respectively. Integration of our method into the HIN secure statewide data system in real time prospectively validated its performance. Cluster analysis in both the retrospective and prospective analyses revealed discrete subpopulations of high-risk patients, grouped around multiple "anchoring" demographics and chronic conditions. With the Web-based population risk-monitoring enterprise dashboards, the effectiveness of the active case finding algorithm has been validated by clinicians and caregivers in Maine. CONCLUSIONS: The active case finding model and associated real-time Web-based app were designed to track the evolving nature of total population risk, in a longitudinal manner, for ED visits across all payers, all diseases, and all age groups. Therefore, providers can implement targeted care management strategies to the patient subgroups with similar patterns of clinical histories, driving the delivery of more efficient and effective health care interventions. To the best of our knowledge, this prospectively validated EMR-based, Web-based tool is the first one to allow real-time total population risk assessment for statewide ED visits.

Risk prediction of emergency department revisit 30 days post discharge: a prospective study.

BACKGROUND: Among patients who are discharged from the Emergency Department (ED), about 3% return within 30 days. Revisits can be related to the nature of the disease, medical errors, and/or inadequate diagnoses and treatment during their initial ED visit. Identification of high-risk patient population can help device new strategies for improved ED care with reduced ED utilization. METHODS AND FINDINGS: A decision tree based model with discriminant Electronic Medical Record (EMR) features was developed and validated, estimating patient ED 30 day revisit risk. A retrospective cohort of 293,461 ED encounters from HealthInfoNet (HIN), Maine's Health Information Exchange (HIE), between January 1, 2012 and December 31, 2012, was assembled with the associated patients' demographic information and one-year clinical histories before the discharge date as the inputs. To validate, a prospective cohort of 193,886 encounters between January 1, 2013 and June 30, 2013 was constructed. The c-statistics for the retrospective and prospective predictions were 0.710 and 0.704 respectively. Clinical resource utilization, including ED use, was analyzed as a function of the ED risk score. Cluster analysis of high-risk patients identified discrete sub-populations with distinctive demographic, clinical and resource utilization patterns. CONCLUSIONS: Our ED 30-day revisit model was prospectively validated on the Maine State HIN secure statewide data system. Future integration of our ED predictive analytics into the ED care work flow may lead to increased opportunities for targeted care intervention to reduce ED resource burden and overall healthcare expense, and improve outcomes.

AKI in hospitalized children: epidemiology and clinical associations in a national cohort.

BACKGROUND AND OBJECTIVES: Although AKI is common among hospitalized children, comprehensive epidemiologic data are lacking. This study characterizes pediatric AKI across the United States and identifies AKI risk factors using high-content/high-throughput analytic techniques. DESIGN, SETTING, PARTICIPANTS, & MEASUREMENTS: For the cross-sectional analysis of the 2009 Kids Inpatient Database, AKI events were identified using International Classification of Diseases, Ninth Revision, Clinical Modification codes. Demographics, incident rates, and outcome data were analyzed and reported for the entire AKI cohort as well as AKI subsets. Statistical learning methods were applied to the highly imbalanced dataset to derive AKI-related risk factors. RESULTS: Of 2,644,263 children, 10,322 children developed AKI (3.9/1000 admissions). Although 19% of the AKI cohort was ≤ 1 month old, the highest incidence was seen in children 15-18 years old (6.6/1000 admissions); 49% of the AKI cohort was white, but AKI incidence was higher among African Americans (4.5 versus 3.8/1000 admissions). In-hospital mortality among patients with AKI was 15.3% but higher among children ≤ 1 month old (31.3% versus 10.1%, P<0.001) and children requiring critical care (32.8% versus 9.4%, P<0.001) or dialysis (27.1% versus 14.2%, P<0.001). Shock (odds ratio, 2.15; 95% confidence interval, 1.95 to 2.36), septicemia (odds ratio, 1.37; 95% confidence interval, 1.32 to 1.43), intubation/mechanical ventilation (odds ratio, 1.2; 95% confidence interval, 1.16 to 1.25), circulatory disease (odds ratio, 1.47; 95% confidence interval, 1.32 to 1.65), cardiac congenital anomalies (odds ratio, 1.2; 95% confidence interval, 1.13 to 1.23), and extracorporeal support (odds ratio, 2.58; 95% confidence interval, 2.04 to 3.26) were associated with AKI. CONCLUSIONS: AKI occurs in 3.9/1000 at-risk US pediatric hospitalizations. Mortality is highest among neonates and children requiring critical care or dialysis. Identified risk factors suggest that AKI occurs in association with systemic/multiorgan disease more commonly than primary renal disease.

Embedding time-limited laboratory orders within computerized provider order entry reduces laboratory utilization.

OBJECTIVES: To test the hypothesis that limits on repeating laboratory studies within computerized provider order entry decrease laboratory utilization. DESIGN: Cohort study with historical controls. SETTING: A 20-bed PICU in a freestanding, quaternary care, academic children's hospital. PATIENTS: This study included all patients admitted to the pediatric ICU between January 1, 2008, and December 31, 2009. A total of 818 discharges were evaluated prior to the intervention (January 1, 2008, through December 31, 2008) and 1,021 patient discharges were evaluated postintervention (January 1, 2009, through December 31, 2009). INTERVENTION: A computerized provider order entry rule limited the ability to schedule repeating complete blood cell counts, chemistry, and coagulation studies to a 24-hour interval in the future. The time limit was designed to ensure daily evaluation of the utility of each test. MEASUREMENTS AND MAIN RESULTS: Initial analysis with t tests showed significant decreases in tests per patient day in the postintervention period (complete blood cell counts: 1.5 ± 0.1 to 1.0 ± 0.1; chemistry: 10.6 ± 0.9 to 6.9 ± 0.6; coagulation: 3.3 ± 0.4 to 1.7 ± 0.2; p < 0.01, all variables vs. preintervention period). Even after incorporating a trend toward decreasing laboratory utilization in the preintervention period into our regression analysis, the intervention decreased complete blood cell counts (p = 0.007), chemistry (p = 0.049), and coagulation (p = 0.001) tests per patient day. CONCLUSIONS: Limits on laboratory orders within the context of computerized provider order entry decreased laboratory utilization without adverse affects on mortality or length of stay. Broader application of this strategy might decrease costs, the incidence of iatrogenic anemia, and catheter-associated bloodstream infections.

Using an Evidence-Based Approach to EMR Implementation to Optimize Outcomes and Avoid Unintended Consequences.

Implementation of an electronic medical record (EMR) with computerized physician order entry (CPOE) can provide an important foundation for preventing harm and improving outcomes. Incentivized by the recent economic stimulus initiative, healthcare systems are implementing vendor-based EMR systems at an unprecedented rate. Accumulating evidence suggests that local implementation decisions, rather than the specific EMR product or technology selected, are the primary drivers of the quality improvement performance of these systems. However, limited attention has been paid to effective approaches to EMR implementation. In this case report, we outline the evidence-based approach we used to make EMR implementation decisions in a pragmatic structure intended for replication at other sites.