The Association of the First Surge of the COVID-19 Pandemic with the High- and Low-Value Outpatient Care Delivered to Adults in the USA.

BACKGROUND: The first surge of the COVID-19 pandemic entirely altered healthcare delivery. Whether this also altered the receipt of high- and low-value care is unknown. OBJECTIVE: To test the association between the April through June 2020 surge of COVID-19 and various high- and low-value care measures to determine how the delivery of care changed. DESIGN: Difference in differences analysis, examining the difference in quality measures between the April through June 2020 surge quarter and the January through March 2020 quarter with the same 2 quarters' difference the year prior. PARTICIPANTS: Adults in the MarketScan® Commercial Database and Medicare Supplemental Database. MAIN MEASURES: Fifteen low-value and 16 high-value quality measures aggregated into 8 clinical quality composites (4 of these low-value). KEY RESULTS: We analyzed 9,352,569 adults. Mean age was 44 years (SD, 15.03), 52% were female, and 75% were employed. Receipt of nearly every type of low-value care decreased during the surge. For example, low-value cancer screening decreased 0.86% (95% CI, -1.03 to -0.69). Use of opioid medications for back and neck pain (DiD +0.94 [95% CI, +0.82 to +1.07]) and use of opioid medications for headache (DiD +0.38 [95% CI, 0.07 to 0.69]) were the only two measures to increase. Nearly all high-value care measures also decreased. For example, high-value diabetes care decreased 9.75% (95% CI, -10.79 to -8.71). CONCLUSIONS: The first COVID-19 surge was associated with receipt of less low-value care and substantially less high-value care for most measures, with the notable exception of increases in low-value opioid use.

Recommendations for the safe, effective use of adaptive CDS in the US healthcare system: an AMIA position paper.

The development and implementation of clinical decision support (CDS) that trains itself and adapts its algorithms based on new data-here referred to as Adaptive CDS-present unique challenges and considerations. Although Adaptive CDS represents an expected progression from earlier work, the activities needed to appropriately manage and support the establishment and evolution of Adaptive CDS require new, coordinated initiatives and oversight that do not currently exist. In this AMIA position paper, the authors describe current and emerging challenges to the safe use of Adaptive CDS and lay out recommendations for the effective management and monitoring of Adaptive CDS.

A comparison of rule-based and machine learning approaches for classifying patient portal messages.

OBJECTIVE: Secure messaging through patient portals is an increasingly popular way that consumers interact with healthcare providers. The increasing burden of secure messaging can affect clinic staffing and workflows. Manual management of portal messages is costly and time consuming. Automated classification of portal messages could potentially expedite message triage and delivery of care. MATERIALS AND METHODS: We developed automated patient portal message classifiers with rule-based and machine learning techniques using bag of words and natural language processing (NLP) approaches. To evaluate classifier performance, we used a gold standard of 3253 portal messages manually categorized using a taxonomy of communication types (i.e., main categories of informational, medical, logistical, social, and other communications, and subcategories including prescriptions, appointments, problems, tests, follow-up, contact information, and acknowledgement). We evaluated our classifiers' accuracies in identifying individual communication types within portal messages with area under the receiver-operator curve (AUC). Portal messages often contain more than one type of communication. To predict all communication types within single messages, we used the Jaccard Index. We extracted the variables of importance for the random forest classifiers. RESULTS: The best performing approaches to classification for the major communication types were: logistic regression for medical communications (AUC: 0.899); basic (rule-based) for informational communications (AUC: 0.842); and random forests for social communications and logistical communications (AUCs: 0.875 and 0.925, respectively). The best performing classification approach of classifiers for individual communication subtypes was random forests for Logistical-Contact Information (AUC: 0.963). The Jaccard Indices by approach were: basic classifier, Jaccard Index: 0.674; Naïve Bayes, Jaccard Index: 0.799; random forests, Jaccard Index: 0.859; and logistic regression, Jaccard Index: 0.861. For medical communications, the most predictive variables were NLP concepts (e.g., Temporal_Concept, which maps to 'morning', 'evening' and Idea_or_Concept which maps to 'appointment' and 'refill'). For logistical communications, the most predictive variables contained similar numbers of NLP variables and words (e.g., Telephone mapping to 'phone', 'insurance'). For social and informational communications, the most predictive variables were words (e.g., social: 'thanks', 'much', informational: 'question', 'mean'). CONCLUSIONS: This study applies automated classification methods to the content of patient portal messages and evaluates the application of NLP techniques on consumer communications in patient portal messages. We demonstrated that random forest and logistic regression approaches accurately classified the content of portal messages, although the best approach to classification varied by communication type. Words were the most predictive variables for classification of most communication types, although NLP variables were most predictive for medical communication types. As adoption of patient portals increases, automated techniques could assist in understanding and managing growing volumes of messages. Further work is needed to improve classification performance to potentially support message triage and answering.

