Search

Pharmacovigilance (PV) has proven to detect post-marketing adverse drug events (ADE). Previous research used the natural language processing (NLP) tool to extract unstructured texts relevant to ADEs. However, texts without context reduce the efficiency of such algorithms. Our objective was to develop and validate an innovative NLP tool, aTarantula, using a context-aware machine-learning algorithm to detect existing ADEs from social media using an aggregated lexicon.aTarantula utilized FastText embeddings and an aggregated lexicon to extract contextual data from three patient forums (i.e., MedHelp, MedsChat, and PatientInfo) taking warfarin. The lexicon used warfarin package inserts and synonyms of warfarin ADEs from UMLS and FAERS databases. Data was stored on SQLite and then refined and manually checked by three clinical pharmacists for validation.Multiple organ systems where the most frequent ADE were reported at 1.50%, followed by CNS side effects at 1.19%. Lymphatic system ADEs were the least common side effect reported at 0.09%. The overall Spearman rank correlation coefficient between patient-reported data from the forums and FAERS was 0.19. As determined by pharmacist validation, aTarantula had a sensitivity of 84.2% and a specificity of 98%. Three clinical pharmacists manually validated our results. Finally, we created an aggregated lexicon for mining ADEs from social media.We successfully developed aTarantula, a machine-learning algorithmn based on artificial intelligence to extract warfarin-related ADEs from online social discussion forums automatically. Our study shows that it is feasible to use aTarantula to detect ADEs. Future researchers can validate aTarantula on the diverse dataset.

Pharmacists provide direct patient care services such as chronic disease management and medication therapy management services. Patient satisfaction measures are valuable tools to assess outcomes. Therefore, measuring patient satisfaction with pharmacist services, using tools such as the Patient Satisfaction with Pharmacist Services Questionnaire 2.0 (PSPSQ 2.0), is important to ensure service quality.The objective of the study was to evaluate the descriptive properties and reliability of the original English and newly translated Spanish versions of the PSPSQ 2.0 in a larger sample.This project evaluated the functioning of the Spanish translation of the PSPSQ 2.0 compared to the English version. Demographic characteristics were analyzed to determine whether the instrument functioned differently for English- and Spanish-speaking groups. Psychometric properties were analyzed.Completed data for both PSPSQ 2.0 versions were available for 337 patients (English, n = 187; Spanish, n = 150) enrolled. In the English data set, no items had a ceiling or a floor effect, while in the Spanish data set, all items had a ceiling effect, but no items had a floor effect. In both the English and Spanish versions, nearly all the items had a strong, positive correlation with one another (greater than 0.30), indicating the measure was unidimensional. The pattern of the estimated loading indicated the items were assigned as expected. The items functioned differently in the English and Spanish instruments, and there was a statistically significant difference in Wald values between the 2 versions (P0.05).The PSPSQ 2.0 demonstrated reliability for this setting and population. However, regarding demonstration of validity, the response categories in the instrument seem not to capture the views of the Spanish-speaking respondents. Further work may focus on uncovering the preferences for use of Likert scale response categories by Spanish speakers to ensure greater cultural fidelity in the translation.

BACKGROUND Despite the detailed patient package inserts (PPIs) with prescription drugs that communicate crucial information about safety, there is a critical gap between patient understanding and the knowledge presented. As a result, patients may suffer from adverse events. We propose using human factors design methodologies such as hierarchical task analysis (HTA) and interactive visualization to bridge this gap. We hypothesize that an innovative mobile app employing human factors design with an interactive visualization can deliver PPI information aligned with patients’ information processing heuristics. Such an app may help patients gain an improved overall knowledge of medications. OBJECTIVE The objective of this study was to explore the feasibility of designing an interactive visualization-based mobile app using an HTA approach through a mobile prototype. METHODS Two pharmacists constructed the HTA for the drug risperidone. Later, the specific requirements of the design were translated using infographics. We transferred the wireframes of the prototype into an interactive user interface. Finally, a usability evaluation of the mobile health app was conducted. RESULTS A mobile app prototype using HTA and infographics was successfully created. We reiterated the design based on the specific recommendations from the usability evaluations. CONCLUSIONS Using HTA methodology, we successfully created a mobile prototype for delivering PPI on the drug risperidone to patients. The hierarchical goals and subgoals were translated into a mobile prototype.

Objectives: Candida non-albicans species cause an increasing proportion of invasive candidiasis (IC). Prompt initiation of effective antifungal therapy has been shown to positively impact the outcomes of IC. Caspofungin is often reserved as a second-line agent after suboptimal response to initial therapy. We determined the impact of the timing of caspofungin administration on outcomes of IC. Methods: Medical records were reviewed on all hospitalized adults who received ≥72 h of caspofungin for IC (isolation of Candida species from blood, intra-abdominal or other sterile sites). Clinical data were extracted from medical charts and recorded. Patients were classified based on delayed initiation (DI; .3 days) versus early initiation (EI; ≤3 days) of caspofungin relative to the time the culture was obtained. Results: A total of 169 patients received caspofungin for IC; Candida glabrata (n¼78, 46%) was the most common cause, followed by mixed species (n¼36, 21%), Candida albicans (n¼36, 21%), Candida parapsilosis (n¼9, 6%), Candida tropicalis (n ¼6, 3%), Candida krusei and other species (n¼4, 2%). Infection sites were bloodstream related (n¼119, 71%), intra-abdominal (n ¼44, 26%) and other sterile sites (n¼6, 3%). DI of caspofungin was associated with a lower response rate (35/62, 56% versus 82/107, 77%; P ¼0.006), longer time to achieve clinical stability (10 versus 4 days; P ¼0.002) and longer length of stay after isolation of the organism (28 versus 21 days; P ¼0.007), compared with EI (n ¼107). Conclusions: Non-albicans Candida species accounted for the majority of IC in caspofungin-treated patients. Improved outcomes were observed for patients initiated with caspofungin within 72 h of positive culture compared with those who received delayed therapy.

Background Guidelines for care of hypertensive patients have proliferated recently, yet quality assessment remains difficult in the absence of well-defined measurement systems. Existing systems have not always linked process measures to blood pressure outcomes. Methods A quality measurement system was developed and tested on hypertensive women in a West Coast health plan. An expert panel selected clinically detailed, evidence-explicit indicators using a modified Delphi method. Thirteen indicators (1 screening, 5 diagnostic, 5 treatment, and 2 follow-up indicators) were selected by this process. Trained nurses used a laptop-based tool to abstract data from medical records for the most recent 2 years of care. Results Of 15 004 eligible patients with hypertensive and other chronic disease codes, 613 patients were sampled, all eligible for the screening indicator. Of these, 234 women with an average blood pressure of 140/90 mm Hg or more, or a documented diagnosis of hypertension, were studied for the remaining indicators. The average woman received 64% of the recommended care. Most patients did not receive adequate initial history, physical examination, or laboratory tests. Only 37% of hypertensive women with persistent elevations to more than 160/90 mm Hg had changes in therapy or lifestyle recommended. The average adherence proportion to all indicators was lower in patients with uncontrolled blood pressure (>140/90 mm Hg) than in those with controlled blood pressure (54% vs 73%; P Conclusions Quality of hypertensive care falls short of indicators based on randomized controlled trials and national guidelines. Poor performance in essential care processes is associated with poor blood pressure control.