Using Artificial Intelligence With Natural Language Processing to Combine Electronic Health Record's Structured and Free Text Data to Identify Nonvalvular Atrial Fibrillation to Decrease Strokes and Death: Evaluation and Case-Control Study.

BACKGROUND: Nonvalvular atrial fibrillation (NVAF) affects almost 6 million Americans and is a major contributor to stroke but is significantly undiagnosed and undertreated despite explicit guidelines for oral anticoagulation. OBJECTIVE: The aim of this study is to investigate whether the use of semisupervised natural language processing (NLP) of electronic health record's (EHR) free-text information combined with structured EHR data improves NVAF discovery and treatment and perhaps offers a method to prevent thousands of deaths and save billions of dollars. METHODS: We abstracted 96,681 participants from the University of Buffalo faculty practice's EHR. NLP was used to index the notes and compare the ability to identify NVAF, congestive heart failure, hypertension, age ≥75 years, diabetes mellitus, stroke or transient ischemic attack, vascular disease, age 65 to 74 years, sex category (CHA2DS2-VASc), and Hypertension, Abnormal liver/renal function, Stroke history, Bleeding history or predisposition, Labile INR, Elderly, Drug/alcohol usage (HAS-BLED) scores using unstructured data (International Classification of Diseases codes) versus structured and unstructured data from clinical notes. In addition, we analyzed data from 63,296,120 participants in the Optum and Truven databases to determine the NVAF frequency, rates of CHA2DS2­VASc ≥2, and no contraindications to oral anticoagulants, rates of stroke and death in the untreated population, and first year's costs after stroke. RESULTS: The structured-plus-unstructured method would have identified 3,976,056 additional true NVAF cases (P<.001) and improved sensitivity for CHA2DS2-VASc and HAS-BLED scores compared with the structured data alone (P=.002 and P<.001, respectively), causing a 32.1% improvement. For the United States, this method would prevent an estimated 176,537 strokes, save 10,575 lives, and save >US $13.5 billion. CONCLUSIONS: Artificial intelligence-informed bio-surveillance combining NLP of free-text information with structured EHR data improves data completeness, prevents thousands of strokes, and saves lives and funds. This method is applicable to many disorders with profound public health consequences.

Can billing codes accurately identify rapidly progressing stage 3 and stage 4 chronic kidney disease patients: a diagnostic test study.

BACKGROUND: The International Classification of Diseases (ICD) coding system is the industry standard tool for billing, disease classification, and epidemiology purposes. However, ICD codes are often not assigned or incorrectly given, particularly among Chronic Kidney disease (CKD) patients. Our study evaluated the diagnostic accuracy of CKD-staging ICD codes among CKD patients from a large insurer database in identifying individuals rapidly progressing towards end-stage renal disease (ESRD). PATIENTS AND METHODS: Serial observations including outpatient serum creatinine measurements collected from 2007 through 2014 of 216,529 patients were examined. The progression of CKD using a serum creatinine based longitudinal mixed-model was contrasted with that documented by CKD-staging ICD codes. Rapid progressors, defined as those with yearly estimated glomerular filtration rate (eGFR) loss greater than 4 ml/min/1.73m2) were identified. The diagnosis of CKD using eGFR was also compared to diagnosis using a set of CKD related ICD codes. RESULTS: Of 10,927 clinically identified CKD patients qualifying for inclusion in the progression analysis, 323 were clinically identified as rapid progressors. CKD-staging ICD codes identified 83 of these, for a sensitivity of 25.7% with positive predictive value (PPV) of 13.74%, and specificity 95.09% with negative predictive value (NPV) of 97.68%. Of 28,762 laboratory-confirmed CKD patients, 9249 had a qualifying ICD code, for a sensitivity of 16% with PPV of 63.10%; Of 187,767 patients with laboratory-confirmed absence of CKD, 182,359 also did not have a qualifying ICD code, for a specificity of 97.12% with NPV of 90.33%. CONCLUSION: This study depicts the novel finding that ICD-codes display poor capacity to identify rapidly progressing CKD patients when compared to gold standard eGFR measures, and further demonstrates the limitations of coding in CKD diagnosis. This analysis further defines the limitations of ICD codes in addressing diagnosis of disease severity or disease progression for clinical or epidemiological purposes.

Secondary Use of EHR: Interpreting Clinician Inter-Rater Reliability Through Qualitative Assessment.

