Identification of Wernicke Encephalopathy in a Patient Presenting With Altered Mental Status and Dehydration.

INTRODUCTION: Providing glucose before thiamine can cause or exacerbate Wernicke encephalopathy, a potentially life-threatening condition associated with a variety of neurological impairments. CASE PRESENTATION: An emaciated, middle-aged woman with a longstanding history of alcohol abuse and an undifferentiated seizure disorder presented to a local emergency department with altered mental status of unknown duration. Initial labs showed signs of acute kidney injury and she could not tolerate oral intake. Overnight, dextrose-containing maintenance fluids were started. The next day, she had an acute deterioration of mental status. Empiric therapy for Wernicke encephalopathy was begun, resulting in resolution of most of her symptoms over a matter of days. DISCUSSION: It is generally recommended to administer thiamine treatment prior to glucose in patients with suspected thiamine deficiency. The Caine criteria can assist in the decision to start empiric treatment to prevent delays in thiamine therapy. CONCLUSION: Wernicke encephalopathy is a disease with high morbidity that is usually treated with the generally benign therapy of thiamine. Given the risk of harm of untreated Wernicke encephalopathy and the benign nature of treatment, clinicians should have a low threshold to provide thiamine therapy.

An Unusual Case of Blastomycosis and Severe Lung Necrosis in a Hmong Woman With Preexisting Liver Cirrhosis.

Predisposing factors that lead to blastomycosis remain unknown, although like other fungal infections, blastomycosis is an opportunistic infection. Here, we report on an unusual presentation in a Hmong woman with preexisting liver disease. This case highlights genetic and medical factors that may increase susceptibility to blastomycosis.

Pericarditis as a Secondary Complication of COVID-19 in a Renal Transplant Patient.

INTRODUCTION: A wide range of complications from COVID-19 are being reported, including cardiac complications. CASE PRESENTATION: A 71-year-old woman with systemic lupus erythematosus complicated by focal segmental glomerular sclerosis status post kidney transplant presented with worsening left-sided chest pain after receiving treatment for COVID-19 pneumonia at an outside hospital. She was subsequently diagnosed with acute pericarditis, likely secondary to viral infection with COVID-19, and was successfully treated with aspirin and colchicine for 90 days without complications. DISCUSSION: NSAIDs and colchicine are mainstays in acute pericarditis treatment. Though treatment presented a potential challenge given this patient's prior kidney transplant, aspirin and colchicine proved to be effective in treating her case of COVID-19-associated pericarditis. CONCLUSION: This report has implications for future treatment of renal transplant patients with COVID-19-related pericarditis and emphasizes the need for research into the pathophysiology of pericarditis in the context of COVID-19, including risk factors and treatment.

Extraction of Geriatric Syndromes From Electronic Health Record Clinical Notes: Assessment of Statistical Natural Language Processing Methods.

BACKGROUND: Geriatric syndromes in older adults are associated with adverse outcomes. However, despite being reported in clinical notes, these syndromes are often poorly captured by diagnostic codes in the structured fields of electronic health records (EHRs) or administrative records. OBJECTIVE: We aim to automatically determine if a patient has any geriatric syndromes by mining the free text of associated EHR clinical notes. We assessed which statistical natural language processing (NLP) techniques are most effective. METHODS: We applied conditional random fields (CRFs), a widely used machine learning algorithm, to identify each of 10 geriatric syndrome constructs in a clinical note. We assessed three sets of features and attributes for CRF operations: a base set, enhanced token, and contextual features. We trained the CRF on 3901 manually annotated notes from 85 patients, tuned the CRF on a validation set of 50 patients, and evaluated it on 50 held-out test patients. These notes were from a group of US Medicare patients over 65 years of age enrolled in a Medicare Advantage Health Maintenance Organization and cared for by a large group practice in Massachusetts. RESULTS: A final feature set was formed through comprehensive feature ablation experiments. The final CRF model performed well at patient-level determination (macroaverage F1=0.834, microaverage F1=0.851); however, performance varied by construct. For example, at phrase-partial evaluation, the CRF model worked well on constructs such as absence of fecal control (F1=0.857) and vision impairment (F1=0.798) but poorly on malnutrition (F1=0.155), weight loss (F1=0.394), and severe urinary control issues (F1=0.532). Errors were primarily due to previously unobserved words (ie, out-of-vocabulary) and a lack of context. CONCLUSIONS: This study shows that statistical NLP can be used to identify geriatric syndromes from EHR-extracted clinical notes. This creates new opportunities to identify patients with geriatric syndromes and study their health outcomes.

