The potential use of artificial intelligence for venous thromboembolism prophylaxis and management: clinician and healthcare informatician perspectives.

Venous thromboembolism (VTE) is the leading cause of preventable death in hospitalized patients. Artificial intelligence (AI) and machine learning (ML) can support guidelines recommending an individualized approach to risk assessment and prophylaxis. We conducted electronic surveys asking clinician and healthcare informaticians about their perspectives on AI/ML for VTE prevention and management. Of 101 respondents to the informatician survey, most were 40 years or older, male, clinicians and data scientists, and had performed research on AI/ML. Of the 607 US-based respondents to the clinician survey, most were 40 years or younger, female, physicians, and had never used AI to inform clinical practice. Most informaticians agreed that AI/ML can be used to manage VTE (56.0%). Over one-third were concerned that clinicians would not use the technology (38.9%), but the majority of clinicians believed that AI/ML probably or definitely can help with VTE prevention (70.1%). The most common concern in both groups was a perceived lack of transparency (informaticians 54.4%; clinicians 25.4%). These two surveys revealed that key stakeholders are interested in AI/ML for VTE prevention and management, and identified potential barriers to address prior to implementation.

Artificial intelligence in the prediction of venous thromboembolism: A systematic review and pooled analysis.

BACKGROUND: Accurate diagnostic and prognostic predictions of venous thromboembolism (VTE) are crucial for VTE management. Artificial intelligence (AI) enables autonomous identification of the most predictive patterns from large complex data. Although evidence regarding its performance in VTE prediction is emerging, a comprehensive analysis of performance is lacking. AIMS: To systematically review the performance of AI in the diagnosis and prediction of VTE and compare it to clinical risk assessment models (RAMs) or logistic regression models. METHODS: A systematic literature search was performed using PubMed, MEDLINE, EMBASE, and Web of Science from inception to April 20, 2021. Search terms included "artificial intelligence" and "venous thromboembolism." Eligible criteria were original studies evaluating AI in the prediction of VTE in adults and reporting one of the following outcomes: sensitivity, specificity, positive predictive value, negative predictive value, or area under receiver operating curve (AUC). Risks of bias were assessed using the PROBAST tool. Unpaired t-test was performed to compare the mean AUC from AI versus conventional methods (RAMs or logistic regression models). RESULTS: A total of 20 studies were included. Number of participants ranged from 31 to 111 888. The AI-based models included artificial neural network (six studies), support vector machines (four studies), Bayesian methods (one study), super learner ensemble (one study), genetic programming (one study), unspecified machine learning models (two studies), and multiple machine learning models (five studies). Twelve studies (60%) had both training and testing cohorts. Among 14 studies (70%) where AUCs were reported, the mean AUC for AI versus conventional methods were 0.79 (95% CI: 0.74-0.85) versus 0.61 (95% CI: 0.54-0.68), respectively (p < .001). However, the good to excellent discriminative performance of AI methods is unlikely to be replicated when used in clinical practice, because most studies had high risk of bias due to missing data handling and outcome determination. CONCLUSION: The use of AI appears to improve the accuracy of diagnostic and prognostic prediction of VTE over conventional risk models; however, there was a high risk of bias observed across studies. Future studies should focus on transparent reporting, external validation, and clinical application of these models.

Venous thromboembolism prophylaxis for hospitalized adult patients: a survey of US health care providers on attitudes and practices.

Background: Venous thromboembolism (VTE) is a leading cause of preventable mortality among hospitalized patients, but appropriate risk assessment and thromboprophylaxis remain underutilized or misapplied. Objectives: We conducted an electronic survey of US health care providers to explore attitudes, practices, and barriers related to thromboprophylaxis in adult hospitalized patients and at discharge. Results: A total of 607 US respondents completed the survey: 63.1% reported working in an academic hospital, 70.7% identified as physicians, and hospital medicine was the most frequent specialty (52.1%). The majority of respondents agreed that VTE prophylaxis is important (98.8%; 95% CI: 97.6%-99.5%) and that current measures are safe (92.6%; 95% CI: 90.2%-94.5%) and effective (93.8%; 95% CI: 91.6%-95.6%), but only half (52.0%; 95% CI: 47.9%-56.0%) believed that hospitalized patients at their institution are on appropriate VTE prophylaxis almost all the time. One-third (35.4%) reported using a risk assessment model (RAM) to determine VTE prophylaxis need; 44.9% reported unfamiliarity with RAMs. The most common recommendation for improving rates of appropriate thromboprophylaxis was to leverage technology. A majority of respondents (84.5%) do not reassess a patient's need for VTE prophylaxis at discharge, and a minority educates patients about the risk (16.2%) or symptoms (18.9%) of VTE at discharge. Conclusion: Despite guideline recommendations to use RAMs, the majority of providers in our survey do not use them. A majority of respondents believed that technology could help improve VTE prophylaxis rates. A majority of respondents do not reassess the risk of VTE at discharge or educate patients about this risk of VTE at discharge.

Exercise social support, barriers, and instructions in venous thromboembolism survivors: a descriptive study.

Background: Diagnosis of venous thromboembolism (VTE) can be a significant life event that leads to changes in physical activity and exercise. Currently, little is known about the psychosocial experiences of survivors including perceived sources of social support, exercise barriers, and instructions for exercise from medical providers. Objectives: This study aimed to explore psychosocial characteristics associated with VTE survivors' postdiagnosis exercise. Specifically, 1) what are the main sources of social support utilized by VTE survivors for exercise, 2) what are the most significant exercise barriers (eg, physical, social, and psychological) faced by VTE survivors, and 3) what specific information relative to exercise is provided by medical professionals following diagnosis? Methods: VTE survivors (n = 472) were recruited through social media groups to participate in open-ended questions about psychosocial characteristics pertaining to postdiagnosis exercise. Results: VTE survivors reported multiple forms of exercise social support, although almost 1 in 4 participants reported having no support for exercise. Several postdiagnosis exercise barriers were noted, and the data indicated a wide variety of information from their medical providers regarding engaging in exercise following their diagnosis, suggesting that the unique benefits and drawbacks to these instructions should be examined in more detail. Conclusion: Although VTE survivors identified numerous categories of social support, there also exist numerous barriers, including a lack of standardized instructions for exercise. Further exploration of these characteristics is needed to better serve this population to encourage postdiagnosis exercise.

Direct Oral Anticoagulants in Obese Patients with Venous Thromboembolism: Results of an Expert Consensus Panel.

In clinical practice, direct oral anticoagulants (DOACs) are increasingly used for venous thromboembolism treatment and prevention. A substantial proportion of patients with venous thromboembolism are also obese. International guidance published in 2016 stated that DOACs could be used in standard doses in patients with obesity up to a body mass index (BMI) of 40 kg/m2, but should not be used in those with severe obesity (BMI >40 kg/m2) owing to limited supporting data at the time. Although updated guidance in 2021 removed this limitation, some health care providers still avoid DOACs even in patients with lower levels of obesity. Furthermore, there are still evidence gaps regarding treatment of severe obesity, the role of peak and trough DOAC levels in these patients, use of DOACs after bariatric surgery, and appropriateness of DOAC dose reduction in the setting of secondary venous thromboembolism prevention. This document describes proceedings and outcomes of a multidisciplinary panel convened to review these and other key issues regarding DOAC use for treatment or prevention of venous thromboembolism in individuals with obesity.

Proceedings from the 2022 Consensus Conference to Implement Optimal Venous Thromboembolism Prophylaxis in Trauma.

