A machine-learning prediction model to identify risk of firearm injury using electronic health records data.

IMPORTANCE: Firearm injuries constitute a public health crisis. At the healthcare encounter level, they are, however, rare events. OBJECTIVE: To develop a predictive model to identify healthcare encounters of adult patients at increased risk of firearm injury to target screening and prevention efforts. MATERIALS AND METHODS: Electronic health records data from Kaiser Permanente Southern California (KPSC) were used to identify healthcare encounters of patients with fatal and non-fatal firearm injuries, as well as healthcare visits of a sample of matched controls during 2010-2018. More than 170 predictors, including diagnoses, healthcare utilization, and neighborhood characteristics were identified. Extreme gradient boosting (XGBoost) and a split sample design were used to train and test a model that predicted risk of firearm injury within the next 3 years at the encounter level. RESULTS: A total of 3879 firearm injuries were identified among 5 288 529 KPSC adult members. Prevalence at the healthcare encounter level was 0.01%. The 15 most important predictors included demographics, healthcare utilization, and neighborhood-level socio-economic factors. The sensitivity and specificity of the final model were 0.83 and 0.56, respectively. A very high-risk group (top 1% of predicted risk) yielded a positive predictive value of 0.14% and sensitivity of 13%. This high-risk group potentially reduces screening burden by a factor of 11.7, compared to universal screening. Results for alternative probability cutoffs are presented. DISCUSSION: Our model can support more targeted screening in healthcare settings, resulting in improved efficiency of firearm injury risk assessment and prevention efforts.

Identifying the Severity of Heart Valve Stenosis and Regurgitation Among a Diverse Population Within an Integrated Health Care System: Natural Language Processing Approach.

BACKGROUND: Valvular heart disease (VHD) is a leading cause of cardiovascular morbidity and mortality that poses a substantial health care and economic burden on health care systems. Administrative diagnostic codes for ascertaining VHD diagnosis are incomplete. OBJECTIVE: This study aimed to develop a natural language processing (NLP) algorithm to identify patients with aortic, mitral, tricuspid, and pulmonic valve stenosis and regurgitation from transthoracic echocardiography (TTE) reports within a large integrated health care system. METHODS: We used reports from echocardiograms performed in the Kaiser Permanente Southern California (KPSC) health care system between January 1, 2011, and December 31, 2022. Related terms/phrases of aortic, mitral, tricuspid, and pulmonic stenosis and regurgitation and their severities were compiled from the literature and enriched with input from clinicians. An NLP algorithm was iteratively developed and fine-trained via multiple rounds of chart review, followed by adjudication. The developed algorithm was applied to 200 annotated echocardiography reports to assess its performance and then the study echocardiography reports. RESULTS: A total of 1,225,270 TTE reports were extracted from KPSC electronic health records during the study period. In these reports, valve lesions identified included 111,300 (9.08%) aortic stenosis, 20,246 (1.65%) mitral stenosis, 397 (0.03%) tricuspid stenosis, 2585 (0.21%) pulmonic stenosis, 345,115 (28.17%) aortic regurgitation, 802,103 (65.46%) mitral regurgitation, 903,965 (73.78%) tricuspid regurgitation, and 286,903 (23.42%) pulmonic regurgitation. Among the valves, 50,507 (4.12%), 22,656 (1.85%), 1685 (0.14%), and 1767 (0.14%) were identified as prosthetic aortic valves, mitral valves, tricuspid valves, and pulmonic valves, respectively. Mild and moderate were the most common severity levels of heart valve stenosis, while trace and mild were the most common severity levels of regurgitation. Males had a higher frequency of aortic stenosis and all 4 valvular regurgitations, while females had more mitral, tricuspid, and pulmonic stenosis. Non-Hispanic Whites had the highest frequency of all 4 valvular stenosis and regurgitations. The distribution of valvular stenosis and regurgitation severity was similar across race/ethnicity groups. Frequencies of aortic stenosis, mitral stenosis, and regurgitation of all 4 heart valves increased with age. In TTE reports with stenosis detected, younger patients were more likely to have mild aortic stenosis, while older patients were more likely to have severe aortic stenosis. However, mitral stenosis was opposite (milder in older patients and more severe in younger patients). In TTE reports with regurgitation detected, younger patients had a higher frequency of severe/very severe aortic regurgitation. In comparison, older patients had higher frequencies of mild aortic regurgitation and severe mitral/tricuspid regurgitation. Validation of the NLP algorithm against the 200 annotated TTE reports showed excellent precision, recall, and F1-scores. CONCLUSIONS: The proposed computerized algorithm could effectively identify heart valve stenosis and regurgitation, as well as the severity of valvular involvement, with significant implications for pharmacoepidemiological studies and outcomes research.

Neighborhood Deprivation and Crime on Asthma Exacerbations and Utilization in Mild Adult Asthma.

