Dataset Information

Development and Validation of an Attitudinal-Profiling Tool for Patients With Asthma.

ABSTRACT: To develop a profiling tool which accurately assigns a patient to the appropriate attitudinal cluster for the management of asthma.Attitudinal data from an online survey of 2,467 patients with asthma from 8 Asian countries/region, aged 18-50 years, having had ?2 prescriptions in the previous 2 years and access to social media was used in a discriminant function analysis to identify a minimal set of questions for the Profiling Tool. A split-sample procedure based on 100 sets of randomly selected estimation and validation sub-samples from the original sample was used to cross-validate the Tool and assess the robustness of its predictive accuracy.Our Profiling Tool contained 10 attitudinal questions for the patient and 1 GINA-based level of asthma control question for the physician. It achieved a predictive accuracy of 76.2%. The estimation and validation sub-sample accuracies of 76.7% and 75.3%, respectively, were consistent with the tool's predictive accuracy at 95% confidence level; and their 1.4 percentage-points difference set upper-bound estimate for the degree of over-fitting.The Profiling Tool is highly predictive (>75%) of the attitudinal clusters that best describe patients with asthma in the Asian population. By identifying the attitudinal profile of the patient, the physician can make the appropriate asthma management decisions in practice. The challenge is to integrate its use into the consultation workflow and apply to areas where Internet resources are not available or patients who are not comfortable with the use of such technology.

SUBMITTER: David-Wang A

PROVIDER: S-EPMC5102835 | biostudies-other | 2017 Jan

REPOSITORIES: biostudies-other

ACCESS DATA

Publications

Development and Validation of an Attitudinal-Profiling Tool for Patients With Asthma.

David-Wang Aileen A Price David D Cho Sang Heon SH Ho James Chung Man JC Liam Chong Kin CK Neira Glenn G Teh Pei Li PL

Allergy, asthma & immunology research 20170101 1

<h4>Purpose</h4>To develop a profiling tool which accurately assigns a patient to the appropriate attitudinal cluster for the management of asthma.<h4>Methods</h4>Attitudinal data from an online survey of 2,467 patients with asthma from 8 Asian countries/region, aged 18-50 years, having had ≥2 prescriptions in the previous 2 years and access to social media was used in a discriminant function analysis to identify a minimal set of questions for the Profiling Tool. A split-sample procedure based o ...[more]

PMID: 27826961

Similar Datasets

Project description:Medication non-adherence remains a significant barrier in achieving better health outcomes for patients with chronic diseases. Previous self-reported medication adherence tools were not developed in the context of the Malaysia population. The most commonly used tool, MMAS-8, is no longer economical because it requires a license and currently every form used is charged. Hence, there is a need to develop and validate a new medication adherence tool. The Malaysia Medication Adherence Assessment Tool (MyMAAT) was developed by a multidisciplinary team with expertise in medication adherence and health literacy. The face and content validities of the MyMAAT was established by a panel of experts. A total of 495 patients with type 2 diabetes were recruited from the Ministry of Health facilities consisting of five hospitals and five primary health clinics. A test-retest was conducted on 42 of the patients one week following their first data collection. Exploratory factor analysis was performed to evaluate the validity of the MyMAAT. The final item for MyMAAT was compared with SEAMS, HbA1c%, Medication Possession ratio (MPR) score, and pharmacist's subjective assessment for its hypothesis testing validity. The MyMAAT-12 achieved acceptable internal consistency (Cronbach's alpha = 0.910) and stable reliability as the test-retest score showed good to excellent correlation (Spearman's rho = 0.96, p = 0.001). The MyMAAT has significant moderate association with SEAMS (Spearman's rho = 0.44, p = < 0.001) and significant relationship with HbA1c (< 8% and ≥ 8%) (χ2(1) = 13.4, p < 0.001), MPR (χ2(1) = 13.6, p < 0.001) and pharmacist's subjective assessment categories (χ2(1) = 31, p < 0.001). The sensitivity of MyMAAT-12, tested against HbA1c% was 72.9% while its specificity was 43%. This study demonstrates that the MyMAAT-12 together with other methods of assessment may make a better screening tool to identify patients who were non-adherence to their medications.

Project description:Patients with serious chronic illnesses face increasingly complex care and are at risk of poor experience due to a fragmented health system. Most current patient experience tools are not designed to address the unique care aspects of this population and the few that exist are delivered too late in the disease trajectory and are not administered longitudinally which makes them less useful across settings.We developed a new tool designed to address these gaps. The 25 item scale was tested and refined using randomly cross-validated exploratory and confirmatory factor analyses. Participants were not yet hospice eligible but sick enough to receive benefits of a supportive care approach in the last 2 to 3 years of life. Full information maximum likelihood models were run to confirm the factor structure developed in exploratory analyses. Goodness-of-fit was assessed with the Comparative Fit Index, the Tucker-Lewis Index, and the Root Mean Square Error of Approximation. Test-retest reliability was assessed with the intraclass correlation coefficient and internal consistency of the final scale was examined using Cronbach's alpha.Exploratory factor analysis revealed three domains - Care Team, Communication, and Care Goals - after removing weak loading and cross loading items. The initial three domain measurement model suggested in the development cohort was tested in the validation cohort and exhibited poor fit X 2 (206)?=?565.37, p?<?0.001; CFI?=?0.879; TLI?=?0.864; RMSEA?=?0.076. After model respecification, including removing one additional item and allowing paths between theoretically plausible error terms, the final 21 item tool exhibited good fit X 2 (173)?=?295.63, p?<?0.001; CFI?=?0.958; TLI?=?0.949; RMSEA?=?0.048. Cronbach's alpha revealed high reliability of each domain (Care Team?=?0.92, Communication?=?0.83, Care Goals?=?0.77) and the entire scale (??=?0.91). ICC showed adequate test-retest validity (ICC?=?0.58; 95% CI: 0.52-0.65) of the full scale.When administered earlier in the chronic illness trajectory, a new patient experience scale focused on care teams across settings, communication, and care goals, displayed strong reliability and performed well psychometrically.This trial ( NCT01746446 ) was registered at ClinicalTrials.gov on November 27, 2012 (retrospectively registered).

