Post-COVID Conditions in US Primary Care: A PRIME Registry Comparison of Patients With COVID-19, Influenza-Like Illness, and Wellness Visits.

PURPOSE: COVID-19 is a condition that can lead to other chronic conditions. These conditions are frequently diagnosed in the primary care setting. We used a novel primary care registry to quantify the burden of post-COVID conditions among adult patients with a COVID-19 diagnosis across the United States. METHODS: We used the American Family Cohort, a national primary care registry, to identify study patients. After propensity score matching, we assessed the prevalence of 17 condition categories individually and cumulatively, comparing patients having COVID-19 in 2020-2021 with (1) historical control patients having influenza-like illness in 2018 and (2) contemporaneous control patients seen for wellness or preventive visits in 2020-2021. RESULTS: We identified 28,215 patients with a COVID-19 diagnosis and 235,953 historical control patients with influenza-like illness. The COVID-19 group had higher prevalences of breathing difficulties (4.2% vs 1.9%), type 2 diabetes (12.0% vs 10.2%), fatigue (3.9% vs 2.2%), and sleep disturbances (3.5% vs 2.4%). There were no differences, however, in the postdiagnosis monthly trend in cumulative morbidity between the COVID-19 patients (trend = 0.026; 95% CI, 0.025-0.027) and the patients with influenza-like illness (trend = 0.026; 95% CI, 0.023-0.027). Relative to contemporaneous wellness control patients, COVID-19 patients had higher prevalences of breathing difficulties and type 2 diabetes. CONCLUSIONS: Our findings show a moderate burden of post-COVID conditions in primary care, including breathing difficulties, fatigue, and sleep disturbances. Based on clinical registry data, the prevalence of post-COVID conditions in primary care practices is lower than that reported in subspecialty and hospital settings.

A Real-Time Early Warning System for Monitoring Inpatient Mortality Risk: Prospective Study Using Electronic Medical Record Data.

BACKGROUND: The rapid deterioration observed in the condition of some hospitalized patients can be attributed to either disease progression or imperfect triage and level of care assignment after their admission. An early warning system (EWS) to identify patients at high risk of subsequent intrahospital death can be an effective tool for ensuring patient safety and quality of care and reducing avoidable harm and costs. OBJECTIVE: The aim of this study was to prospectively validate a real-time EWS designed to predict patients at high risk of inpatient mortality during their hospital episodes. METHODS: Data were collected from the system-wide electronic medical record (EMR) of two acute Berkshire Health System hospitals, comprising 54,246 inpatient admissions from January 1, 2015, to September 30, 2017, of which 2.30% (1248/54,246) resulted in intrahospital deaths. Multiple machine learning methods (linear and nonlinear) were explored and compared. The tree-based random forest method was selected to develop the predictive application for the intrahospital mortality assessment. After constructing the model, we prospectively validated the algorithms as a real-time inpatient EWS for mortality. RESULTS: The EWS algorithm scored patients' daily and long-term risk of inpatient mortality probability after admission and stratified them into distinct risk groups. In the prospective validation, the EWS prospectively attained a c-statistic of 0.884, where 99 encounters were captured in the highest risk group, 69% (68/99) of whom died during the episodes. It accurately predicted the possibility of death for the top 13.3% (34/255) of the patients at least 40.8 hours before death. Important clinical utilization features, together with coded diagnoses, vital signs, and laboratory test results were recognized as impactful predictors in the final EWS. CONCLUSIONS: In this study, we prospectively demonstrated the capability of the newly-designed EWS to monitor and alert clinicians about patients at high risk of in-hospital death in real time, thereby providing opportunities for timely interventions. This real-time EWS is able to assist clinical decision making and enable more actionable and effective individualized care for patients' better health outcomes in target medical facilities.

Prediction of the 1-Year Risk of Incident Lung Cancer: Prospective Study Using Electronic Health Records from the State of Maine.