ABSTRACT: On May 4 and 5, 2022, a meeting of multidisciplinary stakeholders in the prevention and treatment of venous thromboembolism (VTE) after trauma was convened by the Coalition for National Trauma Research, funded by the National Heart, Lung, and Blood Institute of the National Institutes of Health, and hosted by the American College of Surgeons in Chicago, Illinois. This consensus conference gathered more than 40 in-person and 80 virtual attendees, including trauma surgeons, other physicians, thrombosis experts, nurses, pharmacists, researchers, and patient advocates. The objectives of the meeting were twofold: (1) to review and summarize the present state of the scientific evidence regarding VTE prevention strategies in injured patients and (2) to develop consensus on future priorities in VTE prevention implementation and research gaps.To achieve these objectives, the first part of the conference consisted of talks from physician leaders, researchers, clinical champions, and patient advocates to summarize the current state of knowledge of VTE pathogenesis and prevention in patients with major injury. Video recordings of all talks and accompanying slides are freely available on the conference website ( https://www.nattrauma.org/research/research-policies-templates-guidelines/vte-conference/ ). Following this curriculum, the second part of the conference consisted of a series of small-group breakout sessions on topics potentially requiring future study. Through this process, research priorities were identified, and plans of action to develop and undertake future studies were defined.The 2022 Consensus Conference to Implement Optimal VTE Prophylaxis in Trauma answered the National Trauma Research Action Plan call to define a course for future research into preventing thromboembolism after trauma. A multidisciplinary group of clinical champions, physicians, scientists, and patients delineated clear objectives for future investigation to address important, persistent key knowledge gaps. The series of papers from the conference outlines the consensus based on the current literature and a roadmap for research to answer these unanswered questions.

Positive deviants for medication therapy management: A mixed-methods comparative case study of community pharmacy practices.

BACKGROUND: To optimize medication use in older adults, the Centers for Medicare & Medicaid Services (CMS) launched Medication Therapy Management (MTM) services as part of Medicare Part D policy; however, strategies for achieving high quality MTM outcomes are not well understood. OBJECTIVE: The objective of this study was to generate hypotheses for strategies contributing to community pharmacies' high performance on policy-relevant MTM quality measures. METHODS: This mixed-methods comparative case study was guided by the Positive Deviance approach and Chronic Care Model. The study population consisted of pharmacy staff employed by a Midwestern division of a national supermarket-community pharmacy chain. Data consisted of demographics and qualitative data from semi-structured interviews. Qualitative and quantitative data were analyzed deductively and inductively or using descriptive statistics, respectively. MTM quality measures used to evaluate participant pharmacies' MTM performance mirrored select 2017 Medicare Part D Plans' Star Rating measures. RESULTS: Thirteen of 18 selected case pharmacies (72.2%) participated in this study, of which 5 were categorized as high performers, 4 moderate performers, and 4 low performers. Eleven pharmacists, 11 technicians, and 3 student interns participated in interviews. Eight strategies were hypothesized as contributing to MTM performance: Strong pharmacy staff-provider relationships and trust, Inability to address patients' social determinants of health (negatively contributing), Technician involvement in MTM, Providing comprehensive medication reviews in person vs. phone alone, Placing high priority on MTM, Using available clinical information systems to identify eligible patients, Technicians using clinical information systems to collect/document information for pharmacists, Faxing prescribers adherence medication therapy problems (MTPs) and calling on indication MTPs. CONCLUSIONS: Eight strategies were hypothesized as contributing to community pharmacies' performance on MTM quality measures. Findings from this work can inform MTM practice and Medicare Part D MTM policy changes to positively influence patient outcomes. Future research should test hypotheses in a larger representative sample of pharmacies.

Pharmacist and pharmacy intern perceptions of adolescent vaccination administration.

