Prediction of pancreatic cancer in patients with new onset hyperglycemia: A modified ENDPAC model.

BACKGROUND/OBJECTIVES: The Enriching New-Onset Diabetes for Pancreatic Cancer (ENDPAC) model relies primarily on fasting glucose values. Health systems have increasingly shifted practice towards use of glycated hemoglobin (HbA1c) measurement. We modified the ENDPAC model using patients with new onset hyperglycemia. METHODS: Four cohorts of patients 50-84 years of age with HbA1c results ≥6.2-6.5 % in 2011-2018 were identified. A combine cohort was formed. A widened eligibility criterion was applied to form additional four individual cohorts and one combined cohort. The primary outcome was the diagnosis of pancreatic cancer within 3 years after the first elevated HbA1c testing. The performance of the modified ENDPAC model was evaluated by AUC, sensitivity, positive predictive value, cases detected, and total number of patients screened. RESULTS: The individual and combined cohorts consisted of 39,001-79,060 and 69,334-92,818 patients, respectively (mean age 63.5-65.0 years). The three-year PC incidence rates were 0.47%-0.54 %. The AUC measures were in the range of 0.75-0.77 for the individual cohorts and 0.75 for the combined cohorts. When the four individual cohorts were combined, more PC cases can be identified (149 by the combined vs. 113-116 by individual cohorts when risk score was 5+). Performance measures were compromised in nonwhites. Asian and Pacific islanders had lower sensitivity compared to other racial and ethnic groups (29 % vs. 50-60 %) when risk score was 5+. CONCLUSIONS: The modified ENDPAC model targets a broader population and thus identifies more high-risk patients for cancer screening. The differential performance needs to be considered when the model is applied to non-white population.

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..

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..

Derivation and External Validation of Machine Learning-Based Model for Detection of Pancreatic Cancer.

INTRODUCTION: There is currently no widely accepted approach to screening for pancreatic cancer (PC). We aimed to develop and validate a risk prediction model for pancreatic ductal adenocarcinoma (PDAC), the most common form of PC, across 2 health systems using electronic health records. METHODS: This retrospective cohort study consisted of patients aged 50-84 years having at least 1 clinic-based visit over a 10-year study period at Kaiser Permanente Southern California (model training, internal validation) and the Veterans Affairs (VA, external testing). Random survival forests models were built to identify the most relevant predictors from >500 variables and to predict risk of PDAC within 18 months of cohort entry. RESULTS: The Kaiser Permanente Southern California cohort consisted of 1.8 million patients (mean age 61.6) with 1,792 PDAC cases. The 18-month incidence rate of PDAC was 0.77 (95% confidence interval 0.73-0.80)/1,000 person-years. The final main model contained age, abdominal pain, weight change, HbA1c, and alanine transaminase change (c-index: mean = 0.77, SD = 0.02; calibration test: P value 0.4, SD 0.3). The final early detection model comprised the same features as those selected by the main model except for abdominal pain (c-index: 0.77 and SD 0.4; calibration test: P value 0.3 and SD 0.3). The VA testing cohort consisted of 2.7 million patients (mean age 66.1) with an 18-month incidence rate of 1.27 (1.23-1.30)/1,000 person-years. The recalibrated main and early detection models based on VA testing data sets achieved a mean c-index of 0.71 (SD 0.002) and 0.68 (SD 0.003), respectively. DISCUSSION: Using widely available parameters in electronic health records, we developed and externally validated parsimonious machine learning-based models for detection of PC. These models may be suitable for real-time clinical application.

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.

Examining recent trends in spontaneous and iatrogenic preterm birth across race and ethnicity in a large managed care population.