BACKGROUND: Lung cancer is the leading cause of cancer death worldwide. Early detection of individuals at risk of lung cancer is critical to reduce the mortality rate. OBJECTIVE: The aim of this study was to develop and validate a prospective risk prediction model to identify patients at risk of new incident lung cancer within the next 1 year in the general population. METHODS: Data from individual patient electronic health records (EHRs) were extracted from the Maine Health Information Exchange network. The study population consisted of patients with at least one EHR between April 1, 2016, and March 31, 2018, who had no history of lung cancer. A retrospective cohort (N=873,598) and a prospective cohort (N=836,659) were formed for model construction and validation. An Extreme Gradient Boosting (XGBoost) algorithm was adopted to build the model. It assigned a score to each individual to quantify the probability of a new incident lung cancer diagnosis from October 1, 2016, to September 31, 2017. The model was trained with the clinical profile in the retrospective cohort from the preceding 6 months and validated with the prospective cohort to predict the risk of incident lung cancer from April 1, 2017, to March 31, 2018. RESULTS: The model had an area under the curve (AUC) of 0.881 (95% CI 0.873-0.889) in the prospective cohort. Two thresholds of 0.0045 and 0.01 were applied to the predictive scores to stratify the population into low-, medium-, and high-risk categories. The incidence of lung cancer in the high-risk category (579/53,922, 1.07%) was 7.7 times higher than that in the overall cohort (1167/836,659, 0.14%). Age, a history of pulmonary diseases and other chronic diseases, medications for mental disorders, and social disparities were found to be associated with new incident lung cancer. CONCLUSIONS: We retrospectively developed and prospectively validated an accurate risk prediction model of new incident lung cancer occurring in the next 1 year. Through statistical learning from the statewide EHR data in the preceding 6 months, our model was able to identify statewide high-risk patients, which will benefit the population health through establishment of preventive interventions or more intensive surveillance.

Fluid overload independent of acute kidney injury predicts poor outcomes in neonates following congenital heart surgery.

BACKGROUND: Fluid overload (FO) is common after neonatal congenital heart surgery and may contribute to mortality and morbidity. It is unclear if the effects of FO are independent of acute kidney injury (AKI). METHODS: This was a retrospective cohort study which examined neonates (age < 30 days) who underwent cardiopulmonary bypass in a university-affiliated children's hospital between 20 October 2010 and 31 December 2012. Demographic information, risk adjustment for congenital heart surgery score, surgery type, cardiopulmonary bypass time, cross-clamp time, and vasoactive inotrope score were recorded. FO [(fluid in-out)/pre-operative weight] and AKI defined by Kidney Disease Improving Global Outcomes serum creatinine criteria were calculated. Outcomes were all-cause, in-hospital mortality and median postoperative hospital and intensive care unit lengths of stay. RESULTS: Overall, 167 neonates underwent cardiac surgery using cardiopulmonary bypass in the study period, of whom 117 met the inclusion criteria. Of the 117 neonates included in the study, 76 (65%) patients developed significant FO (>10%), and 25 (21%) developed AKI ≥ Stage 2. When analyzed as FO cohorts (< 10%,10-20%, > 20% FO), patients with greater FO were more likely to have AKI (9.8 vs. 18.2 vs. 52.4%, respectively, with AKI ≥ stage 2; p = 0.013) and a higher vasoactive-inotrope score, and be premature. In the multivariable regression analyses of patients without AKI, FO was independently associated with hospital and intensive care unit lengths of stay [0.322 extra days (p = 0.029) and 0.468 extra days (p < 0.001), respectively, per 1% FO increase). In all patients, FO was also associated with mortality [odds ratio 1.058 (5.8% greater odds of mortality per 1% FO increase); 95% confidence interval 1.008,1.125;p = 0.032]. CONCLUSIONS: Fluid overload is an important independent contributor to outcomes in neonates following congenital heart surgery. Careful fluid management after cardiac surgery in neonates with and without AKI is warranted.

Prediction of Incident Hypertension Within the Next Year: Prospective Study Using Statewide Electronic Health Records and Machine Learning.

BACKGROUND: As a high-prevalence health condition, hypertension is clinically costly, difficult to manage, and often leads to severe and life-threatening diseases such as cardiovascular disease (CVD) and stroke. OBJECTIVE: The aim of this study was to develop and validate prospectively a risk prediction model of incident essential hypertension within the following year. METHODS: Data from individual patient electronic health records (EHRs) were extracted from the Maine Health Information Exchange network. Retrospective (N=823,627, calendar year 2013) and prospective (N=680,810, calendar year 2014) cohorts were formed. A machine learning algorithm, XGBoost, was adopted in the process of feature selection and model building. It generated an ensemble of classification trees and assigned a final predictive risk score to each individual. RESULTS: The 1-year incident hypertension risk model attained areas under the curve (AUCs) of 0.917 and 0.870 in the retrospective and prospective cohorts, respectively. Risk scores were calculated and stratified into five risk categories, with 4526 out of 381,544 patients (1.19%) in the lowest risk category (score 0-0.05) and 21,050 out of 41,329 patients (50.93%) in the highest risk category (score 0.4-1) receiving a diagnosis of incident hypertension in the following 1 year. Type 2 diabetes, lipid disorders, CVDs, mental illness, clinical utilization indicators, and socioeconomic determinants were recognized as driving or associated features of incident essential hypertension. The very high risk population mainly comprised elderly (age>50 years) individuals with multiple chronic conditions, especially those receiving medications for mental disorders. Disparities were also found in social determinants, including some community-level factors associated with higher risk and others that were protective against hypertension. CONCLUSIONS: With statewide EHR datasets, our study prospectively validated an accurate 1-year risk prediction model for incident essential hypertension. Our real-time predictive analytic model has been deployed in the state of Maine, providing implications in interventions for hypertension and related diseases and hopefully enhancing hypertension care.

