Evaluation of machine learning methodology for the prediction of healthcare resource utilization and healthcare costs in patients with critical limb ischemia-is preventive and personalized approach on the horizon?

BACKGROUND: Critical limb ischemia (CLI) is a severe stage of peripheral arterial disease and has a substantial disease and economic burden not only to patients and families, but also to the society and healthcare systems. We aim to develop a personalized prediction model that utilizes baseline patient characteristics prior to CLI diagnosis to predict subsequent 1-year all-cause hospitalizations and total annual healthcare cost, using a novel Bayesian machine learning platform, Reverse Engineering Forward Simulation™ (REFS™), to support a paradigm shift from reactive healthcare to Predictive Preventive and Personalized Medicine (PPPM)-driven healthcare. METHODS: Patients ≥ 50 years with CLI plus clinical activity for a 6-month pre-index and a 12-month post-index period or death during the post-index period were included in this retrospective cohort of the linked Optum-Humedica databases. REFS™ built an ensemble of 256 predictive models to identify predictors of all-cause hospitalizations and total annual all-cause healthcare costs during the 12-month post-index interval. RESULTS: The mean age of 3189 eligible patients was 71.9 years. The most common CLI-related comorbidities were hypertension (79.5%), dyslipidemia (61.4%), coronary atherosclerosis and other heart disease (42.3%), and type 2 diabetes (39.2%). Post-index CLI-related healthcare utilization included inpatient services (14.6%) and ≥ 1 outpatient visits (32.1%). Median annual all-cause and CLI-related costs per patient were $30,514 and $2196, respectively. REFS™ identified diagnosis of skin and subcutaneous tissue infections, cellulitis and abscess, use of nonselective beta-blockers, other aftercare, and osteoarthritis as high confidence predictors of all-cause hospitalizations. The leading predictors for total all-cause costs included region of residence and comorbid health conditions including other diseases of kidney and ureters, blindness of vision defects, chronic ulcer of skin, and chronic ulcer of leg or foot. CONCLUSIONS: REFS™ identified baseline predictors of subsequent healthcare resource utilization and costs in CLI patients. Machine learning and model-based, data-driven medicine may complement physicians' evidence-based medical services. These findings also support the PPPM framework that a paradigm shift from post-diagnosis disease care to early management of comorbidities and targeted prevention is warranted to deliver a cost-effective medical services and desirable healthcare economy.

The Effect of Implementing Gene Expression Classifier on Outcomes of Thyroid Nodules with Indeterminate Cytology.

Thyroid nodules are classified into six cytological categories under the Bethesda classification system. Two of these categories, atypical of undetermined significance (AUS) and suspicious for a follicular neoplasm (SFN), are further labeled as "indeterminate" diagnosis. Starting in June, 2012, Kansas University-Wichita Endocrine clinic implemented Afirma® Gene Expression Classifier (AGEC) to evaluate the need for surgical resection of thyroid nodules in patients with an indeterminate diagnosis. Electronic medical records of patients who underwent thyroid nodule fine-needle aspiration from 2004-2014 were reviewed. The aim of this study was to find whether implementing AGEC was associated with decreased surgical recommendation rate, decreased cost, and increased incidence of thyroid malignancy diagnosed by surgery in patients with indeterminate diagnosis. A total of 299 consecutive patients' charts were screened. Sixty-one (20 %) patients had an indeterminate diagnosis. Out of these, 27 (44 %) patients underwent evaluation before and 34 (56 %) patients underwent evaluation after AGEC implementation, respectively. Surgical recommendation for patients with indeterminate finding decreased from 81.5 to 50 % (p = 0.01) after AGEC implementation. Surgical pathology was read as malignant in 20 and 85.7 % (p < 0.01) of patients before and after AGEC implementation, respectively. Primary cost-benefit estimate showed implementing AGEC has saved $1048/patient in medical evaluation and initial management of patients with indeterminate diagnosis. AGEC implementation has decreased the number of surgical recommendations, has lowered financial burden, and has increased incidence of thyroid malignancy diagnosed by surgical pathology in patients with indeterminate diagnosis of thyroid nodules.

Readability of state-sponsored advance directive forms in the United States: a cross sectional study.

BACKGROUND: State governments provide preprinted advance directive forms to the general public. However, many adults in the United States (US) lack the skills necessary to read and comprehend health care-related materials. In this study, we sought to determine the readability of state government-sponsored advance directive forms. METHODS: A cross sectional study design was used. The readability of advance directive forms available online from all 50 US states and the District of Columbia was determined using 6 validated readability scales. RESULTS: Overall, 62 advance directive forms were obtained. For 47 states, forms were available by way of government-sponsored Web sites. The average (SD) readability (with the Flesch-Kincaid score) of all forms was grade level 11.9 (2.6). Similar results were obtained with the other readability scales. No form had a readability score at the 5th grade level or lower, the level recommended by the National Work Group on Literacy and Health. The readability of the forms exceeded this level by an average of 6.9 grade levels (95% confidence interval, 6.3-7.6; P < .001). Only 5 of the forms had a readability score at 8th grade level or lower, the average reading skill level of US adults. The readability of the forms exceeded this level by an average of 3.9 grade levels (95% confidence interval, 3.3-4.6; P < .001). CONCLUSIONS: The readability of US state government-sponsored advance directive forms exceeds the readability level recommended by the National Work Group on Literacy and Health and the average reading skill level of most US adults. Such forms may inhibit advance care planning and therefore patient autonomy.