BACKGROUND: For the past several decades, epidemiological studies originating from the United States have consistently reported increasing rates of preterm birth (PTB). Despite the implementation of several clinical and public health interventions to reduce PTB rates, it remains the leading cause of infant morbidity and mortality in the United States and around the world. OBJECTIVE: This study aimed to examine recent trends in preterm birth and its clinical subtypes by maternal race and ethnicity among singleton births. STUDY DESIGN: Kaiser Permanente Southern California electronic health records for all singleton births between 2009 and 2020 (n=427,698) were used to examine preterm birth trends and their subtypes (spontaneous and iatrogenic preterm births). Data on preterm labor triage extracted from electronic health records using natural language processing were used to define preterm birth subtypes. Maternal race and ethnicity are categorized as non-Hispanic White, non-Hispanic Black, Hispanic, and non-Hispanic Asian or Pacific Islander. Multiple logistic regression was used to quantify the linear trend for preterm birth and its subtypes. Racial and ethnic trends were further examined by considering statistical interactions and stratifications. RESULTS: From 2009 to 2020, the overall preterm birth rate decreased by 9.12% (from 8.04% to 7.31%; P<.001). The rates decreased by 19.29% among non-Hispanic Whites (from 7.23% to 5.83%; P<.001), 6.15% among Hispanics (from 7.82% to 7.34%; P=.036), and 12.60% among non-Hispanic Asian or Pacific Islanders (from 8.90% to 7.78%; P<.001), whereas a nonsignificantly increased preterm birth rate (8.45%) was observed among non-Hispanic Blacks (from 9.91% to 10.75%; P=.103). Between 2009 and 2020, overall spontaneous preterm birth rates decreased by 28.85% (from 5.75% to 4.09%; P<.001). However, overall iatrogenic preterm birth rates increased by 40.45% (from 2.29% to 3.22%; p<.001). Spontaneous preterm birth rates decreased by 34.73% among non-Hispanic Whites (from 5.44% to 3.55%; P<.001), 19.75% among non-Hispanic Blacks (from 6.82% to 5.47%; P<.001), 22.96% among Hispanics (from 5.55% to 4.28%; P<.001), and 28.19% among non-Hispanic Asian or Pacific Islanders (from 6.50% to 4.67%; P<.001). Iatrogenic preterm birth rates increased by 52.42% among non-Hispanic Whites (from 1.88% to 2.61%; P<.001), 107.89% among non-Hispanic Blacks (from 3.18% to 6.13%; P<.001), 46.88% among Hispanics (from 2.29% to 3.26%; P<.001), and 42.21% among non-Hispanic Asian or Pacific Islanders (from 2.45% to 3.44%; P<.001). CONCLUSION: The overall preterm birth rate decreased over time and was driven by a decrease in the spontaneous preterm birth rate. There is racial and ethnic variability in the rates of spontaneous preterm birth and iatrogenic preterm birth. The observed increase in iatrogenic preterm birth among all racial and ethnic groups, especially non-Hispanic Blacks, is disconcerting and needs further investigation.

Association between intrauterine device type and risk of perforation and device expulsion: results from the Association of Perforation and Expulsion of Intrauterine Device study.