BACKGROUND: Social determinants of health have a significant impact on asthma outcomes, and factors such as income level and neighborhood environment have crucial roles. OBJECTIVE: This study aimed to assess the impact of the Neighborhood Deprivation Index (NDI) and Total Crime Index (TCI) on acute asthma exacerbation (AAE) and asthma-related emergency department and urgent care (ED/UC) visits in adults with mild asthma. METHODS: This retrospective cohort study used administrative data from Kaiser Permanente Southern California among 198,873 adult patients with mild asthma between January 1, 2013 and December 31, 2018. We employed robust Poisson regression models, adjusted for age and sex, to investigate the associations of NDI and TCI with AAE and asthma-related ED/UC visits. Data analysis included subgroup assessments by race and ethnicity and body mass index categories to explore potential disparities in asthma outcomes. RESULTS: Among the cohort, 12,906 patients (6.5%) experienced AAE in 1 year, and Black patients had the highest AAE percentage (7.1%). Higher NDI quintiles were associated with increased AAE risk (adjusted risk ratio = 1.11-1.27), with similar trends across body mass index categories and race or ethnicity, except for Black patients. The TCI showed weaker associations with AAE. Regarding ED/UC visits, 5.0% had such visits within 1 year. Higher NDI quintiles were associated with higher ED/UC visit risk (adjusted risk ratio = 1.23-1.75) whereas TCI associations were weaker. CONCLUSION: Addressing socioeconomic disparities, as indicated by NDI, may be crucial in mitigating asthma exacerbations and reducing health care use, highlighting the importance of incorporating social determinants into asthma management strategies even in patients with mild asthma.

Identifying Elective Induction of Labor among a Diverse Pregnant Population from Electronic Health Records within a Large Integrated Health Care System.

OBJECTIVE: Distinguishing between medically indicated induction of labor (iIOL) and elective induction of labor (eIOL) is a daunting process for researchers. We aimed to develop a Natural Language Processing (NLP) algorithm to identify eIOLs from electronic health records (EHRs) within a large integrated health care system. STUDY DESIGN: We used structured and unstructured data from Kaiser Permanente Southern California's EHRs of patients who were <35 years old and had singleton deliveries between 37 and 40 gestational weeks. Induction of labor (IOL) pregnancies were identified if there was evidence of an IOL diagnosis code, procedure code, or documentation in a delivery flowsheet or progress note. A comprehensive NLP algorithm was developed and refined through an iterative process of chart reviews and adjudications, where IOL-associated reasons (medically indicated vs. elective induction) were reviewed. The final algorithm was applied to discern the indications of IOLs performed during the study period. RESULTS: A total of 332,163 eligible pregnancies were identified between January 1, 2008, and December 31, 2022. Of these eligible pregnancies, 68,541 (20.6%) were IOL, of which 6,824 (10.0%) were eIOL. Validation of the NLP process against 300 randomly selected pregnancies (100 eIOL, iIOL, and non-IOL cases each) yielded a positive predictive value of 83.0% and 88.0% for eIOL and iIOL, respectively. The rates of eIOL among the maternal age groups ranged between 9.6 and 10.3%, except for the <20 years group (12.2%). Non-Hispanic White individuals had the highest rate of eIOL (13.2%), while non-Hispanic Asian/Pacific Islanders had the lowest rate of eIOL (7.8%). The rate of eIOL increased from 1.0% in the 37-week gestational age (GA) group to 20.6% in the 40-week GA group. CONCLUSION: Findings suggest that the developed NLP algorithm effectively identifies eIOL. It can be utilized to support eIOL-related pharmacoepidemiological studies, fill in knowledge gaps, and provide content more relevant to researchers. KEY POINTS: · An NLP algorithm was developed to identify indications of IOL.. · The study algorithm was successfully implemented within a large integrated health care system.. · The study algorithm can be utilized to support eIOL-related studies..

Racial and Ethnic Differences in the Prevalence of Severe Aortic Stenosis by Echocardiography.

BACKGROUND: Understanding the burden of aortic stenosis (AS) across diverse racial and ethnic populations is important to ensure equitable resource allocation. This study explored whether severe AS rate varies by race and ethnicity. METHODS: The rates of severe AS, stratified by race and ethnicity, were calculated among 615,038 adults with a transthoracic echocardiogram. Logistic regression analysis was performed to identify factors associated with severe AS. RESULTS: Severe AS rates ranged from 0.08% in adults < 50 years old to 3.8% in those ≥ 90 years old. Compared to non-Hispanic White and Asian American [adjusted odds ratio (aOR) = 0.47, 95% confidence interval (CI): 0.42-0.53] and non-Hispanic Black (aOR = 0.44, 95% CI: 0.39-0.50) patients were less likely to have severe AS, whereas Hispanic patients (aOR = 0.91, 95% CI: 0.87-0.98) had near similar likelihood. Age was the strongest risk factor for severe AS (compared to age < 50 years, aOR = 21.8, 95% CI: 17.8-26.6 for age 80-89 years, and aOR = 43.8, 95% 35.5-54.0 for age ≥ 90 years). Additional factors associated with severe AS included male sex (aOR = 1.38, 95% CI: 1.30-1.46) and diabetes (aOR = 1.23, 95% CI: 1.15-1.31). CONCLUSIONS: Asian American and non-Hispanic Black adults had lower rates of severe AS compared to White and Hispanic patients. The rate of severe AS progressively increases with age in all racial and ethnic groups, with higher rates in men compared with women. With a demographic shift toward an aging and more diverse population, the burden of AS is anticipated to rise. Ensuring adequate allocation of resources to meet the evolving needs of a diverse population remains a shared health care imperative.