Assessing Statewide All-Cause Future One-Year Mortality: Prospective Study With Implications for Quality of Life, Resource Utilization, and Medical Futility.

BACKGROUND: For many elderly patients, a disproportionate amount of health care resources and expenditures is spent during the last year of life, despite the discomfort and reduced quality of life associated with many aggressive medical approaches. However, few prognostic tools have focused on predicting all-cause 1-year mortality among elderly patients at a statewide level, an issue that has implications for improving quality of life while distributing scarce resources fairly. OBJECTIVE: Using data from a statewide elderly population (aged ≥65 years), we sought to prospectively validate an algorithm to identify patients at risk for dying in the next year for the purpose of minimizing decision uncertainty, improving quality of life, and reducing futile treatment. METHODS: Analysis was performed using electronic medical records from the Health Information Exchange in the state of Maine, which covered records of nearly 95% of the statewide population. The model was developed from 125,896 patients aged at least 65 years who were discharged from any care facility in the Health Information Exchange network from September 5, 2013, to September 4, 2015. Validation was conducted using 153,199 patients with same inclusion and exclusion criteria from September 5, 2014, to September 4, 2016. Patients were stratified into risk groups. The association between all-cause 1-year mortality and risk factors was screened by chi-squared test and manually reviewed by 2 clinicians. We calculated risk scores for individual patients using a gradient tree-based boost algorithm, which measured the probability of mortality within the next year based on the preceding 1-year clinical profile. RESULTS: The development sample included 125,896 patients (72,572 women, 57.64%; mean 74.2 [SD 7.7] years). The final validation cohort included 153,199 patients (88,177 women, 57.56%; mean 74.3 [SD 7.8] years). The c-statistic for discrimination was 0.96 (95% CI 0.93-0.98) in the development group and 0.91 (95% CI 0.90-0.94) in the validation cohort. The mortality was 0.99% in the low-risk group, 16.75% in the intermediate-risk group, and 72.12% in the high-risk group. A total of 99 independent risk factors (n=99) for mortality were identified (reported as odds ratios; 95% CI). Age was on the top of list (1.41; 1.06-1.48); congestive heart failure (20.90; 15.41-28.08) and different tumor sites were also recognized as driving risk factors, such as cancer of the ovaries (14.42; 2.24-53.04), colon (14.07; 10.08-19.08), and stomach (13.64; 3.26-86.57). Disparities were also found in patients' social determinants like respiratory hazard index (1.24; 0.92-1.40) and unemployment rate (1.18; 0.98-1.24). Among high-risk patients who expired in our dataset, cerebrovascular accident, amputation, and type 1 diabetes were the top 3 diseases in terms of average cost in the last year of life. CONCLUSIONS: Our study prospectively validated an accurate 1-year risk prediction model and stratification for the elderly population (≥65 years) at risk of mortality with statewide electronic medical record datasets. It should be a valuable adjunct for helping patients to make better quality-of-life choices and alerting care givers to target high-risk elderly for appropriate care and discussions, thus cutting back on futile treatment.

A Classification Tool for Differentiation of Kawasaki Disease from Other Febrile Illnesses.

OBJECTIVE: To develop and validate a novel decision tree-based clinical algorithm to differentiate Kawasaki disease (KD) from other pediatric febrile illnesses that share common clinical characteristics. STUDY DESIGN: Using clinical and laboratory data from 801 subjects with acute KD (533 for development, and 268 for validation) and 479 febrile control subjects (318 for development, and 161 for validation), we developed a stepwise KD diagnostic algorithm combining our previously developed linear discriminant analysis (LDA)-based model with a newly developed tree-based algorithm. RESULTS: The primary model (LDA) stratified the 1280 subjects into febrile controls (n = 276), indeterminate (n = 247), and KD (n = 757) subgroups. The subsequent model (decision trees) further classified the indeterminate group into febrile controls (n = 103) and KD (n = 58) subgroups, leaving only 29 of 801 KD (3.6%) and 57 of 479 febrile control (11.9%) subjects indeterminate. The 2-step algorithm had a sensitivity of 96.0% and a specificity of 78.5%, and correctly classified all subjects with KD who later developed coronary artery aneurysms. CONCLUSION: The addition of a decision tree step increased sensitivity and specificity in the classification of subject with KD and febrile controls over our previously described LDA model. A multicenter trial is needed to prospectively determine its utility as a point of care diagnostic test for KD.

