To quantify and contextualize the risk for coronavirus disease 2019 (COVID-19)-related hospitalization and illness severity in type 1 diabetes.
We conducted a prospective cohort study to identify ...case subjects with COVID-19 across a regional health care network of 137 service locations. Using an electronic health record query, chart review, and patient contact, we identified clinical factors influencing illness severity.
We identified COVID-19 in 6,138, 40, and 273 patients without diabetes and with type 1 and type 2 diabetes, respectively. Compared with not having diabetes, people with type 1 diabetes had adjusted odds ratios of 3.90 (95% CI 1.75-8.69) for hospitalization and 3.35 (95% CI 1.53-7.33) for greater illness severity, which was similar to risk in type 2 diabetes. Among patients with type 1 diabetes, glycosylated hemoglobin (HbA
), hypertension, race, recent diabetic ketoacidosis, health insurance status, and less diabetes technology use were significantly associated with illness severity.
Diabetes status, both type 1 and type 2, independently increases the adverse impacts of COVID-19. Potentially modifiable factors (e.g., HbA
) had significant but modest impact compared with comparatively static factors (e.g., race and insurance) in type 1 diabetes, indicating an urgent and continued need to mitigate severe acute respiratory syndrome coronavirus 2 infection risk in this community.
Display omitted
•We use sequential pattern mining to identify temporal relationships between drugs.•Mined stepwise patterns of pharmacologic therapy are consistent with guidelines.•Mined patterns are ...useful for predicting the next drug prescribed for a patient.•Accurate predictions can be made using only a few drugs in the patient’s history.
Therapy for certain medical conditions occurs in a stepwise fashion, where one medication is recommended as initial therapy and other medications follow. Sequential pattern mining is a data mining technique used to identify patterns of ordered events.
To determine whether sequential pattern mining is effective for identifying temporal relationships between medications and accurately predicting the next medication likely to be prescribed for a patient.
We obtained claims data from Blue Cross Blue Shield of Texas for patients prescribed at least one diabetes medication between 2008 and 2011, and divided these into a training set (90% of patients) and test set (10% of patients). We applied the CSPADE algorithm to mine sequential patterns of diabetes medication prescriptions both at the drug class and generic drug level and ranked them by the support statistic. We then evaluated the accuracy of predictions made for which diabetes medication a patient was likely to be prescribed next.
We identified 161,497 patients who had been prescribed at least one diabetes medication. We were able to mine stepwise patterns of pharmacological therapy that were consistent with guidelines. Within three attempts, we were able to predict the medication prescribed for 90.0% of patients when making predictions by drug class, and for 64.1% when making predictions at the generic drug level. These results were stable under 10-fold cross validation, ranging from 89.1%–90.5% at the drug class level and 63.5–64.9% at the generic drug level. Using 1 or 2 items in the patient’s medication history led to more accurate predictions than not using any history, but using the entire history was sometimes worse.
Sequential pattern mining is an effective technique to identify temporal relationships between medications and can be used to predict next steps in a patient’s medication regimen. Accurate predictions can be made without using the patient’s entire medication history.
Abstract
Objective
To determine if ChatGPT can generate useful suggestions for improving clinical decision support (CDS) logic and to assess noninferiority compared to human-generated suggestions.
...Methods
We supplied summaries of CDS logic to ChatGPT, an artificial intelligence (AI) tool for question answering that uses a large language model, and asked it to generate suggestions. We asked human clinician reviewers to review the AI-generated suggestions as well as human-generated suggestions for improving the same CDS alerts, and rate the suggestions for their usefulness, acceptance, relevance, understanding, workflow, bias, inversion, and redundancy.
Results
Five clinicians analyzed 36 AI-generated suggestions and 29 human-generated suggestions for 7 alerts. Of the 20 suggestions that scored highest in the survey, 9 were generated by ChatGPT. The suggestions generated by AI were found to offer unique perspectives and were evaluated as highly understandable and relevant, with moderate usefulness, low acceptance, bias, inversion, redundancy.
Conclusion
AI-generated suggestions could be an important complementary part of optimizing CDS alerts, can identify potential improvements to alert logic and support their implementation, and may even be able to assist experts in formulating their own suggestions for CDS improvement. ChatGPT shows great potential for using large language models and reinforcement learning from human feedback to improve CDS alert logic and potentially other medical areas involving complex, clinical logic, a key step in the development of an advanced learning health system.
Background
Early detection of clinical deterioration among hospitalized patients is a clinical priority for patient safety and quality of care. Current automated approaches for identifying these ...patients perform poorly at identifying imminent events.
Objective
Develop a machine learning algorithm using pager messages sent between clinical team members to predict imminent clinical deterioration.
Design
We conducted a large observational study using long short-term memory machine learning models on the content and frequency of clinical pages.