Identifying Symptoms Prior to Pancreatic Ductal Adenocarcinoma Diagnosis in Real-World Care Settings: Natural Language Processing Approach.

BACKGROUND: Pancreatic cancer is the third leading cause of cancer deaths in the United States. Pancreatic ductal adenocarcinoma (PDAC) is the most common form of pancreatic cancer, accounting for up to 90% of all cases. Patient-reported symptoms are often the triggers of cancer diagnosis and therefore, understanding the PDAC-associated symptoms and the timing of symptom onset could facilitate early detection of PDAC. OBJECTIVE: This paper aims to develop a natural language processing (NLP) algorithm to capture symptoms associated with PDAC from clinical notes within a large integrated health care system. METHODS: We used unstructured data within 2 years prior to PDAC diagnosis between 2010 and 2019 and among matched patients without PDAC to identify 17 PDAC-related symptoms. Related terms and phrases were first compiled from publicly available resources and then recursively reviewed and enriched with input from clinicians and chart review. A computerized NLP algorithm was iteratively developed and fine-trained via multiple rounds of chart review followed by adjudication. Finally, the developed algorithm was applied to the validation data set to assess performance and to the study implementation notes. RESULTS: A total of 408,147 and 709,789 notes were retrieved from 2611 patients with PDAC and 10,085 matched patients without PDAC, respectively. In descending order, the symptom distribution of the study implementation notes ranged from 4.98% for abdominal or epigastric pain to 0.05% for upper extremity deep vein thrombosis in the PDAC group, and from 1.75% for back pain to 0.01% for pale stool in the non-PDAC group. Validation of the NLP algorithm against adjudicated chart review results of 1000 notes showed that precision ranged from 98.9% (jaundice) to 84% (upper extremity deep vein thrombosis), recall ranged from 98.1% (weight loss) to 82.8% (epigastric bloating), and F1-scores ranged from 0.97 (jaundice) to 0.86 (depression). CONCLUSIONS: The developed and validated NLP algorithm could be used for the early detection of PDAC.

Management, Utilization, and Outcomes of Preterm Labor in an Integrated Health Care System.

OBJECTIVE: Fetal fibronectin (fFN) testing and transvaginal ultrasound (TVUS) are diagnostic tools used to predict impending spontaneous preterm birth (sPTB) among women presenting with preterm labor (PTL). We evaluated the association between fFN testing or TVUS cervical length (CL) measurement in predicting sPTB, respiratory distress syndrome (RDS), neonatal intensive care unit (NICU) admission, and sPTB-related costs. STUDY DESIGN: We conducted a retrospective cohort study using data from the Kaiser Permanente Southern California electronic health system (January 1, 2009-December 31, 2020) using diagnostic and procedure codes, along with a natural language processing algorithm to identify pregnancies with PTL evaluations. PTL evaluation was defined as having fFN and/or TVUS assessment. Outcomes were ascertained using diagnostic, procedural, and diagnosis-related group codes. Multivariable logistic regression assessed the association between fFN and/or TVUS results and perinatal outcomes. RESULTS: Compared with those without PTL evaluations, those with positive fFN tests had higher adjusted odds ratio (adj.OR) for sPTB (2.95, 95% confidence interval [CI]: 2.64, 3.29), RDS (2.34, 95% CI: 2.03, 2.69), and NICU admission (2.24, 95% CI: 2.01, 2.50). In contrast, those who tested negative had lower odds for sPTB (adj.OR: 0.75, 95% CI: 0.70, 0.79), RDS (adj.OR: 0.67, 95% CI: 0.61, 0.73), and NICU admission (adj.OR: 0.74, 95% CI: 0.70, 0.79). Among those with positive fFN results, the odds of sPTB was inversely associated with CL. Health care costs for mothers and neonates were lowest for those with fFN testing only. CONCLUSION: This study demonstrates that positive fFN results were associated with an increased odds of sPTB, RDS, and NICU admission and the association with sPTB was inversely proportional to CL. Additionally, negative fFN results were associated with decreased odds of sPTB, RDS, and NICU admissions. fFN testing may predict these and other sPTB-related adverse outcomes hence its utility should be explored further. Moreover, fFN testing has some cost savings over TVUS. KEY POINTS: · Patients with positive fFN tests had higher odds of sPTB, RDS, and NICU admission.. · Inverse relationship between sPTB and CL among those with positive fFN tests was observed.. · Health care costs for mothers and neonates were lowest for those with fFN testing only..