In a retrospective secondary-use EHR study identifying a cohort of Non-Valvular Atrial Fibrillation (NVAF) patients, chart abstraction was done by two sets of clinicians to create a gold standard for risk measures CHA2DS2-VASc and HAS-BLED. Inter-rater reliability between each set of clinicians for NVAF and the outcomes of interest were variable, ranging from extremely low agreement to high agreement. To assess the chart abstraction process, a focus group and a survey was conducted. Survey findings revealed patterns of difficulty in assessing certain items dealing with temporality and social data. The focus group raised issues on the quality and completeness of EHR data, including missing encounters, truncated notes, and low granularity. It also raised the issue of the usability of the data system, the Clinical Data Viewer, which did not mirror a live EHR and made it difficult to record outcomes. Finally, the focus group found it was difficult to infer certain outcomes, like severity, from the provided data. These factors produced differences in clinician rated outcomes.

Preoperative serum potassium predicts the clinical outcome after non-cardiac surgery.

BACKGROUND: Potassium disorders have been linked to adverse outcomes in various medical conditions. However, the association of preoperative serum potassium with postoperative outcome is not well established. We aimed to examine the association between preoperative potassium with a 30-day mortality and adverse cardiovascular event (MACE). METHODS: We conducted a cohort study using a prospectively collected database of patients, undergoing surgical procedures from 1998 to 2013 in the VA Western New York Healthcare System, which are reported to the Veterans Affairs Surgical Quality Improvement Program (VASQIP). The patients were categorized into three groups based on their documented preoperative potassium concentrations. Hypokalemia was defined as serum potassium concentration <4 mmol/L and hyperkalemia was defined as serum potassium concentrations >5.5 mmol/L. The values within the range of 4.0-5.5 mmol/L were considered as normokalemia and used as the control group. Statistical analyses included Chi-square test, analysis of variance and multivariate logistic regression to estimate the risk of MACE within 30 days of surgery. RESULTS: Study included 5959 veterans who underwent surgery between 1998 and 2013. The patients in the hyperkalemics group had lower kidney function compared to the other two groups. The frequency of MACE was 13.6% in hypokalemics and 21.9% in hyperkalemics that were both significantly higher than 4.9% in controls. In multivariate logistic regression the hazard risk (HR) ratios of MACE were (2.17, 95% CI 1.75-2.70) for hypokalemics and (3.23, 95% CI 2.10-4.95) for hyperkalemics when compared to normokalemic controls. CONCLUSIONS: Preoperative hypokalemia and hyperkalemia are both independent predictors of MACE within 30 days.

Barriers, Facilitators, and Solutions to Optimal Patient Portal and Personal Health Record Use: A Systematic Review of the Literature.

Patient portal and personal health record adoption and usage rates have been suboptimal. A systematic review of the literature was performed to capture all published studies that specifically addressed barriers, facilitators, and solutions to optimal patient portal and personal health record enrollment and use. Consistent themes emerged from the review. Patient attitudes were critical as either barrier or facilitator. Institutional buy-in, information technology support, and aggressive tailored marketing were important facilitators. Interface redesign was a popular solution. Quantitative studies identified many barriers to optimal patient portal and personal health record enrollment and use, and qualitative and mixed methods research revealed thoughtful explanations for why they existed. Our study demonstrated the value of qualitative and mixed research methodologies in understanding the adoption of consumer health technologies. Results from the systematic review should be used to guide the design and implementation of future patient portals and personal health records, and ultimately, close the digital divide.

Referral to nephrologists for chronic kidney disease care: is non-diabetic kidney disease ignored?

BACKGROUND: Late referral to nephrologists is common and associated with increased morbidity and mortality. We aimed to analyze the prevalence rates, predictors and consequences of late referral to nephrologists by primary care physicians for chronic kidney disease (CKD) care. METHODS: A retrospective analysis of 204 patients started on dialysis for CKD in two community hospitals between March 2003 and March 2005 was conducted. Relevant clinical and laboratory data were obtained from the patient records of the nephrology clinics and dialysis units. Patients referred in CKD stage 5 (estimated glomerular filtration rate <15 ml/min) were defined as late referral and patients in CKD stage 1-4 (estimated glomerular filtration rate >15 ml/min) as early referral. RESULTS: Forty-five (22%) of the 204 patients were referred late. In the multivariate analysis, non-diabetic kidney disease (odds ratio = 2.46, p = 0.02) and Charlson comorbidity index (odds ratio = 1.17, p = 0.009) were significantly associated with late referral. The late referral group had lower hematocrit and serum calcium levels, and higher serum phosphorus and parathyroid hormone levels than the early referral group (p < or =0.05) at the time of referral. Late referral resulted in less permanent vascular access for initiation of dialysis (p = 0.03). Even though there was twice the number of deaths in the late referral group in 1 year (18 vs. 9%), this was not statistically significant (p = 0.07). CONCLUSION: Referring physicians should pay special attention to patients with non-diabetic kidney disease and patients with multiple comorbidities since delayed referral to nephrologists may result in poorer patient-related outcomes. Larger and long-term prospective studies analyzing the long-term consequences of late referral to nephrologists are needed.