Participants
We included all hospitalizations between January 1, 2018 and December 31, 2020 at Vanderbilt University Medical Center that included at least one page message to physicians. Exclusion criteria included patients receiving palliative care, hospitalizations with a planned intensive care stay, and hospitalizations in the top 2% longest length of stay.
Main Measures
Model classification performance to identify in-hospital cardiac arrest, transfer to intensive care, or Rapid Response activation in the next 3-, 6-, and 12-hours. We compared model performance against three common early warning scores: Modified Early Warning Score, National Early Warning Score, and the Epic Deterioration Index.
Key Results
There were 87,783 patients (mean SD age 54.0 18.8 years; 45,835 52.2% women) who experienced 136,778 hospitalizations. 6214 hospitalized patients experienced a deterioration event. The machine learning model accurately identified 62% of deterioration events within 3-hours prior to the event and 47% of events within 12-hours. Across each time horizon, the model surpassed performance of the best early warning score including area under the receiver operating characteristic curve at 6-hours (0.856 vs. 0.781), sensitivity at 6-hours (0.590 vs. 0.505), specificity at 6-hours (0.900 vs. 0.878), and F-score at 6-hours (0.291 vs. 0.220).
Conclusions
Machine learning applied to the content and frequency of clinical pages improves prediction of imminent deterioration. Using clinical pages to monitor patient acuity supports improved detection of imminent deterioration without requiring changes to clinical workflow or nursing documentation.
Clickbusters letter response McCoy, Allison B; Russo, Elise M; Wright, Adam
Journal of the American Medical Informatics Association : JAMIA,
09/2023, Letnik:
30, Številka:
10
Journal Article
To develop and test an accurate deep learning model for predicting new onset delirium in hospitalized adult patients.
Using electronic health record (EHR) data extracted from a large academic medical ...center, we developed a model combining long short-term memory (LSTM) and machine learning to predict new onset delirium and compared its performance with machine-learning-only models (logistic regression, random forest, support vector machine, neural network, and LightGBM). The labels of models were confusion assessment method (CAM) assessments. We evaluated models on a hold-out dataset. We calculated Shapley additive explanations (SHAP) measures to gauge the feature impact on the model.
A total of 331 489 CAM assessments with 896 features from 34 035 patients were included. The LightGBM model achieved the best performance (AUC 0.927 0.924, 0.929 and F1 0.626 0.618, 0.634) among the machine learning models. When combined with the LSTM model, the final model's performance improved significantly (P = .001) with AUC 0.952 0.950, 0.955 and F1 0.759 0.755, 0.765. The precision value of the combined model improved from 0.497 to 0.751 with a fixed recall of 0.8. Using the mean absolute SHAP values, we identified the top 20 features, including age, heart rate, Richmond Agitation-Sedation Scale score, Morse fall risk score, pulse, respiratory rate, and level of care.
Leveraging LSTM to capture temporal trends and combining it with the LightGBM model can significantly improve the prediction of new onset delirium, providing an algorithmic basis for the subsequent development of clinical decision support tools for proactive delirium interventions.
Recently, continuous glucose monitors (CGM) have become increasingly available and affordable to support T2D management. Evidence to date supports CGM use in T2D to improve glycemic control and ...quality of life, across medication regimens and care settings. However, the rate and correlates of CGM uptake in T2D are unknown. We used electronic health record data to examine incidence of CGM use among adults (≥18 years old) receiving care for T2D at Vanderbilt University Medical Center. Eligible patients had T2D per a validated algorithm, and an A1c test and a primary care or endocrinology clinic visit from 10/1/2020 to 09/30/2021. We extracted historical data on CGM prescriptions and A1c values for these patients and compared CGM users and non-users on age, gender, race, ethnicity, insulin prescriptions, and A1c. Of the 26,841 adults seen for T2D, 12.3% (n=3,310) had been prescribed CGM. The earliest CGM prescriptions for the cohort appeared in Spring 2018. In 2021, each month an average of 110.2 patients (0.4% of cohort) were newly prescribed CGM (range 85-126 per month) . CGM use was associated with younger age, insulin use, and higher A1c, but not gender, race, or ethnicity (Table) . Since 2018, CGM use among adults with T2D has increased rapidly. Adults who are younger with higher A1c and using insulin are more likely to be prescribed CGM. There is potential to leverage the increase in CGM use among adults with T2D to improve outcomes and quality of life.
Disclosure
L. S. Mayberry: Consultant; Abbott Diabetes, Cecelia Health. C. Hendrickson: None. A. B. Mccoy: None. T. A. Elasy: None.
Despite growing interest in patient-reported outcome measures to track the progression of Crohn’s disease, frameworks to apply these questionnaires in the preoperative setting are lacking. Using the ...Short Inflammatory Bowel Disease Questionnaire (sIBDQ), this study aimed to describe the interpretable quality of life thresholds and examine potential associations with future bowel resection in Crohn’s disease.