Risk Factors for Acute Asthma Exacerbations in Adults With Mild Asthma.

BACKGROUND: Although individuals with mild asthma account for 30% to 40% of acute asthma exacerbations (AAEs), relatively little attention has been paid to risk factors for AAEs in this population. OBJECTIVE: To identify risk factors associated with AAEs in patients with mild asthma. METHODS: This was a retrospective cohort study. We used administrative data from a large managed care organization to identify 199,010 adults aged 18 to 85 years who met study criteria for mild asthma between 2013 and 2018. An asthma-coded qualifying visit (index visit) was identified for each patient. We then used information at the index visit or from the year before the index visit to measure potential risk factors for AAEs in the subsequent year. An AAE was defined as either an asthma-coded hospitalization or emergency department visit, or an asthma-related systemic corticosteroid administration (intramuscular or intravenous) or oral corticosteroid dispensing. Poisson regression models with robust SEs were used to estimate the adjusted risk ratios for future AAEs. RESULTS: In the study cohort, mean age was 44 years and 64% were female; 6.5% had AAEs within 1 year after the index visit. In multivariate models, age, sex, race, ethnicity, smoking status, body mass index, prior acute asthma care, and a variety of comorbidities and other clinical characteristics were significant predictors for future AAE risk. CONCLUSION: Population-based disease management strategies for asthma should be expanded to include people with mild asthma in addition to those with moderate to severe disease.

Effectiveness of BNT162b2 BA.4/5 bivalent mRNA vaccine against a range of COVID-19 outcomes in a large health system in the USA: a test-negative case-control study.

BACKGROUND: XBB-related omicron sublineages have recently replaced BA.4/5 as the predominant omicron sublineages in the USA and other regions globally. Despite preliminary signs of immune evasion of XBB sublineages, few data exist describing the real-world effectiveness of bivalent COVID-19 vaccines, especially against XBB-related illness. We aimed to investigate the effectiveness of the Pfizer--BioNTech BNT162b2 BA.4/5 bivalent vaccine against both BA.4/5-related and XBB-related disease in adults aged 18 years or older. METHODS: In this test-negative case-control study, we estimated the effectiveness of the BNT162b2 BA.4/5 bivalent vaccine using data from electronic health records of Kaiser Permanente Southern California health system members aged 18 years or older who received at least two doses of the wild-type COVID-19 mRNA vaccines. Participants sought care for acute respiratory infection between Aug 31, 2022, and April 15, 2023, and were tested for SARS-CoV-2 via PCR tests. Relative vaccine effectiveness (≥2 doses of wild-type mRNA vaccine plus a BNT162b2 BA.4/5 bivalent booster vs ≥2 doses of a wild-type mRNA vaccine alone) and absolute vaccine effectiveness (vs unvaccinated individuals) was estimated against critical illness related to acute respiratory infection (intensive care unit [ICU] admission, mechanical ventilation, or inpatient death), hospital admission, emergency department or urgent care visits, and in-person outpatient encounters with odds ratios from logistic regression models adjusted for demographic and clinical factors. We stratified vaccine effectiveness estimates for hospital admission, emergency department or urgent care visits, and outpatient encounters by omicron sublineage (ie, likely BA.4/5-related vs likely XBB-related), time since bivalent booster receipt, age group, number of wild-type doses received, and immunocompromised status. This study is registered with ClinicalTrials.gov (NCT04848584). FINDINGS: Analyses were conducted for 123 419 encounters (24 246 COVID-19 cases and 99 173 test-negative controls), including 4131 episode of critical illness (a subset of hospital admissions), 14 529 hospital admissions, 63 566 emergency department or urgent care visits, and 45 324 outpatient visits. 20 555 infections were BA.4/5 related and 3691 were XBB related. In adjusted analyses, relative vaccine effectiveness for those who received the BNT162b2 BA.4/5 bivalent booster compared with those who received at least two doses of a wild-type mRNA vaccine alone was an additional 50% (95% CI 23-68) against critical illness, an additional 39% (28-49) against hospital admission, an additional 35% (30-40) against emergency department or urgent care visits, and an additional 28% (22-33) against outpatient encounters. Waning of the bivalent booster from 0-3 months to 4-7 months after vaccination was evident for outpatient outcomes but was not detected for critical illness, hospital admission, and emergency department or urgent care outcomes. The relative effectiveness of the BNT162b2 BA.4/5 bivalent booster for XBB-related infections compared with BA.4/5-related infections was 56% (95% CI 12-78) versus 40% (27-50) for hospital admission; 34% (21-45) versus 36% (30-41) against emergency department or urgent care visits; and 29% (19-38) versus 27% (20-33) for outpatient encounters. INTERPRETATION: By mid-April, 2023, individuals previously vaccinated only with wild-type vaccines had little protection against COVID-19-including hospital admission. A BNT162b2 BA.4/5 bivalent booster restored protection against a range of COVID-19 outcomes, including against XBB-related sublineages, with the most substantial protection observed against hospital admission and critical illness. FUNDING: Pfizer.

