Development and validation of a machine-learning prediction model to improve abdominal aortic aneurysm screening.

OBJECTIVE: Despite recommendations by the United States Preventive Services Task Force and the Society for Vascular Surgery, adoption of screening for abdominal aortic aneurysms (AAAs) remains low. One challenge is the low prevalence of AAAs in the unscreened population, and therefore a low detection rate for AAA screenings. We sought to use machine learning to identify factors associated with the presence of AAAs and create a model to identify individuals at highest risk for AAAs, with the aim of increasing the detection rate of AAA screenings. METHODS: A machine-learning model was trained using longitudinal medical records containing lab results, medications, and other data from our institutional database. A retrospective cohort study was performed identifying current or past smoking in patients aged 65 to 75 years and stratifying the patients by sex and smoking status as well as determining which patients had a confirmed diagnosis of AAA. The model was then adjusted to maximize fairness between sexes without significantly reducing precision and validated using six-fold cross validation. RESULTS: Validation of the algorithm on the single-center institutional data utilized 18,660 selected patients over 2 years and identified 314 AAAs. There were 41 factors identified in the medical record included in the machine-learning algorithm, with several factors never having been previously identified to be associated with AAAs. With an estimated 100 screening ultrasounds completed monthly, detection of AAAs is increased with a lift of 200% using the algorithm as compared with screening based on guidelines. The increased detection of AAAs in the model-selected individuals is statistically significant across all cutoff points. CONCLUSIONS: By utilizing a machine-learning model, we created a novel algorithm to detect patients who are at high risk for AAAs. By selecting individuals at greatest risk for targeted screening, this algorithm resulted in a 200% lift in the detection of AAAs when compared with standard screening guidelines. Using machine learning, we also identified several new factors associated with the presence of AAAs. This automated process has been integrated into our current workflows to improve screening rates and yield of high-risk individuals for AAAs.

Prediction of Influenza Complications: Development and Validation of a Machine Learning Prediction Model to Improve and Expand the Identification of Vaccine-Hesitant Patients at Risk of Severe Influenza Complications.

Influenza vaccinations are recommended for high-risk individuals, but few population-based strategies exist to identify individual risks. Patient-level data from unvaccinated individuals, stratified into retrospective cases (n = 111,022) and controls (n = 2,207,714), informed a machine learning model designed to create an influenza risk score; the model was called the Geisinger Flu-Complications Flag (GFlu-CxFlag). The flag was created and validated on a cohort of 604,389 unique individuals. Risk scores were generated for influenza cases; the complication rate for individuals without influenza was estimated to adjust for unrelated complications. Shapley values were used to examine the model's correctness and demonstrate its dependence on different features. Bias was assessed for race and sex. Inverse propensity weighting was used in the derivation stage to correct for biases. The GFlu-CxFlag model was compared to the pre-existing Medial EarlySign Flu Algomarker and existing risk guidelines that describe high-risk patients who would benefit from influenza vaccination. The GFlu-CxFlag outperformed other traditional risk-based models; the area under curve (AUC) was 0.786 [0.783−0.789], compared with 0.694 [0.690−0.698] (p-value < 0.00001). The presence of acute and chronic respiratory diseases, age, and previous emergency department visits contributed most to the GFlu-CxFlag model's prediction. When higher numerical scores were assigned to more severe complications, the GFlu-CxFlag AUC increased to 0.828 [0.823−0.833], with excellent discrimination in the final model used to perform the risk stratification of the population. The GFlu-CxFlag can better identify high-risk individuals than existing models based on vaccination guidelines, thus creating a population-based risk stratification for individual risk assessment and deployment in vaccine hesitancy reduction programs in our health system.

Informing patients that they are at high risk for serious complications of viral infection increases vaccination rates.

For many vaccine-preventable diseases like influenza, vaccination rates are lower than optimal to achieve community protection. Those at high risk for infection and serious complications are especially advised to be vaccinated to protect themselves. Using influenza as a model, we studied one method of increasing vaccine uptake: informing high-risk patients, identified by a machine learning model, about their risk status. Patients (N=39,717) were evenly randomized to (1) a control condition (exposure only to standard direct mail or patient portal vaccine promotion efforts) or to be told via direct mail, patient portal, and/or SMS that they were (2) at high risk for influenza and its complications if not vaccinated; (3) at high risk according to a review of their medical records; or (4) at high risk according to a computer algorithm analysis of their medical records. Patients in the three treatment conditions were 5.7% more likely to get vaccinated during the 112 days post-intervention (p < .001), and did so 1.4 days earlier (p < .001), on average, than those in the control group. There were no significant differences among risk messages, suggesting that patients are neither especially averse to nor uniquely appreciative of learning their records had been reviewed or that computer algorithms were involved. Similar approaches should be considered for COVID-19 vaccination campaigns.