Cerebrospinal fluid protein dynamic driver network: At the crossroads of brain tumorigenesis.

To get a better understanding of the ongoing in situ environmental changes preceding the brain tumorigenesis, we assessed cerebrospinal fluid (CSF) proteome profile changes in a glioma rat model in which brain tumor invariably developed after a single in utero exposure to the neurocarcinogen ethylnitrosourea (ENU). Computationally, the CSF proteome profile dynamics during the tumorigenesis can be modeled as non-smooth or even abrupt state changes. Such brain tumor environment transition analysis, correlating the CSF composition changes with the development of early cellular hyperplasia, can reveal the pathogenesis process at network level during a time before the image detection of the tumors. In our controlled rat model study, matched ENU- and saline-exposed rats' CSF proteomics changes were quantified at approximately 30, 60, 90, 120, 150 days of age (P30, P60, P90, P120, P150). We applied our transition-based network entropy (TNE) method to compute the CSF proteome changes in the ENU rat model and test the hypothesis of the critical transition state prior to impending hyperplasia. Our analysis identified a dynamic driver network (DDN) of CSF proteins related with the emerging tumorigenesis progressing from the non-hyperplasia state. The DDN associated leading network CSF proteins can allow the early detection of such dynamics before the catastrophic shift to the clear clinical landmarks in gliomas. Future characterization of the critical transition state (P60) during the brain tumor progression may reveal the underlying pathophysiology to device novel therapeutics preventing tumor formation. More detailed method and information are accessible through our website at http://translationalmedicine.stanford.edu.

Exploring the Role of Polycythemia in Patients With Cyanosis After Palliative Congenital Heart Surgery.

OBJECTIVES: To understand the relationship between polycythemia and clinical outcome in patients with hypoplastic left heart syndrome following the Norwood operation. DESIGN: A retrospective, single-center cohort study. SETTING: Pediatric cardiovascular ICU, university-affiliated children's hospital. PATIENTS: Infants with hypoplastic left heart syndrome admitted to our medical center from September 2009 to December 2012 undergoing stage 1/Norwood operation. INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: Baseline demographic and clinical information including first recorded postoperative hematocrit and subsequent mean, median, and nadir hematocrits during the first 72 hours postoperatively were recorded. The primary outcomes were in-hospital mortality and length of hospitalization. Thirty-two patients were included in the analysis. Patients did not differ by operative factors (cardiopulmonary bypass time and cross-clamp time) or traditional markers of severity of illness (vasoactive inotrope score, lactate, saturation, and PaO2/FIO2 ratio). Early polycythemia (hematocrit value > 49%) was associated with longer cardiovascular ICU stay (51.0 [± 38.6] vs 21.4 [± 16.2] d; p < 0.01) and total hospital length of stay (65.0 [± 46.5] vs 36.1 [± 20.0] d; p = 0.03). In a multivariable analysis, polycythemia remained independently associated with the length of hospitalization after controlling for the amount of RBC transfusion (weight, 4.36 [95% CI, 1.35-7.37]; p < 0.01). No difference in in-hospital mortality rates was detected between the two groups (17.6% vs 20%). CONCLUSIONS: Early polycythemia following the Norwood operation is associated with longer length of hospitalization even after controlling for blood cell transfusion practices. We hypothesize that polycythemia may be caused by hemoconcentration and used as an early marker of capillary leak syndrome.

Prospective stratification of patients at risk for emergency department revisit: resource utilization and population management strategy implications.

BACKGROUND: Estimating patient risk of future emergency department (ED) revisits can guide the allocation of resources, e.g. local primary care and/or specialty, to better manage ED high utilization patient populations and thereby improve patient life qualities. METHODS: We set to develop and validate a method to estimate patient ED revisit risk in the subsequent 6 months from an ED discharge date. An ensemble decision-tree-based model with Electronic Medical Record (EMR) encounter data from HealthInfoNet (HIN), Maine's Health Information Exchange (HIE), was developed and validated, assessing patient risk for a subsequent 6 month return ED visit based on the ED encounter-associated demographic and EMR clinical history data. A retrospective cohort of 293,461 ED encounters that occurred between January 1, 2012 and December 31, 2012, was assembled with the associated patients' 1-year clinical histories before the ED discharge date, for model training and calibration purposes. To validate, a prospective cohort of 193,886 ED encounters that occurred between January 1, 2013 and June 30, 2013 was constructed. RESULTS: Statistical learning that was utilized to construct the prediction model identified 152 variables that included the following data domains: demographics groups (12), different encounter history (104), care facilities (12), primary and secondary diagnoses (10), primary and secondary procedures (2), chronic disease condition (1), laboratory test results (2), and outpatient prescription medications (9). The c-statistics for the retrospective and prospective cohorts were 0.742 and 0.730 respectively. Total medical expense and ED utilization by risk score 6 months after the discharge were analyzed. Cluster analysis identified discrete subpopulations of high-risk patients with distinctive resource utilization patterns, suggesting the need for diversified care management strategies. CONCLUSIONS: Integration of our method into the HIN secure statewide data system in real time prospectively validated its performance. It promises to provide increased opportunity for high ED utilization identification, and optimized resource and population management.

Online Prediction of Health Care Utilization in the Next Six Months Based on Electronic Health Record Information: A Cohort and Validation Study.

BACKGROUND: The increasing rate of health care expenditures in the United States has placed a significant burden on the nation's economy. Predicting future health care utilization of patients can provide useful information to better understand and manage overall health care deliveries and clinical resource allocation. OBJECTIVE: This study developed an electronic medical record (EMR)-based online risk model predictive of resource utilization for patients in Maine in the next 6 months across all payers, all diseases, and all demographic groups. METHODS: In the HealthInfoNet, Maine's health information exchange (HIE), a retrospective cohort of 1,273,114 patients was constructed with the preceding 12-month EMR. Each patient's next 6-month (between January 1, 2013 and June 30, 2013) health care resource utilization was retrospectively scored ranging from 0 to 100 and a decision tree-based predictive model was developed. Our model was later integrated in the Maine HIE population exploration system to allow a prospective validation analysis of 1,358,153 patients by forecasting their next 6-month risk of resource utilization between July 1, 2013 and December 31, 2013. RESULTS: Prospectively predicted risks, on either an individual level or a population (per 1000 patients) level, were consistent with the next 6-month resource utilization distributions and the clinical patterns at the population level. Results demonstrated the strong correlation between its care resource utilization and our risk scores, supporting the effectiveness of our model. With the online population risk monitoring enterprise dashboards, the effectiveness of the predictive algorithm has been validated by clinicians and caregivers in the State of Maine. CONCLUSIONS: The model and associated online applications were designed for tracking the evolving nature of total population risk, in a longitudinal manner, for health care resource utilization. It will enable more effective care management strategies driving improved patient outcomes.

COVID-19 Vaccine Strategy Left Small Primary Care Practices On The Sidelines.

We report on the experience of small primary care practices participating in a national clinical registry with COVID-19 vaccines and vaccination data. At the end of 2021, 11.2 percent of these practices' 3.9 million patients had records of COVID-19 vaccination; 43.1 percent of clinics had no record of patients' COVID-19 vaccinations, but 93.4 percent of clinics had provided or recorded other routine vaccinations.

Machine Learning for Pediatric Echocardiographic Mitral Regurgitation Detection.

BACKGROUND: Echocardiography-based screening for valvular disease in at-risk asymptomatic children can result in early diagnosis. These screening programs, however, are resource intensive and may not be feasible in many resource-limited settings. Automated echocardiographic diagnosis may enable more widespread echocardiographic screening, early diagnosis, and improved outcomes. In this feasibility study, the authors sought to build a machine learning model capable of identifying mitral regurgitation (MR) on echocardiography. METHODS: Echocardiograms were labeled by clip for view and by frame for the presence of MR. The labeled data were used to build two convolutional neural networks to perform the stepwise tasks of classifying the clips (1) by view and (2) by the presence of any MR, including physiologic, in parasternal long-axis color Doppler views. The view classification model was developed using 66,330 frames, and model performance was evaluated using a hold-out testing data set with 45 echocardiograms (11,730 frames). The MR detection model was developed using 938 frames, and model performance was evaluated using a hold-out testing data set with 42 echocardiograms (182 frames). Metrics to evaluate model performance included accuracy, precision, recall, F1 score (average of precision and recall, ranging from 0 to 1, with 1 suggesting perfect precision and recall), and receiver operating characteristic analysis. RESULTS: For the parasternal long-axis view with color Doppler, the view classification convolutional neural network achieved an F1 score of 0.97. The MR detection convolutional neural network achieved testing accuracy of 0.86 and an area under the receiver operating characteristic curve of 0.91. CONCLUSIONS: A machine learning model is capable of discerning MR on transthoracic echocardiography. This is an encouraging step toward machine learning-based diagnosis of valvular heart disease on pediatric echocardiography.

Gestational Dating by Urine Metabolic Profile at High Resolution Weekly Sampling Timepoints: Discovery and Validation.

Background: Pregnancy triggers longitudinal metabolic alterations in women to allow precisely-programmed fetal growth. Comprehensive characterization of such a "metabolic clock" of pregnancy may provide a molecular reference in relation to studies of adverse pregnancy outcomes. However, a high-resolution temporal profile of metabolites along a healthy pregnancy remains to be defined. Methods: Two independent, normal pregnancy cohorts with high-density weekly urine sampling (discovery: 478 samples from 19 subjects at California; validation: 171 samples from 10 subjects at Alabama) were studied. Urine samples were profiled by liquid chromatography-mass spectrometry (LC-MS) for untargeted metabolomics, which was applied for gestational age dating and prediction of time to delivery. Results: 5,473 urinary metabolic features were identified. Partial least-squares discriminant analysis on features with robust signals (n = 1,716) revealed that the samples were distributed on the basis of the first two principal components according to their gestational age. Pathways of bile secretion, steroid hormone biosynthesis, pantohenate, and CoA biosynthesis, benzoate degradation, and phenylpropanoid biosynthesis were significantly regulated, which was collectively applied to discover and validate a predictive model that accurately captures the chronology of pregnancy. With six urine metabolites (acetylcholine, estriol-3-glucuronide, dehydroepiandrosterone sulfate, α-lactose, hydroxyexanoy-carnitine, and l-carnitine), models were constructed based on gradient-boosting decision trees to date gestational age in high accordance with ultrasound results, and to accurately predict time to delivery. Conclusion: Our study characterizes the weekly baseline profile of the human pregnancy metabolome, which provides a high-resolution molecular reference for future studies of adverse pregnancy outcomes.

Single center blind testing of a US multi-center validated diagnostic algorithm for Kawasaki disease in Taiwan.

Background: Kawasaki disease (KD) is the leading cause of acquired heart disease in children. The major challenge in KD diagnosis is that it shares clinical signs with other childhood febrile control (FC) subjects. We sought to determine if our algorithmic approach applied to a Taiwan cohort. Methods: A single center (Chang Gung Memorial Hospital in Taiwan) cohort of patients suspected with acute KD were prospectively enrolled by local KD specialists for KD analysis. Our previously single-center developed computer-based two-step algorithm was further tested by a five-center validation in US. This first blinded multi-center trial validated our approach, with sufficient sensitivity and positive predictive value, to identify most patients with KD diagnosed at centers across the US. This study involved 418 KDs and 259 FCs from the Chang Gung Memorial Hospital in Taiwan. Findings: Our diagnostic algorithm retained sensitivity (379 of 418; 90.7%), specificity (223 of 259; 86.1%), PPV (379 of 409; 92.7%), and NPV (223 of 247; 90.3%) comparable to previous US 2016 single center and US 2020 fiver center results. Only 4.7% (15 of 418) of KD and 2.3% (6 of 259) of FC patients were identified as indeterminate. The algorithm identified 18 of 50 (36%) KD patients who presented 2 or 3 principal criteria. Of 418 KD patients, 157 were infants younger than one year and 89.2% (140 of 157) were classified correctly. Of the 44 patients with KD who had coronary artery abnormalities, our diagnostic algorithm correctly identified 43 (97.7%) including all patients with dilated coronary artery but one who found to resolve in 8 weeks. Interpretation: This work demonstrates the applicability of our algorithmic approach and diagnostic portability in Taiwan.

A machine-learning algorithm for diagnosis of multisystem inflammatory syndrome in children and Kawasaki disease in the USA: a retrospective model development and validation study.

BACKGROUND: Multisystem inflammatory syndrome in children (MIS-C) is a novel disease that was identified during the COVID-19 pandemic and is characterised by systemic inflammation following SARS-CoV-2 infection. Early detection of MIS-C is a challenge given its clinical similarities to Kawasaki disease and other acute febrile childhood illnesses. We aimed to develop and validate an artificial intelligence algorithm that can distinguish among MIS-C, Kawasaki disease, and other similar febrile illnesses and aid in the diagnosis of patients in the emergency department and acute care setting. METHODS: In this retrospective model development and validation study, we developed a deep-learning algorithm called KIDMATCH (Kawasaki Disease vs Multisystem Inflammatory Syndrome in Children) using patient age, the five classic clinical Kawasaki disease signs, and 17 laboratory measurements. All features were prospectively collected at the time of initial evaluation from patients diagnosed with Kawasaki disease or other febrile illness between Jan 1, 2009, and Dec 31, 2019, at Rady Children's Hospital in San Diego (CA, USA). For patients with MIS-C, the same data were collected from patients between May 7, 2020, and July 20, 2021, at Rady Children's Hospital, Connecticut Children's Medical Center in Hartford (CT, USA), and Children's Hospital Los Angeles (CA, USA). We trained a two-stage model consisting of feedforward neural networks to distinguish between patients with MIS-C and those without and then those with Kawasaki disease and other febrile illnesses. After internally validating the algorithm using stratified tenfold cross-validation, we incorporated a conformal prediction framework to tag patients with erroneous data or distribution shifts. We finally externally validated KIDMATCH on patients with MIS-C enrolled between April 22, 2020, and July 21, 2021, from Boston Children's Hospital (MA, USA), Children's National Hospital (Washington, DC, USA), and the CHARMS Study Group consortium of 14 US hospitals. FINDINGS: 1517 patients diagnosed at Rady Children's Hospital between Jan 1, 2009, and June 7, 2021, with MIS-C (n=69), Kawasaki disease (n=775), or other febrile illnesses (n=673) were identified for internal validation, with an additional 16 patients with MIS-C included from Connecticut Children's Medical Center and 50 from Children's Hospital Los Angeles between May 7, 2020, and July 20, 2021. KIDMATCH achieved a median area under the receiver operating characteristic curve during internal validation of 98·8% (IQR 98·0-99·3) in the first stage and 96·0% (95·6-97·2) in the second stage. We externally validated KIDMATCH on 175 patients with MIS-C from Boston Children's Hospital (n=50), Children's National Hospital (n=42), and the CHARMS Study Group consortium of 14 US hospitals (n=83). External validation of KIDMATCH on patients with MIS-C correctly classified 76 of 81 patients (94% accuracy, two rejected by conformal prediction) from 14 hospitals in the CHARMS Study Group consortium, 47 of 49 patients (96% accuracy, one rejected by conformal prediction) from Boston Children's Hospital, and 36 of 40 patients (90% accuracy, two rejected by conformal prediction) from Children's National Hospital. INTERPRETATION: KIDMATCH has the potential to aid front-line clinicians to distinguish between MIS-C, Kawasaki disease, and other similar febrile illnesses to allow prompt treatment and prevent severe complications. FUNDING: US Eunice Kennedy Shriver National Institute of Child Health and Human Development, US National Heart, Lung, and Blood Institute, US Patient-Centered Outcomes Research Institute, US National Library of Medicine, the McCance Foundation, and the Gordon and Marilyn Macklin Foundation.

Multicenter Validation of a Machine Learning Algorithm for Diagnosing Pediatric Patients with Multisystem Inflammatory Syndrome and Kawasaki Disease.

BACKGROUND: Multisystem inflammatory syndrome in children (MIS-C) is a novel disease identified during the COVID-19 pandemic characterized by systemic inflammation following SARS-CoV-2 infection. Delays in diagnosing MIS-C may lead to more severe disease with cardiac dysfunction or death. Most pediatric patients recover fully with anti-inflammatory treatments, but early detection of MIS-C remains a challenge given its clinical similarities to Kawasaki disease (KD) and other acute childhood illnesses. METHODS: We developed KIDMATCH ( K awasak I D isease vs M ultisystem Infl A mma T ory syndrome in CH ildren), a deep learning algorithm for screening patients for MIS-C, KD, or other febrile illness, using age, the five classical clinical KD signs, and 17 laboratory measurements prospectively collected within 24 hours of admission to the emergency department from 1448 patients diagnosed with KD or other febrile illness between January 1, 2009 and December 31, 2019 at Rady Children's Hospital. For MIS-C patients, the same data was collected from 131 patients between May 14, 2020 to June 18, 2021 at Rady Children's Hospital, Connecticut Children's Hospital, and Children's Hospital Los Angeles. We trained a two-stage model consisting of feedforward neural networks to distinguish between MIS-C and non MIS-C patients and then KD and other febrile illness. After internally validating the algorithm using 10-fold cross validation, we incorporated a conformal prediction framework to tag patients with erroneous data or distribution shifts, enhancing the model generalizability and confidence by flagging unfamiliar cases as indeterminate instead of making spurious predictions. We externally validated KIDMATCH on 175 MIS-C patients from 16 hospitals across the United States. FINDINGS: KIDMATCH achieved a high median area under the curve in the 10-fold cross validation of 0.988 [IQR: 0.98-0.993] in the first stage and 0.96 [IQR: 0.956-0.972] in the second stage using thresholds set at 95% sensitivity to detect positive MIS-C and KD cases respectively during training. External validation of KIDMATCH on MIS-C patients correctly classified 76/83 (2 rejected) patients from the CHARMS consortium, 47/50 (1 rejected) patients from Boston Children's Hospital, and 36/42 (2 rejected) patients from Children's National Hospital. INTERPRETATION: KIDMATCH has the potential to aid frontline clinicians with distinguishing between MIS-C, KD, and similar febrile illnesses in a timely manner to allow prompt treatment and prevent severe complications. FUNDING: Eunice Kennedy Shriver National Institute of Child Health and Human Development, National Heart, Lung, and Blood Institute, Patient-Centered Outcomes Research Institute, National Library of Medicine.

The Correlation Between SPP1 and Immune Escape of EGFR Mutant Lung Adenocarcinoma Was Explored by Bioinformatics Analysis.

BACKGROUND: Immune checkpoint inhibitors have achieved breakthrough efficacy in treating lung adenocarcinoma (LUAD) with wild-type epidermal growth factor receptor (EGFR), leading to the revision of the treatment guidelines. However, most patients with EGFR mutation are resistant to immunotherapy. It is particularly important to study the differences in tumor microenvironment (TME) between patients with and without EGFR mutation. However, relevant research has not been reported. Our previous study showed that secreted phosphoprotein 1 (SPP1) promotes macrophage M2 polarization and PD-L1 expression in LUAD, which may influence response to immunotherapy. Here, we assessed the role of SPP1 in different populations and its effects on the TME. METHODS: We compared the expression of SPP1 in LUAD tumor and normal tissues, and in samples with wild-type and mutant EGFR. We also evaluated the influence of SPP1 on survival. The LUAD data sets were downloaded from TCGA and CPTAC databases. Clinicopathologic characteristics associated with overall survival in TCGA were assessed using Cox regression analysis. GSEA revealed that several fundamental signaling pathways were enriched in the high SPP1 expression group. We applied CIBERSORT and xCell to calculate the proportion and abundance of tumor-infiltrating immune cells (TICs) in LUAD, and compared the differences in patients with high or low SPP1 expression and wild-type or mutant EGFR. In addition, we explored the correlation between SPP1 and CD276 for different groups. RESULTS: SPP1 expression was higher in LUAD tumor tissues and in people with EGFR mutation. High SPP1 expression was associated with poor prognosis. Univariate and multivariate cox analysis revealed that up-regulated SPP1 expression was independent indicator of poor prognosis. GSEA showed that the SPP1 high expression group was mainly enriched in immunosuppressed pathways. In the SPP1 high expression group, the infiltration of CD8+ T cells was lower and M2-type macrophages was higher. These results were also observed in patients with EGFR mutation. Furthermore, we found that the SPP1 expression was positively correlated with CD276, especially in patients with EGFR mutation. CONCLUSION: SPP1 levels might be a useful marker of immunosuppression in patients with EGFR mutation, and could offer insight for therapeutics.

Identification of patients at risk of new onset heart failure: Utilizing a large statewide health information exchange to train and validate a risk prediction model.

BACKGROUND: New-onset heart failure (HF) is associated with poor prognosis and high healthcare utilization. Early identification of patients at increased risk incident-HF may allow for focused allocation of preventative care resources. Health information exchange (HIE) data span the entire spectrum of clinical care, but there are no HIE-based clinical decision support tools for diagnosis of incident-HF. We applied machine-learning methods to model the one-year risk of incident-HF from the Maine statewide-HIE. METHODS AND RESULTS: We included subjects aged ≥ 40 years without prior HF ICD9/10 codes during a three-year period from 2015 to 2018, and incident-HF defined as assignment of two outpatient or one inpatient code in a year. A tree-boosting algorithm was used to model the probability of incident-HF in year two from data collected in year one, and then validated in year three. 5,668 of 521,347 patients (1.09%) developed incident-HF in the validation cohort. In the validation cohort, the model c-statistic was 0.824 and at a clinically predetermined risk threshold, 10% of patients identified by the model developed incident-HF and 29% of all incident-HF cases in the state of Maine were identified. CONCLUSIONS: Utilizing machine learning modeling techniques on passively collected clinical HIE data, we developed and validated an incident-HF prediction tool that performs on par with other models that require proactively collected clinical data. Our algorithm could be integrated into other HIEs to leverage the EMR resources to provide individuals, systems, and payors with a risk stratification tool to allow for targeted resource allocation to reduce incident-HF disease burden on individuals and health care systems.