Using natural language processing to identify the status of homelessness and housing instability among serious illness patients from clinical notes in an integrated healthcare system.

Background: Efficiently identifying the social risks of patients with serious illnesses (SIs) is the critical first step in providing patient-centered and value-driven care for this medically vulnerable population. Objective: To apply and further hone an existing natural language process (NLP) algorithm that identifies patients who are homeless/at risk of homeless to a SI population. Methods: Patients diagnosed with SI between 2019 and 2020 were identified using an adapted list of diagnosis codes from the Center for Advance Palliative Care from the Kaiser Permanente Southern California electronic health record. Clinical notes associated with medical encounters within 6 months before and after the diagnosis date were processed by a previously developed NLP algorithm to identify patients who were homeless/at risk of homelessness. To improve the generalizability to the SI population, the algorithm was refined by multiple iterations of chart review and adjudication. The updated algorithm was then applied to the SI population. Results: Among 206 993 patients with a SI diagnosis, 1737 (0.84%) were identified as homeless/at risk of homelessness. These patients were more likely to be male (51.1%), age among 45-64 years (44.7%), and have one or more emergency visit (65.8%) within a year of their diagnosis date. Validation of the updated algorithm yielded a sensitivity of 100.0% and a positive predictive value of 93.8%. Conclusions: The improved NLP algorithm effectively identified patients with SI who were homeless/at risk of homelessness and can be used to target interventions for this vulnerable group.

Risks of Uterine Perforation and Expulsion Associated With Intrauterine Devices.

OBJECTIVE: The APEX-IUD (Association of Perforation and Expulsion of Intrauterine Devices) study evaluated the association of postpartum timing of intrauterine device (IUD) insertion, breastfeeding, heavy menstrual bleeding, and IUD type (levonorgestrel-releasing vs copper) with risks of uterine perforation and IUD expulsion in usual clinical practice. We summarize the clinically important findings to inform counseling and shared decision making. METHODS: APEX-IUD was a real-world (using U.S. health care data) retrospective cohort study of individuals aged 50 years and younger with IUD insertions between 2001 and 2018 and with electronic health record data. Cumulative incidences of uterine perforation and IUD expulsion were calculated. Adjusted hazard ratios (aHRs) and 95% CIs were estimated from proportional hazards models with control of confounding. RESULTS: Among the study population of 326,658, absolute risk of uterine perforation was low overall (cumulative incidence, 0.21% [95% CI 0.19-0.23%] at 1 year and 0.61% [95% CI 0.56-0.66% at 5 years]) but was elevated for IUDs inserted during time intervals within 1 year postpartum, particularly among those between 4 days and 6 weeks postpartum (aHR 6.71, 95% CI 4.80-9.38), relative to nonpostpartum insertions. Among postpartum insertions, IUD expulsion risk was greatest for insertions in the immediate postpartum period (0-3 days after delivery) compared with nonpostpartum (aHR 5.34, 95% CI 4.47-6.39). Postpartum individuals who were breastfeeding had a slightly elevated risk of perforation and lowered risk of expulsion than those not breastfeeding. Among nonpostpartum individuals, those with a heavy menstrual bleeding diagnosis were at greater risk of expulsion than those without (aHR 2.84, 95% CI 2.66-3.03); heavy menstrual bleeding also was associated with a slightly elevated perforation risk. There was a slightly elevated perforation risk and slightly lower expulsion risk associated with levonorgestrel-releasing IUDs compared with copper IUDs. CONCLUSION: Absolute risk of adverse outcomes with IUD insertion is low. Clinicians should be aware of the differences in risks of uterine perforation and expulsion associated with IUD insertion during specific postpartum time periods and with a heavy menstrual bleeding diagnosis. This information should be incorporated into counseling and decision making for patients considering IUD insertion. FUNDING SOURCE: Bayer AG. CLINICAL TRIAL REGISTRATION: EU PAS register, EUPAS33461.

Research data warehouse: using electronic health records to conduct population-based observational studies.

Background: Electronic health records and many legacy systems contain rich longitudinal data that can be used for research; however, they typically are not readily available. Materials and methods: At Kaiser Permanente Southern California (KPSC), a research data warehouse (RDW) has been developed and maintained since the late 1990s and widely extended in 2006, aggregating and standardizing data collected from internal and a few external sources. This article provides a high-level overview of the RDW and discusses challenges common to data warehouses or repositories for research use. To demonstrate the application of the data, we report the volume, patient characteristics, and age-adjusted prevalence of selected medical conditions and utilization rates of selected medical procedures. Results: A total of 105 million person-years of health plan enrollment was recorded in the RDW between 1981 and 2018, with most healthcare utilization data available since early or middle 1990s. Among active enrollees on December 31, 2018, 15% were ≥65 years of age, 33.9% were non-Hispanic white, 43.3% Hispanic, 11.0% Asian, and 8.4% African American, and 34.4% of children (2-17 years old) and 72.1% of adults (≥18 years old) were overweight or obese. The age-adjusted prevalence of asthma, atrial fibrillation, diabetes mellitus, hypercholesteremia, and hypertension increased between 2001 and 2018. Hospitalization and Emergency Department (ED) visit rates appeared lower, and office visit rates seemed higher at KPSC compared to the reported US averages. Discussion and conclusion: Although the RDW is unique to KPSC, its methodologies and experience may provide useful insights for researchers of other healthcare systems worldwide in the era of big data analysis.