Adult patients with Crohn’s disease completing an sIBDQ at a clinic visit between 2020 and 2022 were eligible. A stoplight framework was adopted for sIBDQ scores, including a “Resection Red” zone suggesting poor quality of life that may benefit from discussions about surgery as well as a “Nonoperative Green” zone. Thresholds were identified with both anchor- and distribution-based methods using receiver operating characteristic curve analysis and subgroup percentile scores, respectively. To quantify associations between sIBDQ scores and subsequent bowel resection, multivariable logistic regression models were fit with covariates of age, sex assigned at birth, body mass index, medications, disease pattern and location, resection history, and the Harvey Bradshaw Index. The incremental discriminatory value of the sIBDQ beyond clinical factors was assessed through the area under the receiver operating characteristics curve (AUC) with an internal validation through bootstrap resampling.
Of the 2003 included patients, 102 underwent Crohn’s-related bowel resection. The sIBDQ Nonoperative Green zone threshold ranged from 61 to 64 and the Resection Red zone from 36 to 38. When adjusting for clinical covariates, a worse sIBDQ score was associated with greater odds of subsequent 90-day bowel resection when considered as a 1-point (odds ratio OR 95% CI, 1.05 1.03-1.07) or 5-point change (OR 95% CI, 1.27 1.14-1.41). Inclusion of the sIBDQ modestly improved discriminative performance (AUC 95% CI, 0.85 0.85-0.86) relative to models that included only demographics (0.57 0.57-0.58) or demographics with clinical covariates (0.83 0.83-0.84).
In the decision-making process for bowel resection, disease-specific patient-reported outcome measures may be useful to identify patients with Crohn’s disease with poor quality of life and promote a shared understanding of personalized burden.
This study aimed to develop and assess the performance of fine-tuned large language models for generating responses to patient messages sent via an electronic health record patient portal.
Utilizing ...a dataset of messages and responses extracted from the patient portal at a large academic medical center, we developed a model (CLAIR-Short) based on a pre-trained large language model (LLaMA-65B). In addition, we used the OpenAI API to update physician responses from an open-source dataset into a format with informative paragraphs that offered patient education while emphasizing empathy and professionalism. By combining with this dataset, we further fine-tuned our model (CLAIR-Long). To evaluate fine-tuned models, we used 10 representative patient portal questions in primary care to generate responses. We asked primary care physicians to review generated responses from our models and ChatGPT and rated them for empathy, responsiveness, accuracy, and usefulness.
The dataset consisted of 499 794 pairs of patient messages and corresponding responses from the patient portal, with 5000 patient messages and ChatGPT-updated responses from an online platform. Four primary care physicians participated in the survey. CLAIR-Short exhibited the ability to generate concise responses similar to provider's responses. CLAIR-Long responses provided increased patient educational content compared to CLAIR-Short and were rated similarly to ChatGPT's responses, receiving positive evaluations for responsiveness, empathy, and accuracy, while receiving a neutral rating for usefulness.
This subjective analysis suggests that leveraging large language models to generate responses to patient messages demonstrates significant potential in facilitating communication between patients and healthcare providers.
First health care professionals arriving at the bedside in tracheostomy-related emergencies are rarely the surgical subspecialists who placed the tracheostomy and are unfamiliar with the relevant ...anatomy and tracheostomy specifications for the individual patient. We hypothesized that implementing a bedside airway safety placard would increase caregiver confidence, understanding of airway anatomy, and management of patients with a tracheostomy.
A prospective survey study was performed by distributing a tracheostomy airway safety survey before and after implementation of an airway safety placard in a 6-month study period. Placards emphasizing critical airway anomalies as well as emergency management algorithm suggestions designed by the otolaryngology team at the time of tracheostomy were placed at the head of the bed and traveled with the patient during transport around the hospital.
Of 377 staff members requested to complete the surveys, 165 (43.8%) responses were obtained, and 31 (8.2% 95% CI 5.7-11.5) paired pre- and post-implementation responses were recorded. Differences were found in the paired responses, including increases in the domains of confidence (
= .009) and experience (
= .01) post implementation. Less experienced providers (≤ 5 y of experience) (
= .005) and providers from neonatology (
= .049) demonstrated improved confidence post implementation, which was not observed in their more experienced (> 5 y) or respiratory therapy counterparts.
Given the limitations of a low survey response rate, our findings suggest that an educational airway safety placard initiative can be a simple, feasible, and low-cost quality improvement tool to enhance airway safety and possibly decrease potentially life-threating complications among pediatric patients with a tracheostomy. The implementation of the tracheostomy airway safety survey at our single institution warrants a larger multi-center study and validation of the survey.
PDF
