Parsing Clinical Trial Eligibility Criteria for Cohort Query by a Multi-Input Multi-Output Sequence Labeling Model

To enable electronic screening of eligible patients for clinical trials, free-text clinical trial eligibility criteria should be translated to a computable format. Natural language processing (NLP) techniques have the potential to automate this process. In this study, we explored a supervised multi-input multi-output (MIMO) sequence labeling model to parse eligibility criteria into combinations of fact and condition tuples. Our experiments on a small manually annotated training dataset showed that that the performance of the MIMO framework with a BERT-based encoder using all the input sequences achieved an overall lenient-level AUROC of 0.61. Although the performance is suboptimal, representing eligibility criteria into logical and semantically clear tuples can potentially make subsequent translation of these tuples into database queries more reliable.

Development and Assessment of PharmaCheck: An Electronic Screening Tool for the Prevention of Twenty Major Adverse Drug Events

Background: Adverse drug events (ADEs) can be prevented by deploying clinical decision support systems (CDSS) that directly assist physicians, via computerized order entry systems, and clinical pharmacists performing medication reviews as part of medical rounds. However, physicians using CDSS are known to be exposed to the alert-fatigue phenomenon. Our study aimed to assess the performance of PharmaCheck—a CDSS to help clinical pharmacists detect high-risk situations with the potential to lead to ADEs—and its impact on clinical pharmacists’ activities.Methods: Twenty clinical rules, divided into four risk classes, were set for the daily screening of high-risk situations in the electronic health records of patients admitted to our General Internal Medicine Department. Alerts to clinical pharmacists encouraged them to telephone prescribers and suggest any necessary treatment adjustments. PharmaCheck’s performance was assessed using the intervention’s positive predictive value (PPV), which characterizes the proportion of interventions for each alert triggered. PharmaCheck’s impact was assessed by considering clinical pharmacists as a filter for ruling out futile alerts and by comparing the final clinical PPV with a pharmacist (the proportion of interventions that led to a change in the medical regimen) to the final clinical PPV without a pharmacist.Results: Over 132 days, 447 alerts were triggered for 383 patients, leading to 90 interventions (overall intervention PPV = 20.1%). By risk class, intervention PPVs made up 26.9% (n = 65/242) of abnormal laboratory value alerts, 3.1% (4/127) of alerts for contraindicated medications or medications to be used with caution, 28.2% (20/71) of drug–drug interaction alerts, and 14.3% (1/7) of inadequate mode of administration alerts. Clinical PPVs reached 71.0% (64/90) when pharmacists filtered alerts and 14% (64/242) if they were not doing it.Conclusion: PharmaCheck enabled clinical pharmacists to improve their traditional processes and broaden their coverage by focusing on 20 high-risk situations. Alert management by pharmacists seemed to be a more effective way of preventing risky situations and alert fatigue than a model addressing alerts to physicians exclusively. Some fine-tuning could enhance PharmaCheck's performance by considering the information quality of triggers, the variability of clinical settings, and the fact that some prescription processes are already highly secured.

Feasibility of implementing a same-day electronic screening tool for clinical assessment to measure patient-reported outcomes for eliciting actionable information on adherence to HIV medication and related factors in a busy Canadian urban HIV clinic

Background: An optimal adherence to antiretroviral therapy (ART) is fundamental for suppression of HIV viral load and favourable treatment outcomes. Patient-reported outcomes (PROs) are effective tools for improving patient–provider communication and focusing providers’ awareness on current health problems. The objectives of this analysis were (1) to determine the feasibility of implementing an electronic screening tool to measure PROs in a Canadian HIV clinic to obtain information on ART adherence and related factors and (2) to determine the factors related to sub-optimal adherence. Methods: This implementation research with a convenience sample of 600 people living with HIV (PLWH) was conducted in a busy, academic, urban HIV clinic in Toronto, Canada. PLWH were approached to participate in PRO assessments just prior to their in-clinic appointments, including health-related domains such as mental health, housing, nutrition, financial stress and medication adherence, and responses were summarized on a single sheet available for providers to review. Feasibility of implementing PROs was assessed by quantifying response rate, completion rate, time taken and participation rate. Medication adherence was elicited by self-report of the percentage of prescribed HIV medications taken in the last month. Unadjusted and adjusted odds ratios were estimated from logistic regression models to identify factors associated with adherence of <95%. Results: Of the 748 PLWH invited to participate, 692 (participation rate: 92.5%) completed the PRO assessments as standard of care in clinic. Of these, 600 consented to the use of their PRO results for research and were included in this analysis. The average response rate to the ART-related questions was 96.8% and mean completion rate was 95.5%. The median time taken to complete the assessment was 12.0 (IQR = 8.4–17.3) min, adjusted 8.7 (IQR = 7.2–10.8) min. 445 (74.9%) of participants were male, and 153 (26.2%) reported dissatisfaction with ART. 105 (19.7%) of the PLWH reported ART adherence of <95%. Multivariable logistic regression identified the following risk factors for sub-optimal adherence: dissatisfaction with ART (OR = 2.30, 95% CI 1.38–3.83), not having a family doctor or not visiting a family doctor in last year (OR = 1.69, 95% CI 1.02–2.79). Conclusion: Collecting self-reported health information from PLWH through PROs in a busy urban clinic was feasible and can provide relevant information to healthcare providers on issues related to adherence. This has a potential to help in individualizing ambulatory care.