Use of the Multidimensional Health Locus of Control to Predict Information-Seeking Behaviors and Health-Related Needs in Pregnant Women and Caregivers.

Pregnancy produces important health-related needs, and expectant families have turned to technologies to meet them. The ability to predict needs and technology preferences might aid in connecting families with resources. This study examined the relationships among Multidimensional Health Locus of Control (MHLC) scores, information-seeking behaviors, and health-related needs in 71 pregnant women and 29 caregivers. Internal MHLC scores were positively correlated with information-seeking behaviors, including website and patient portal use. Higher Chance scores were associated with decreased portal or pregnancy website use (p=0.002), with the exception of FitPregnancy.com (p=0.02). MHLC scores were not significantly correlated with number of health-related needs or whether needs were met. Individuals with needs about disease management had higher Powerful Others scores (p=0.01); those with questions about tests had lower Powerful Others scores (p=0.008). MHLC scores might be used to identify individuals less likely to seek information and to predict need types.

Application of a Consumer Health Information Needs Taxonomy to Questions in Maternal-Fetal Care.

Pregnancy is a time when expectant mothers may have numerous questions about their unborn children, especially when congenital anomalies are diagnosed prenatally. We sought to characterize information needs of pregnant women seen in the Vanderbilt Children's Hospital Fetal Center. Participants recorded questions from diagnosis through delivery. Questions were categorized by two researchers using a hierarchical taxonomy describing consumer health information needs. Consensus category assignments were made, and inter-rater reliability was measured with Cohen's Kappa. Sixteen participants reported 398 questions in 39 subcategories, of which the most common topics were prognosis (53 questions; 13.3%) and indications for intervention (31 questions; 7.8%). Inter-rater reliability of assignments showed moderate (κ=0.57) to substantial (κ=0.75) agreement for subcategories and primary categories, respectively. Pregnant women with prenatal diagnoses have diverse unmet information needs; a taxonomy of consumer health information needs may improve the ability to meet such needs through content and system design.

Automated Classification of Consumer Health Information Needs in Patient Portal Messages.

Patients have diverse health information needs, and secure messaging through patient portals is an emerging means by which such needs are expressed and met. As patient portal adoption increases, growing volumes of secure messages may burden healthcare providers. Automated classification could expedite portal message triage and answering. We created four automated classifiers based on word content and natural language processing techniques to identify health information needs in 1000 patient-generated portal messages. Logistic regression and random forest classifiers detected single information needs well, with area under the curves of 0.804-0.914. A logistic regression classifier accurately found the set of needs within a message, with a Jaccard index of 0.859 (95% Confidence Interval: (0.847, 0.871)). Automated classification of consumer health information needs expressed in patient portal messages is feasible and may allow direct linking to relevant resources or creation of institutional resources for commonly expressed needs.

A decision model of therapy for potentially resectable pancreatic cancer.

BACKGROUND: Optimal treatment for potentially resectable pancreatic cancer is controversial. Resection is considered the only curative treatment, but neoadjuvant chemoradiotherapy may offer significant advantages. MATERIALS AND METHODS: We developed a decision model for potentially resectable pancreatic cancer. Initial therapeutic choices were surgery, neoadjuvant chemoradiotherapy, or no treatment; subsequent decisions offered a second intervention if not prohibited by complications or death. Payoffs were calculated as the median expected survival. We gathered evidence for this model through a comprehensive MEDLINE search. One-way sensitivity analyses were performed. RESULTS: Neoadjuvant chemoradiation is favored over initial surgery, with expected values of 18.6 and 17.7 mo, respectively. The decision is sensitive to the probabilities of treatment mortality and tumor resectability. Threshold probabilities are 7.0% mortality of neoadjuvant chemoradiotherapy, 69.2% resectability on imaging after neoadjuvant therapy, and 73.7% resectability at exploration after neoadjuvant therapy, 92.2% resectability at initial resection, and 9.9% surgical mortality following chemoradiotherapy. The decision is sensitive to the utility of time spent in chemoradiotherapy, with surgery favored for utilities less than 0.3 and -0.8, for uncomplicated and complicated chemoradiotherapy, respectively. CONCLUSIONS: The ideal treatment for potentially resectable pancreatic cancer remains controversial, but recent evidence supports a slight benefit for neoadjuvant therapy. Our model shows that the decision is sensitive to the probability of tumor resectability and chemoradiation mortality, but not to rates of other treatment complications. With minimal benefit of one treatment over another based on survival alone, patient preferences will likely play an important role in determining best treatment.