Effectiveness of a fourth dose of mRNA-1273 against COVID-19 among older adults in the United States: Interim results from an observational cohort study.

We evaluated relative vaccine effectiveness (rVE) of 4- vs. 3-dose mRNA-1273 against SARS-CoV-2 infection, and COVID-19 hospitalization and death in immunocompetent adults aged ≥50 years at Kaiser Permanente Southern California. We included 178,492 individuals who received a fourth dose of mRNA-1273, and 178,492 randomly selected 3-dose recipients who were matched to 4-dose recipients by age, sex, race/ethnicity, and third dose date. Adjusted 4- vs. 3-dose rVE against SARS-CoV-2 infection, COVID-19 hospitalization, and COVID-19 hospitalization death were 25.9 % (23.5 %, 28.2 %), 67.3 % (58.7 %, 74.1 %), and 72.5 % (-35.9 %, 95.2 %), respectively. Adjusted rVE against SARS-CoV-2 infection ranged between 19.8 % and 39.1 % across subgroups. Adjusted rVE against SARS-CoV-2 infection and COVID-19 hospitalization decreased 2-4 months after the fourth dose. Four mRNA-1273 doses provided significant protection against COVID-19 outcomes compared with 3 doses, consistent in various subgroups of demographic and clinical characteristics, although rVE varied and waned over time.

Machine learning versus regression for prediction of sporadic pancreatic cancer.

BACKGROUND/OBJECTIVES: There is currently no widely accepted approach to identify patients at increased risk for sporadic pancreatic cancer (PC). We aimed to compare the performance of two machine-learning models with a regression-based model in predicting pancreatic ductal adenocarcinoma (PDAC), the most common form of PC. METHODS: This retrospective cohort study consisted of patients 50-84 years of age enrolled in either Kaiser Permanente Southern California (KPSC, model training, internal validation) or the Veterans Affairs (VA, external testing) between 2008 and 2017. The performance of random survival forests (RSF) and eXtreme gradient boosting (XGB) models were compared to that of COX proportional hazards regression (COX). Heterogeneity of the three models were assessed. RESULTS: The KPSC and the VA cohorts consisted of 1.8 and 2.7 million patients with 1792 and 4582 incident PDAC cases within 18 months, respectively. Predictors selected into all three models included age, abdominal pain, weight change, and glycated hemoglobin (A1c). Additionally, RSF selected change in alanine transaminase (ALT), whereas the XGB and COX selected the rate of change in ALT. The COX model appeared to have lower AUC (KPSC: 0.737, 95% CI 0.710-0.764; VA: 0.706, 0.699-0.714), compared to those of RSF (KPSC: 0.767, 0.744-0.791; VA: 0.731, 0.724-0.739) and XGB (KPSC: 0.779, 0.755-0.802; VA: 0.742, 0.735-0.750). Among patients with top 5% predicted risk from all three models (N = 29,663), 117 developed PDAC, of which RSF, XGB and COX captured 84 (9 unique), 87 (4 unique), 87 (19 unique) cases, respectively. CONCLUSIONS: The three models complement each other, but each has unique contributions.

Prior SARS-CoV-2 infection and COVID-19 vaccine effectiveness against outpatient illness during widespread circulation of SARS-CoV-2 Omicron variant, US Flu VE network.

BACKGROUND: We estimated combined protection conferred by prior SARS-CoV-2 infection and COVID-19 vaccination against COVID-19-associated acute respiratory illness (ARI). METHODS: During SARS-CoV-2 Delta (B.1.617.2) and Omicron (B.1.1.529) variant circulation between October 2021 and April 2022, prospectively enrolled adult patients with outpatient ARI had respiratory and filter paper blood specimens collected for SARS-CoV-2 molecular testing and serology. Dried blood spots were tested for immunoglobulin-G antibodies against SARS-CoV-2 nucleocapsid (NP) and spike protein receptor binding domain antigen using a validated multiplex bead assay. Evidence of prior SARS-CoV-2 infection also included documented or self-reported laboratory-confirmed COVID-19. We used documented COVID-19 vaccination status to estimate vaccine effectiveness (VE) by multivariable logistic regression by prior infection status. RESULTS: Four hundred fifty-five (29%) of 1577 participants tested positive for SARS-CoV-2 infection at enrollment; 209 (46%) case-patients and 637 (57%) test-negative patients were NP seropositive, had documented previous laboratory-confirmed COVID-19, or self-reported prior infection. Among previously uninfected patients, three-dose VE was 97% (95% confidence interval [CI], 60%-99%) against Delta, but not statistically significant against Omicron. Among previously infected patients, three-dose VE was 57% (CI, 20%-76%) against Omicron; VE against Delta could not be estimated. CONCLUSIONS: Three mRNA COVID-19 vaccine doses provided additional protection against SARS-CoV-2 Omicron variant-associated illness among previously infected participants.