BACKGROUND: Intrauterine devices, including levonorgestrel-releasing and copper devices, are highly effective long-acting reversible contraceptives. The potential risks associated with intrauterine devices are low and include uterine perforation and device expulsion. OBJECTIVE: This study aimed to evaluate the risk of perforation and expulsion associated with levonorgestrel-releasing devices vs copper devices in clinical practice in the United States. STUDY DESIGN: The Association of Perforation and Expulsion of Intrauterine Device study was a retrospective cohort study of women aged ≤50 years with an intrauterine device insertion during 2001 to 2018 and information on intrauterine device type and patient and medical characteristics. Of note, 4 research sites with access to electronic health records contributed data for the study: 3 Kaiser Permanente-integrated healthcare systems (Northern California, Southern California, and Washington) and 1 healthcare system using data from a healthcare information exchange in Indiana (Regenstrief Institute). Perforation was classified as any extension of the device into or through the myometrium. Expulsion was classified as complete (not visible in the uterus or abdomen or patient reported) or partial (any portion in the cervix or malpositioned). We estimated the crude incidence rates and crude cumulative incidence by intrauterine device type. The risks of perforation and expulsion associated with levonorgestrel-releasing intrauterine devices vs copper intrauterine devices were estimated using Cox proportional-hazards regression with propensity score overlap weighting to adjust for confounders. RESULTS: Among 322,898 women included in this analysis, the incidence rates of perforation per 1000 person-years were 1.64 (95% confidence interval, 1.53-1.76) for levonorgestrel-releasing intrauterine devices and 1.27 (95% confidence interval, 1.08-1.48) for copper intrauterine devices; 1-year and 5-year crude cumulative incidence was 0.22% (95% confidence interval, 0.20-0.24) and 0.63% (95% confidence interval, 0.57-0.68) for levonorgestrel-releasing intrauterine devices and 0.16% (95% confidence interval, 0.13-0.20) and 0.55% (95% confidence interval, 0.44-0.68) for copper intrauterine devices, respectively. The incidence rates of expulsion per 1000 person-years were 13.95 (95% confidence interval, 13.63-14.28) for levonorgestrel-releasing intrauterine devices and 14.08 (95% confidence interval, 13.44-14.75) for copper intrauterine devices; 1-year and 5-year crude cumulative incidence was 2.30% (95% confidence interval, 2.24-2.36) and 4.52% (95% confidence interval, 4.40-4.65) for levonorgestrel-releasing intrauterine devices and 2.30% (95% confidence interval, 2.18-2.44) and 4.82 (95% confidence interval, 4.56-5.10) for copper intrauterine devices, respectively. Comparing levonorgestrel-releasing intrauterine devices with copper intrauterine devices, the adjusted hazard ratios were 1.49 (95% confidence intervals, 1.25-1.78) for perforation and 0.69 (95% confidence intervals, 0.65-0.73) for expulsion. CONCLUSION: After adjusting for potential confounders, levonorgestrel-releasing intrauterine devices were associated with an increased risk of uterine perforation and a decreased risk of expulsion relative to copper intrauterine devices. Given that the absolute numbers of these events are low in both groups, these differences may not be clinically meaningful.

Association between menorrhagia and risk of intrauterine device-related uterine perforation and device expulsion: results from the Association of Uterine Perforation and Expulsion of Intrauterine Device study.

BACKGROUND: Intrauterine devices are effective instruments for contraception, and 1 levonorgestrel-releasing device is also indicated for the treatment of heavy menstrual bleeding (menorrhagia). OBJECTIVE: To compare the incidence of intrauterine device expulsion and uterine perforation in women with and without a diagnosis of menorrhagia within the first 12 months before device insertion STUDY DESIGN: This was a retrospective cohort study conducted in 3 integrated healthcare systems (Kaiser Permanente Northern California, Southern California, and Washington) and a healthcare information exchange (Regenstrief Institute) in the United States using electronic health records. Nonpostpartum women aged ≤50 years with intrauterine device (eg, levonorgestrel or copper) insertions from 2001 to 2018 and without a delivery in the previous 12 months were studied in this analysis. Recent menorrhagia diagnosis (ie, recorded ≤12 months before insertion) was ascertained from the International Classification of Diseases, Ninth and Tenth Revision, Clinical Modification codes. The study outcomes, viz, device expulsion and device-related uterine perforation (complete or partial), were ascertained from electronic medical records and validated in the data sources. The cumulative incidence and crude incidence rates with 95% confidence intervals were estimated. Cox proportional hazards models estimated the crude and adjusted hazard ratios using propensity score overlap weighting (13-16 variables) and 95% confidence intervals. RESULTS: Among 228,834 nonpostpartum women, the mean age was 33.1 years, 44.4% of them were White, and 31,600 (13.8%) had a recent menorrhagia diagnosis. Most women had a levonorgestrel-releasing device (96.4% of those with and 78.2% of those without a menorrhagia diagnosis). Women with a menorrhagia diagnosis were likely to be older, obese, and have dysmenorrhea or fibroids. Women with a menorrhagia diagnosis had a higher intrauterine device-expulsion rate (40.01 vs 10.92 per 1000 person-years) than those without, especially evident in the first few months after insertion. Women with a menorrhagia diagnosis had a higher cumulative incidence (95% confidence interval) of expulsion (7.00% [6.70-7.32] at 1 year and 12.03% [11.52-12.55] at 5 years) vs those without (1.77% [1.70-1.84] at 1 year and 3.69% [3.56-3.83] at 5 years). The risk of expulsion was increased for women with a menorrhagia diagnosis vs for those without (adjusted hazard ratio, 2.84 [95% confidence interval, 2.66-3.03]). The perforation rate was low overall (<1/1000 person-years) but higher in women with a diagnosis of menorrhagia vs in those without (0.98 vs 0.63 per 1000 person-years). The cumulative incidence (95% confidence interval) of uterine perforation was slightly higher for women with a menorrhagia diagnosis (0.09% [0.06-0.14] at 1 year and 0.39% [0.29-0.53] at 5 years) than those without it (0.07% [0.06-0.08] at 1 year and 0.28% [0.24-0.33] at 5 years). The risk of perforation was slightly increased in women with a menorrhagia diagnosis vs in those without (adjusted hazard ratio, 1.53; 95% confidence interval, 1.10-2.13). CONCLUSION: The risk of expulsion is significantly higher in women with a recent diagnosis of menorrhagia. Patient education and counseling regarding the potential expulsion risk is recommended at insertion. The absolute risk of perforation for women with a recent diagnosis of menorrhagia is very low. The increased expulsion and perforation rates observed are likely because of causal factors of menorrhagia.

Design of the Association of Uterine Perforation and Expulsion of Intrauterine Device study: a multisite retrospective cohort study.

BACKGROUND: Intrauterine devices are effective and safe, long-acting reversible contraceptives, but the risk of uterine perforation occurs with an estimated incidence of 1 to 2 per 1000 insertions. The European Active Surveillance Study for Intrauterine Devices, a European prospective observational study that enrolled 61,448 participants (2006-2012), found that women breastfeeding at the time of device insertion or with the device inserted at ≤36 weeks after delivery had a higher risk of uterine perforation. The Association of Uterine Perforation and Expulsion of Intrauterine Device (APEX-IUD) study was a Food and Drug Administration-mandated study designed to reflect current United States clinical practice. The aims of the APEX-IUD study were to evaluate the risk of intrauterine device-related uterine perforation and device expulsion among women who were breastfeeding or within 12 months after delivery at insertion. OBJECTIVE: We aimed to describe the APEX-IUD study design, methodology, and analytical plan and present population characteristics, size of risk factor groups, and duration of follow-up. STUDY DESIGN: APEX-IUD study was a retrospective cohort study conducted in 4 organizations with access to electronic health records: Kaiser Permanente Northern California, Kaiser Permanente Southern California, Kaiser Permanente Washington, and Regenstrief Institute in Indiana. Variables were identified through structured data (eg, diagnostic, procedural, medication codes) and unstructured data (eg, clinical notes) via natural language processing. Outcomes include uterine perforation and device expulsion; potential risk factors were breastfeeding at insertion, postpartum timing of insertion, device type, and menorrhagia diagnosis in the year before insertion. Covariates include demographic characteristics, clinical characteristics, and procedure-related variables, such as difficult insertion. The first potential date of inclusion for eligible women varies by research site (from January 1, 2001 to January 1, 2010). Follow-up begins at insertion and ends at first occurrence of an outcome of interest, a censoring event (device removal or reinsertion, pregnancy, hysterectomy, sterilization, device expiration, death, disenrollment, last clinical encounter), or end of the study period (June 30, 2018). Comparisons of levels of exposure variables were made using Cox regression models with confounding adjusted by propensity score weighting using overlap weights. RESULTS: The study population includes 326,658 women with at least 1 device insertion during the study period (Kaiser Permanente Northern California, 161,442; Kaiser Permanente Southern California, 123,214; Kaiser Permanente Washington, 20,526; Regenstrief Institute, 21,476). The median duration of continuous enrollment was 90 (site medians 74-177) months. The mean age was 32 years, and the population was racially and ethnically diverse across the 4 sites. The mean body mass index was 28.5 kg/m2, and of the women included in the study, 10.0% had menorrhagia ≤12 months before insertion, 5.3% had uterine fibroids, and 10% were recent smokers; furthermore, among these women, 79.4% had levonorgestrel-releasing devices, and 19.5% had copper devices. Across sites, 97,824 women had an intrauterine device insertion at ≤52 weeks after delivery, of which 94,817 women (97%) had breastfeeding status at insertion determined; in addition, 228,834 women had intrauterine device insertion at >52 weeks after delivery or no evidence of a delivery in their health record. CONCLUSION: Combining retrospective data from multiple sites allowed for a large and diverse study population. Collaboration with clinicians in the study design and validation of outcomes ensured that the APEX-IUD study results reflect current United States clinical practice. Results from this study will provide valuable information based on real-world evidence about risk factors for intrauterine devices perforation and expulsion for clinicians.

Antibiotic and antifungal treatment among persons with confirmed coccidioidomycosis - Southern California, 2011.

We investigated coccidioidomycosis testing and treatment patterns among persons in an integrated healthcare delivery system to identify gaps in diagnosis and treatment. Coccidioidomycosis diagnosis delays were common. Among persons who tested positive, 70% were prescribed antibiotics before positive coccidioidomycosis tests. Antibiotic treatment decreased and antifungal treatment increased after positive testing.

The use of natural language processing to identify vaccine-related anaphylaxis at five health care systems in the Vaccine Safety Datalink.

PURPOSE: The objective was to develop a natural language processing (NLP) algorithm to identify vaccine-related anaphylaxis from plain-text clinical notes, and to implement the algorithm at five health care systems in the Vaccine Safety Datalink. METHODS: The NLP algorithm was developed using an internal NLP tool and training dataset of 311 potential anaphylaxis cases from Kaiser Permanente Southern California (KPSC). We applied the algorithm to the notes of another 731 potential cases (423 from KPSC; 308 from other sites) with relevant codes (ICD-9-CM diagnosis codes for anaphylaxis, vaccine adverse reactions, and allergic reactions; Healthcare Common Procedure Coding System codes for epinephrine administration). NLP results were compared against a reference standard of chart reviewed and adjudicated cases. The algorithm was then separately applied to the notes of 6 427 359 KPSC vaccination visits (9 402 194 vaccine doses) without relevant codes. RESULTS: At KPSC, NLP identified 12 of 16 true vaccine-related cases and achieved a sensitivity of 75.0%, specificity of 98.5%, positive predictive value (PPV) of 66.7%, and negative predictive value of 99.0% when applied to notes of patients with relevant diagnosis codes. NLP did not identify the five true cases at other sites. When NLP was applied to the notes of KPSC patients without relevant codes, it captured eight additional true cases confirmed by chart review and adjudication. CONCLUSIONS: The current study demonstrated the potential to apply rule-based NLP algorithms to clinical notes to identify anaphylaxis cases. Increasing the size of training data, including clinical notes from all participating study sites in the training data, and preprocessing the clinical notes to handle special characters could improve the performance of the NLP algorithms. We recommend adding an NLP process followed by manual chart review in future vaccine safety studies to improve sensitivity and efficiency.

Testing for Coccidioidomycosis among Community-Acquired Pneumonia Patients, Southern California, USA1.

We conducted a cohort study to identify characteristics associated with testing for, and testing positive for, coccidioidomycosis among patients with community-acquired pneumonia in southern California, USA. Limited and delayed testing probably leads to underdiagnosis among non-Hispanic black, Filipino, or Hispanic patients and among high-risk groups, including persons in whom antimicrobial drug therapy has failed.

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.

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 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.

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.

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.

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.

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.

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.