The Value of Unstructured Electronic Health Record Data in Geriatric Syndrome Case Identification.

OBJECTIVES: To examine the value of unstructured electronic health record (EHR) data (free-text notes) in identifying a set of geriatric syndromes. DESIGN: Retrospective analysis of unstructured EHR notes using a natural language processing (NLP) algorithm. SETTING: Large multispecialty group. PARTICIPANTS: Older adults (N=18,341; average age 75.9, 58.9% female). MEASUREMENTS: We compared the number of geriatric syndrome cases identified using structured claims and structured and unstructured EHR data. We also calculated these rates using a population-level claims database as a reference and identified comparable epidemiological rates in peer-reviewed literature as a benchmark. RESULTS: Using insurance claims data resulted in a geriatric syndrome prevalence ranging from 0.03% for lack of social support to 8.3% for walking difficulty. Using structured EHR data resulted in similar prevalence rates, ranging from 0.03% for malnutrition to 7.85% for walking difficulty. Incorporating unstructured EHR notes, enabled by applying the NLP algorithm, identified considerably higher rates of geriatric syndromes: absence of fecal control (2.1%, 2.3 times as much as structured claims and EHR data combined), decubitus ulcer (1.4%, 1.7 times as much), dementia (6.7%, 1.5 times as much), falls (23.6%, 3.2 times as much), malnutrition (2.5%, 18.0 times as much), lack of social support (29.8%, 455.9 times as much), urinary retention (4.2%, 3.9 times as much), vision impairment (6.2%, 7.4 times as much), weight loss (19.2%, 2.9 as much), and walking difficulty (36.34%, 3.4 as much). The geriatric syndrome rates extracted from structured data were substantially lower than published epidemiological rates, although adding the NLP results considerably closed this gap. CONCLUSION: Claims and structured EHR data give an incomplete picture of burden related to geriatric syndromes. Geriatric syndromes are likely to be missed if unstructured data are not analyzed. Pragmatic NLP algorithms can assist with identifying individuals at high risk of experiencing geriatric syndromes and improving coordination of care for older adults.

Comparative Cost Analysis of Clinical Reminder for HIV Testing at the Veterans Affairs Healthcare System.

OBJECTIVE: To estimate the cost and health outcomes associated with a new HIV testing strategy that utilizes routine-based clinical reminders. METHODS: We conducted an economic analysis of 1) traditional pretest/post-test counseling; 2) counseling and a new clinical reminders system; and 3) only clinical reminder in the veterans' health care system. A payer-perspective decision model was conducted to calculate the 1-year budget impact of three HIV testing strategies. Parameter values were obtained from the literature, including patients' probability of accepting test, and costs associated with HIV testing procedures. Deidentified patient data, including total population screened and number of new HIV cases, were collected from one clinic in Los Angeles, California, from August 2004 to December 2011. Annual total costs and costs per new case were calculated on the basis of parameter values and patient data. Sensitivity analyses were conducted to evaluate the robustness of the critical variable on costs. RESULTS: The total cost of the clinical reminder system with pretest counseling was $81,726 over 1 year compared with $109,208 for traditional HIV testing. Under a clinical reminder system with no pretest counseling, the number of HIV tests performed and the number of new diagnoses increased for that year. In addition, cost per new diagnoses was the lowest. CONCLUSIONS: The clinical reminder system can reduce the cost per cases identified and promote better performance of HIV testing compared with traditional HIV testing. The fundamental decision model can be used for hospital facilities outside the Veteran Affairs adopting a similar program for improving the HIV testing rate.