Prediction of persistent chronic cough in patients with chronic cough using machine learning.

Introduction: The aim of this study was to develop and validate prediction models for risk of persistent chronic cough (PCC) in patients with chronic cough (CC). This was a retrospective cohort study. Methods: Two retrospective cohorts of patients 18-85 years of age were identified for years 2011-2016: a specialist cohort which included CC patients diagnosed by specialists, and an event cohort which comprised CC patients identified by at least three cough events. A cough event could be a cough diagnosis, dispensing of cough medication or any indication of cough in clinical notes. Model training and validation were conducted using two machine-learning approaches and 400+ features. Sensitivity analyses were also conducted. PCC was defined as a CC diagnosis or any two (specialist cohort) or three (event cohort) cough events in year 2 and again in year 3 after the index date. Results: 8581 and 52 010 patients met the eligibility criteria for the specialist and event cohorts (mean age 60.0 and 55.5 years), respectively. 38.2% and 12.4% of patients in the specialist and event cohorts, respectively, developed PCC. The utilisation-based models were mainly based on baseline healthcare utilisations associated with CC or respiratory diseases, while the diagnosis-based models incorporated traditional parameters including age, asthma, pulmonary fibrosis, obstructive pulmonary disease, gastro-oesophageal reflux, hypertension and bronchiectasis. All final models were parsimonious (five to seven predictors) and moderately accurate (area under the curve: 0.74-0.76 for utilisation-based models and 0.71 for diagnosis-based models). Conclusions: The application of our risk prediction models may be used to identify high-risk PCC patients at any stage of the clinical testing/evaluation to facilitate decision making.

Automated placental abruption identification using semantic segmentation, quantitative features, SVM, ensemble and multi-path CNN.

The placenta is a fundamental organ throughout the pregnancy and the fetus' health is closely related to its proper function. Because of the importance of the placenta, any suspicious placental conditions require ultrasound image investigation. We propose an automated method for processing fetal ultrasonography images to identify placental abruption using machine learning methods in this paper. The placental imaging characteristics are used as the semantic identifiers of the region of the placenta compared with the amniotic fluid and hard organs. The quantitative feature extraction is applied to the automatically identified placental regions to assign a vector of optical features to each ultrasonographic image. In the first classification step, two methods of kernel-based Support Vector Machine (SVM) and decision tree Ensemble classifier are elaborated and compared for identification of the abruption cases and controls. The Recursive Feature Elimination (RFE) is applied for optimizing the feature vector elements for the best performance of each classifier. In the second step, the deep learning classifiers of multi-path ResNet-50 and Inception-V3 are used in combination with RFE. The resulting performances of the algorithms are compared together to reveal the best classification method for the identification of the abruption status. The best results were achieved for optimized ResNet-50 with an accuracy of 82.88% ± SD 1.42% in the identification of placental abruption on the testing dataset. These results show it is possible to construct an automated analysis method with affordable performance for the detection of placental abruption based on ultrasound images.

Analysis of mRNA COVID-19 Vaccine Uptake Among Immunocompromised Individuals in a Large US Health System.

Importance: Immunocompromised individuals are at increased risk for severe outcomes due to SARS-CoV-2 infection. Given the varying and complex nature of COVID-19 vaccination recommendations, it is important to understand COVID-19 vaccine uptake in this vulnerable population. Objective: To assess mRNA COVID-19 vaccine uptake and factors associated with uptake among immunocompromised individuals from December 14, 2020, through August 6, 2022. Design, Setting, and Participants: This cohort study was conducted with patients of Kaiser Permanente Southern California (KPSC), an integrated health care system in the US. The study included patients aged 18 years or older who were immunocompromised (individuals with an immunocompromising condition or patients who received immunosuppressive medications in the year prior to December 14, 2020) and still met criteria for being immunocompromised 1 year later. Exposures: Age, sex, self-identified race and ethnicity, prior positive COVID-19 test result, immunocompromising condition, immunomodulating medication, comorbidities, health care utilization, and neighborhood median income. Main Outcomes and Measures: Outcomes were the number of doses of mRNA COVID-19 vaccine received and the factors associated with receipt of at least 4 doses, estimated by hazard ratios (HRs) and 95% Wald CIs via Cox proportional hazards regression. Statistical analyses were conducted between August 9 and 23, 2022. Results: Overall, 42 697 immunocompromised individuals met the study eligibility criteria. Among these, 18 789 (44.0%) were aged 65 years or older; 20 061 (47.0%) were women and 22 635 (53.0%) were men. With regard to race and ethnicity, 4295 participants (10.1%) identified as Asian or Pacific Islander, 5174 (12.1%) as Black, 14 289 (33.5%) as Hispanic, and 17 902 (41.9%) as White. As of the end of the study period and after accounting for participant censoring due to death or disenrollment from the KPSC health plan, 78.0% of immunocompromised individuals had received a third dose of mRNA COVID-19 vaccine. Only 41.0% had received a fourth dose, which corresponds to a primary series and a monovalent booster dose for immunocompromised individuals. Uptake of a fifth dose was only 0.9% following the US Centers for Disease Control and Prevention (CDC) recommendation to receive a second monovalent booster (ie, fifth dose). Adults aged 65 years or older (HR, 3.95 [95% CI, 3.70-4.22]) were more likely to receive at least 4 doses compared with those aged 18 to 44 years or 45 to 64 years (2.52 [2.36-2.69]). Hispanic and non-Hispanic Black adults (HR, 0.77 [95% CI, 0.74-0.80] and 0.82 [0.78-0.87], respectively, compared with non-Hispanic White adults), individuals with prior documented SARS-CoV-2 infection (0.71 [0.62-0.81] compared with those without), and individuals receiving high-dose corticosteroids (0.88 [0.81-0.95] compared with those who were not) were less likely to receive at least 4 doses. Conclusions and Relevance: These findings suggest that adherence to CDC mRNA monovalent COVID-19 booster dose recommendations among immunocompromised individuals was low. Given the increased risk for severe COVID-19 in this vulnerable population and the well-established additional protection afforded by booster doses, targeted and tailored efforts to ensure that immunocompromised individuals remain up to date with COVID-19 booster dose recommendations are warranted.

Chronic and Sustained High-Dose Opioid Use in an Integrated Health System.

INTRODUCTION: The Centers for Disease Control and Prevention Guideline for Prescribing Opioids for Chronic Pain released in 2016 had led to decreases in opioid prescribing. This study sought to examine chronic and sustained high-dose prescription opioid use in an integrated health system. METHODS: A serial cross-sectional study was conducted in 2021 to estimate the annual age-adjusted prevalence and incidence of chronic and high-dose opioid use among demographically diverse noncancer adults in an integrated health system in Southern California during 2013-2020. Interrupted time-series analysis with segmented regression was conducted to estimate changes in the trends in annual rates before (2013-2015) and after (2017-2020) the 2016 guideline, treating 2016 as a wash-out period. RESULTS: Prevalence and incidence of chronic use and sustained high-dose use had started to decrease after a health system intervention program before the 2016 Centers for Disease Control and Prevention guideline release and continued to decline after the guideline. Among those with sustained high-dose use, there was a substantial decrease in persons with an average daily dosage ≥90 morphine milligram equivalent and concurrent benzodiazepine use. An accelerated decrease in prevalent chronic use after the guideline was observed (slope change: -11.1 [95% CI= -20.3, -1.9] users/10,000 person-years, p=0.03). The incidence of chronic use and sustained high-dose use continued to decrease after the guideline release but at a slower pace. CONCLUSIONS: Implementing evidence-based prescribing guidelines was associated with a decrease in chronic and sustained high-dose prescription opioid use.

Prior SARS-CoV-2 Infection and COVID-19 Vaccine Effectiveness against Outpatient Illness during Widespread Circulation of SARS-CoV-2 Omicron Variant, US Flu VE Network.

Background: We estimated combined protection conferred by prior SARS-CoV-2 infection and COVID-19 vaccination against COVID-19-associated acute respiratory illness (ARI). Methods: During SARS-CoV-2 Delta (B.1.617.2) and Omicron (B.1.1.529) variant circulation between October 2021 and April 2022, prospectively enrolled adult patients with outpatient ARI had respiratory and filter paper blood specimens collected for SARS-CoV-2 molecular testing and serology. Dried blood spots were tested for immunoglobulin-G antibodies against SARS-CoV-2 nucleocapsid (NP) and spike protein receptor binding domain antigen using a validated multiplex bead assay. Evidence of prior SARS-CoV-2 infection also included documented or self-reported laboratory-confirmed COVID-19. We used documented COVID-19 vaccination status to estimate vaccine effectiveness (VE) by multivariable logistic regression by prior infection status. Results: 455 (29%) of 1577 participants tested positive for SARS-CoV-2 infection at enrollment; 209 (46%) case-patients and 637 (57%) test-negative patients were NP seropositive, had documented previous laboratory-confirmed COVID-19, or self-reported prior infection. Among previously uninfected patients, three-dose VE was 97% (95% confidence interval [CI], 60%- 99%) against Delta, but not statistically significant against Omicron. Among previously infected patients, three-dose VE was 57% (CI, 20%-76%) against Omicron; VE against Delta could not be estimated. Conclusions: Three mRNA COVID-19 vaccine doses provided additional protection against SARS-CoV-2 Omicron variant-associated illness among previously infected participants.