OBJECTIVES: To characterize pharmacists' and pharmacy interns' perceptions of administering adolescent vaccinations. Secondary objectives were to model the association between 1) perceptions and respondent demographic information and 2) pre- and post-training survey responses. DESIGN: A 12-item survey, on the basis of the Theory of Self-Perception, was used to collect respondents' perceptions of adolescent vaccination administration retrospectively before and after pharmacist and pharmacy intern completion of Online training. The training reviewed Center for Disease Control and Advisory Committee on Immunization Practice recommendations for vaccination schedules, vaccine administration, managing adverse reactions, finding vaccine-related information, the importance of vaccinating, and dispelling common misconceptions. SETTING AND PARTICIPANTS: Pharmacists and pharmacy interns representing 114 Indiana community pharmacy locations within a national supermarket chain were eligible to complete an Online survey between March and April 2019. OUTCOME MEASURES: Descriptive statistics were used to characterize pharmacists' and pharmacy interns' perceptions of adolescent vaccination administration. A multivariable regression analysis was used to determine the association between perceptions and respondent demographic information. Differences in perceptions before and after the training module were evaluated using paired t tests. RESULTS: Of the 293 eligible pharmacists and pharmacy interns, 138 (47.1%) completed the survey and 124 (42.3%) responses were included for analysis. Pharmacists and pharmacy interns had positive perceptions of adolescent vaccination administration. There was a negative relationship between the number of years that a pharmacist had been in practice and their baseline perceptions of adolescent vaccination administration (P = 0.02). There was a statistically significant increase in perceptions following completion of the training module (P < 0.001). CONCLUSION: Pharmacists and pharmacy interns, specifically those who have been in practice for few years, had positive perceptions about adolescent vaccination administration but their perceptions were strengthened with additional training. Further research is needed to determine the relationship between additional training and vaccination rates.

What predicts medication therapy management completion rates? The role of community pharmacy staff characteristics and beliefs about medication therapy management.

OBJECTIVES: To model the association between pharmacy technicians' attitudes and planned behaviors toward participating in medication therapy management (MTM) and MTM completion rates. Secondary objectives included 1) to compare pharmacy technician and pharmacist attitudes and planned behaviors toward participating in MTM and 2) to identify respondent and pharmacy demographic factors associated with MTM completion rates. DESIGN: A 27-item survey, adapted from a previously published survey tool based on the Theory of Planned Behavior (TPB), was used to collect respondent perceptions of MTM. Study procedures were approved by the institutional review board. SETTING AND PARTICIPANTS: Pharmacy technicians and pharmacists representing 116 Midwestern community pharmacy locations within a national supermarket chain were eligible to complete a telephone survey during February to May 2017. MAIN OUTCOME MEASURES: MTM completion rates were recorded during the 6-month time frame before survey administration. Unique, nonmeaningful survey codes were used to link responses from respondents to their store's MTM completion rates. Multivariate linear regression analysis was used to model the association between survey responses, pharmacy and staff demographics, and MTM completion rates. RESULTS: Of the 116 eligible pharmacy technicians and 114 pharmacists, 77 pharmacy technicians and 99 pharmacists completed the survey yielding response rates of 66.4% and 86.8%, respectively. Pharmacy technicians held significantly more positive perceptions about MTM delivery, particularly regarding adequate time and support. However, pharmacy technicians reported having the necessary knowledge and skills significantly less frequently compared with pharmacists. TPB variables for pharmacy technicians were not significant predictors of MTM completion rates. However, pharmacist attitudes, pharmacy technician education, and number of technician hours worked per week were positively associated with MTM completion rates. CONCLUSION: Pharmacists' attitudes, pharmacy technician level of education, and number of technician hours worked per week were associated with MTM completion rates.

Impact of passive and active promotional strategies on patient acceptance of medication therapy management services.

OBJECTIVES: To assess the impact of passive and active promotional strategies on patient acceptance of medication therapy management (MTM) services, and to identify reasons for patient acceptance or refusal. METHODS: Four promotional approaches were developed to offer MTM services to eligible patients, including letters and bag stuffers ("passive" approaches), and face-to-face offers and telephone calls ("active" approaches). Thirty pharmacies in a grocery store chain were randomized to one of the four approaches. Patient acceptance rates were compared among the four groups, and between active and passive approaches using hierarchical logistic regression techniques. Depending on their decision to accept or decline the service, patients were invited to take part in one of two brief telephone surveys. RESULTS: No significant differences were identified among the four promotional methods or between active and passive methods in the analyses. Patients' most frequent reasons for accepting MTM services were potential cost savings, review of how the medications were working, the expert opinion of the pharmacist, and education about medications. Patients' most frequent reasons for declining MTM services were that the participant already felt comfortable with their medications and felt their pharmacist provides these services on a regular basis. CONCLUSION: No significant difference was found among any of the four groups or between active or passive approaches. Further research is warranted to identify strategies for improving patient engagement in MTM services.