Project description:BackgroundSodium is an essential nutrient; however, excess dietary sodium is associated with increased blood pressure levels. The 2004 Canadian Community Health Survey - Nutrition (CCHS 2.2) concluded that most Canadians exceeded the Tolerable Upper Intake Level (UL) of 2300 mg/day. The 2015 CCHS indicated that Canadians were still consuming above the UL. To assess population sodium intakes, a Sodium AnaLysis Tool (SALT) was developed.MethodsWe used data from CCHS 2.2 (2004) to group foods into types (e.g., popcorn, crackers) and general categories (e.g., snack foods) which formed the SALT questions. Portion sizes and sodium values were calculated for SALT questions. Over a one-month period, one hundred participants completed three, 24-h recalls (at beginning, middle, and end) and two SALT (SALT1 & SALT2) tools (at beginning and end). To assess both validity and reliability, statistical tests including Bland-Altman (B-A) plots, paired t-tests, differences between means, and correlations were conducted. The mean of the 3,24-h recalls (m24HR) was used for validation.ResultsValidity testing between SALT2 and the m24HR yielded variable results. A B-A plot between SALT2 and m24HR depicted a small bias of 7 mg/day of sodium. The sodium intake for m24HR (2742 ± 980 mg/day) (mean ± standard deviation) versus SALT2 (2735 ± 1174 mg/day) was not significantly different (p = 0.960). Pearson's correlation between methods, although significant (p = 0.02) was poor (r = 0.202; de-attenuated r = 0.400). There was a fair, significant agreement (κ = 0.236, p = 0.02) for the classification of sodium intake into two categories (above or below the UL). Test-retest reliability results were also variable. There was moderate, significant agreement (κ = 0.488, p = 0.001) for classification of sodium intake into two categories between SALT1 and SALT2, a significant correlation (Pearson's r = 0.785, p < 0.001), and the B-A plot depicted good agreement. However, the values for sodium intake for SALT1 (3185 ± 1424) vs SALT2 (2735 ± 1174) were significantly different (p = 0.005).ConclusionsResults indicate that the SALT has the potential to be a valid and reliable tool for assessing dietary sodium intake of Canadian adult populations. Despite some classification issues, there may be some value in using the SALT to categorize sodium intakes. Further refinement of the SALT may be required.

Project description:BackgroundBest Practice Alerts (BPAs) are alert messages to physicians in the electronic health record that are used to encourage appropriate use of health care resources. While these alerts are helpful in both improving care and reducing costs, BPAs are often broadly applied nonselectively across entire patient populations. The development of large language models (LLMs) provides an opportunity to selectively identify patients for BPAs.ObjectiveIn this paper, we present an example case where an LLM screening tool is used to select patients appropriate for a BPA encouraging the prescription of deep vein thrombosis (DVT) anticoagulation prophylaxis. The artificial intelligence (AI) screening tool was developed to identify patients experiencing acute bleeding and exclude them from receiving a DVT prophylaxis BPA.MethodsOur AI screening tool used a BioMed-RoBERTa (Robustly Optimized Bidirectional Encoder Representations from Transformers Pretraining Approach; AllenAI) model to perform classification of physician notes, identifying patients without active bleeding and thus appropriate for a thromboembolism prophylaxis BPA. The BioMed-RoBERTa model was fine-tuned using 500 history and physical notes of patients from the MIMIC-III (Medical Information Mart for Intensive Care) database who were not prescribed anticoagulation. A development set of 300 MIMIC patient notes was used to determine the model's hyperparameters, and a separate test set of 300 patient notes was used to evaluate the screening tool.ResultsOur MIMIC-III test set population of 300 patients included 72 patients with bleeding (ie, were not appropriate for a DVT prophylaxis BPA) and 228 without bleeding who were appropriate for a DVT prophylaxis BPA. The AI screening tool achieved impressive accuracy with a precision-recall area under the curve of 0.82 (95% CI 0.75-0.89) and a receiver operator curve area under the curve of 0.89 (95% CI 0.84-0.94). The screening tool reduced the number of patients who would trigger an alert by 20% (240 instead of 300 alerts) and increased alert applicability by 14.8% (218 [90.8%] positive alerts from 240 total alerts instead of 228 [76%] positive alerts from 300 total alerts), compared to nonselectively sending alerts for all patients.ConclusionsThese results show a proof of concept on how language models can be used as a screening tool for BPAs. We provide an example AI screening tool that uses a HIPAA (Health Insurance Portability and Accountability Act)-compliant BioMed-RoBERTa model deployed with minimal computing power. Larger models (eg, Generative Pre-trained Transformers-3, Generative Pre-trained Transformers-4, and Pathways Language Model) will exhibit superior performance but require data use agreements to be HIPAA compliant. We anticipate LLMs to revolutionize quality improvement in hospital medicine.

Dataset Information

Development and Validation of an Attitudinal-Profiling Tool for Patients With Asthma.

Publications

Development and Validation of an Attitudinal-Profiling Tool for Patients With Asthma.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets