Shiying Hao

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.

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.

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.

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.

Unique Molecular Patterns Uncovered in Kawasaki Disease Patients with Elevated Serum Gamma Glutamyl Transferase Levels: Implications for Intravenous Immunoglobulin Responsiveness.

Background Resistance to intravenous immunoglobulin (IVIG) occurs in 10–20% of patients with Kawasaki disease (KD). The risk of resistance is about two-fold higher in patients with elevated gamma glutamyl transferase (GGT) levels. We sought to understand the biological mechanisms underlying IVIG resistance in patients with elevated GGT levels. Method We explored the association between elevated GGT levels and IVIG-resistance with a cohort of 686 KD patients (Cohort I). Gene expression data from 130 children with acute KD (Cohort II) were analyzed using the R square statistic and false discovery analysis to identify genes that were differentially represented in patients with elevated GGT levels with regard to IVIG responsiveness. Two additional KD cohorts (Cohort III and IV) were used to test the hypothesis that sialylation and GGT may be involved in IVIG resistance through neutrophil apoptosis. Results Thirty-six genes were identified that significantly explained the variations of both GGT levels and IVIG responsiveness in KD patients. After Bonferroni correction, significant associations with IVIG resistance persisted for 12 out of 36 genes among patients with elevated GGT levels and none among patients with normal GGT levels. With the discovery of ST6GALNAC3, a sialyltransferase, as the most differentially expressed gene, we hypothesized that sialylation and GGT are involved in IVIG resistance through neutrophil apoptosis. We then confirmed that in Cohort III and IV there was significantly less reduction in neutrophil count in IVIG non-responders. Conclusions Gene expression analyses combining molecular and clinical datasets support the hypotheses that: (1) neutrophil apoptosis induced by IVIG may be a mechanism of action of IVIG in KD; (2) changes in sialylation and GGT level in KD patients may contribute synergistically to IVIG resistance through blocking IVIG-induced neutrophil apoptosis. These findings have implications for understanding the mechanism of action in IVIG resistance, and possibly for development of novel therapeutics.

Utility of clinical biomarkers to predict central line-associated bloodstream infections after congenital heart surgery.

Background: Central line-associated bloodstream infections is an important contributor of morbidity and mortality in children recovering from congenital heart surgery. The reliability of commonly used biomarkers to differentiate these patients has not been specifically studied. Methods: This was a retrospective cohort study in a university-affiliated children’s hospital examining all patients with congenital or acquired heart disease admitted to the cardiovascular intensive care unit after cardiac surgery who underwent evaluation for a catheter-associated bloodstream infection. Results: Among 1260 cardiac surgeries performed, 451 encounters underwent an infection evaluation postoperatively. Twenty-five instances of central line-associated blood stream infections (CLABSI) and 227 instances of a negative infection evaluation were the subject of analysis. Patients with CLABSI tended to be younger (1.34 vs. 4.56 years, P = 0.011) and underwent more complex surgery (RACHS-1 score 3.79 vs. 3.04, P = 0.039). The 2 groups were indistinguishable in white blood cell, polymorphonuclears and band count at the time of their presentation. On multivariate analysis, CLABSI was associated with fever (adjusted odds ratio: 4.78; 95% CI: 1.6–5.8) and elevated C-reactive protein (CRP; adjusted odds ratio: 1.28; 95% CI: 1.09–1.68) after adjusting for differences between the 2 groups. Receiver-operating characteristic analysis demonstrated the discriminatory power of both fever and CRP (area under curve 0.7247, 95% CI: 0.42 to 0.74 and 0.58, 95% CI: 0.4208 to 0.7408). We calculated multilevel likelihood ratios for a spectrum of temperature and CRP values. Conclusions: We found commonly used serum biomarkers such as fever and CRP not to be helpful discriminators in patients after congenital heart surgery.

Exploring the Role of Polycythemia in Patients With Cyanosis After Palliative Congenital Heart Surgery.

Objectives: To understand the relationship between polycythemia and clinical outcome in patients with hypoplastic left heart syndrome following the Norwood operation. Design: A retrospective, single-center cohort study. Setting: Pediatric cardiovascular ICU, university-affiliated children’s hospital. Patients: Infants with hypoplastic left heart syndrome admitted to our medical center from September 2009 to December 2012 undergoing stage 1/Norwood operation. Interventions: None. Measurements and Main Results: Baseline demographic and clinical information including first recorded postoperative hematocrit and subsequent mean, median, and nadir hematocrits during the first 72 hours postoperatively were recorded. The primary outcomes were in-hospital mortality and length of hospitalization. Thirty-two patients were included in the analysis. Patients did not differ by operative factors (cardiopulmonary bypass time and cross-clamp time) or traditional markers of severity of illness (vasoactive inotrope score, lactate, saturation, and PaO2/FIO2 ratio). Early polycythemia (hematocrit value > 49%) was associated with longer cardiovascular ICU stay (51.0 [± 38.6] vs 21.4 [± 16.2] d; p < 0.01) and total hospital length of stay (65.0 [± 46.5] vs 36.1 [± 20.0] d; p = 0.03). In a multivariable analysis, polycythemia remained independently associated with the length of hospitalization after controlling for the amount of RBC transfusion (weight, 4.36 [95% CI, 1.35–7.37]; p < 0.01). No difference in in-hospital mortality rates was detected between the two groups (17.6% vs 20%). Conclusions: Early polycythemia following the Norwood operation is associated with longer length of hospitalization even after controlling for blood cell transfusion practices. We hypothesize that polycythemia may be caused by hemoconcentration and used as an early marker of capillary leak syndrome.

Urinary Colorimetric Sensor Array and Algorithm to Distinguish Kawasaki Disease from Other Febrile Illnesses

Objectives Kawasaki disease (KD) is an acute pediatric vasculitis of infants and young children with unknown etiology and no specific laboratory-based test to identify. A specific molecular diagnostic test is urgently needed to support the clinical decision of proper medical intervention, preventing subsequent complications of coronary artery aneurysms. We used a simple and low-cost colorimetric sensor array to address the lack of a specific diagnostic test to differentiate KD from febrile control (FC) patients with similar rash/fever illnesses. Study Design Demographic and clinical data were prospectively collected for subjects with KD and FCs under standard protocol. After screening using a genetic algorithm, eleven compounds including metalloporphyrins, pH indicators, redox indicators and solvatochromic dye categories, were selected from our chromatic compound library (n = 190) to construct a colorimetric sensor array for diagnosing KD. Quantitative color difference analysis led to a decision-tree-based KD diagnostic algorithm. Results This KD sensing array allowed the identification of 94% of KD subjects (receiver operating characteristic [ROC] area under the curve [AUC] 0.981) in the training set (33 KD, 33 FC) and 94% of KD subjects (ROC AUC: 0.873) in the testing set (16 KD, 17 FC). Color difference maps reconstructed from the digital images of the sensing compounds demonstrated distinctive patterns differentiating KD from FC patients. Conclusions The colorimetric sensor array, composed of common used chemical compounds, is an easily accessible, low-cost method to realize the discrimination of subjects with KD from other febrile illness.

Changes in pregnancy-related serum biomarkers early in gestation are associated with later development of preeclampsia

Background Placental protein expression plays a crucial biological role during normal and complicated pregnancies. We hypothesized that: (1) circulating pregnancy-associated, placenta-related protein levels throughout gestation reflect the uncomplicated, full-term temporal progression of human gestation, and effectively estimates gestational ages (GAs); (2) pregnancies with underlying placental pathology, such as preeclampsia (PE), are associated with disruptions in this GA estimation in early gestation; (3) malfunctions of this GA estimation can be employed to identify impending PE. In addition, to explore the underlying biology and PE etiology, we set to compare protein gestational patterns of human and mouse, using pregnant heme oxygenase-1 (HO-1) heterozygote (Het) mice, a mouse model reflecting PE-like symptoms. Methods Serum levels of circulating placenta-related proteins – leptin (LEP), chorionic somatomammotropin hormone like 1 (CSHL1), elabela (ELA), activin A, soluble fms-like tyrosine kinase 1 (sFlt-1), and placental growth factor (PlGF)– were quantified by ELISA in blood serially collected throughout human pregnancies (20 normal subjects with 66 samples, and 20 PE subjects with 61 samples). Linear multivariate analysis of the targeted serological protein levels was performed to estimate the normal GA. Logarithmic transformed mean-squared errors of GA estimations were used to identify impending PE. Then the human gestational protein patterns were compared to those in the pregnant HO-1 mice. Results An elastic net (EN)-based gestational dating model was developed (R2 = 0.76) and validated (R2 = 0.61) using the serum levels of the 6 proteins at various GAs from women with normal uncomplicated pregnancies (n = 10 for training and n = 6 for validation). In pregnancies complicated by PE (n = 14), the EN model was not (R2 = −0.17) associated with GA at sampling in PE. Statistically significant deviations from the normal GA EN model estimations were observed in PE-associated pregnancies between GAs of 16–30 weeks (P = 0.01). The EN model developed with 5 proteins (ELA excluded due to the lack of robustness of the mouse ELA essay) performed similarly on normal human (R2 = 0.68) and WT mouse (R2 = 0.85) pregnancies. Disruptions of this model were observed in both human PE-associated (human: R2 = 0.27) and mouse HO-1 Het (mouse: R2 = 0.30) pregnancies. LEP out performed sFlt-1 and PlGF in differentiating impending PE at early human and late mouse gestations. Conclusions As revealed in both human and mouse GA EN analyses, temporal serological placenta-related protein patterns are tightly regulated throughout normal human pregnancies and can be significantly disrupted in pathologic PE states. LEP changes earlier during gestation than the well-established late GA PE biomarkers (sFlt-1 and PlGF). Our HO-1 Het mouse analysis provides direct evidence of the causative action of HO-1 deficiency in LEP upregulation in a PE-like murine model. Therefore, longitudinal analyses of pregnancy-related protein patterns in sera, may not only help in the exploration of underlying PE pathophysiology but also provide better clinical utility in PE assessment.