The clinical utility of the ICD-11 classification of personality disorders and related traits: A preliminary scoping review

Objectives: A diagnostic system that fails to deliver clinically useful information will not be utilized and consequently will be unable to provide valuable data for health policy and clinical decision making. Therefore, it is imperative to obtain an accurate depiction of the clinical utility of the eleventh revision of the International Classification of Diseases (ICD-11) Personality Disorder (PD) model. The current mixed-methods systematic review aimed to determine the clinical utility of the ICD-11 PD classification system. Method: An electronic screening of six databases was conducted and resulting studies were subjected to specific exclusion criteria, which elicited eight studies of interest. Study characteristics were tabulated and methodological quality was appraised. Results: Four studies offered strong support for the model’s clinical utility, three offered some support accompanied by notable limitations and one study could only offer criticisms. Conclusion: Future investigation of the ICD-11 PD classification system’s (a) communicative value between clinicians and their patients, and between clinicians and their patient’s families; (b) ease of use; and (c) feasibility in terms of practical application is required to achieve a complete understanding of its clinical utility and ultimately bring clarity to the current ambiguous findings.

P246 Development of a new Inflammatory Bowel Disease Patient Identifier shortens time to clinic review and initiation of treatment

Background Timely diagnosis of inflammatory bowel disease (IBD) is important because earlier use of biologic therapies leads to mucosal healing, a reduction in hospitalisations and surgeries and improvements in quality of life. In the United Kingdom, general practitioners refer patients with symptoms suggestive of IBD to colorectal surgeons, emergency department physicians, gastroenterologists or directly for a lower gastrointestinal endoscopy. Consequently, there is variation in the time from endoscopic diagnosis of IBD to specialist review. We created an electronic tool that screens all endoscopy reports for a new diagnosis of IBD. These cases are then reviewed in our weekly complex multidisciplinary team (MDT) meeting and new patients are allocated an IBD specialist. We sought to determine whether our new patient identifier reduced the time to clinical review by an IBD specialist and initiation of IBD treatment. Methods We designed a retrospective observational cohort study comparing time from endoscopic diagnosis of IBD to initiation of treatment and IBD specialist review. Outcomes were compared in the 18 months before and after the introduction, in January 2018, of our new IBD patient identifier. Demographic, endoscopic and treatment outcome data were recorded from our electronic patient record. Categorical and continuous variables were summarised as frequencies (%) and median [IQR] and compared with Fisher’s exact and Mann Whitney U tests respectively. Results Between the 1st January 2018 and 30th June 2019, 116 new patients diagnosed with IBD were identified and reviewed in our MDT meeting. In the preceding 18 months, 111 patients were diagnosed with IBD. There were no significant differences between groups according to sex, age, age at diagnosis, disease type, or phenotype according to the Montreal classification (Table 1). Both the median time from endoscopic diagnosis to treatment initiation (0 days [IQR 0 – 14.2] vs 14 days [IQR 0 – 31.6], p=0.007) and specialist clinic review (21 days [IQR 7 - 25] vs 48 days [IQR 34 – 63], p&lt;0.0001) were shorter following the introduction of the new IBD patient identifier screening tool (Figure 1). Conclusion Systematic electronic screening of endoscopic reports linked to MDT review reduces the time to first treatment and specialist review in newly diagnosed patients with IBD.