論文

Objective To evaluate whether a machine learning (ML) based screening algorithm can optimize respiratory syncytial virus (RSV) testing while maintaining high diagnostic accuracy in pediatric patients. Study Design We conducted a retrospective analysis of pediatric patients under 2 years old who presented with respiratory infection symptoms and received RSV testing at Yokohama Municipal Citizen's Hospital (2009-2015). The cohort was divided into training (2009-2013; n=3,587) and validation (2014-2015; n=587) sets. Using patient-reported symptoms and background characteristics from structured electronic questionnaires, we collected clinical symptoms and patient characteristics to build an ML model for predicting RSV testing necessity according to established clinical guidelines, focusing on hospitalized patients and those with underlying conditions. Results The median age was 11.2 and 11.7 months in the training and validation sets, respectively, with hospitalization rates of 45.4% and 43.1%. The ML model showed good performance, achieving a sensitivity of 77.1% and specificity of 73.4% in the training dataset, with improved sensitivity (85.1%) and comparable specificity (71.2%) in validation. Implementation could potentially reduce unnecessary testing by 77.9% (98.5 tests annually) for cases requiring hospitalization and 72.9% (17.5 tests) for patients with underlying conditions, with negative predictive values of 97.0% and 100%, respectively. Conclusion This study demonstrates that ML-based screening using symptom data could substantially reduce unnecessary invasive RSV testing while maintaining high diagnostic accuracy. The approach offers promising clinical utility by potentially minimizing patient discomfort and optimizing resource allocation in pediatric respiratory care.

Background: Respiratory syncytial virus (RSV) causes an estimated 3.2 million infant hospitalizations worldwide annually, with 99% of RSV-associated deaths occurring in developing countries. Although laboratory confirmation remains the standard for diagnosis, resource limitations and the need for prompt infection control measures highlight the importance of reliable symptom-based assessment tools. Methods: In this retrospective cohort study (2009–2015), we analyzed symptom characteristics and progression patterns in infants 12 months of age or younger who underwent RSV rapid antigen testing at a tertiary care center, regardless of subsequent hospitalization status. Through structured electronic questionnaires and chronologically divided development and validation cohorts, a predictive model incorporating symptom features and their sequence patterns was developed using multivariable logistic regression analysis. The model was then transformed into a weighted risk score system, for clinical application. Results: Among 1650 eligible infants, RSV was detected in 328 patients (19.9%). The model incorporated productive cough, biphasic wheezing and cough-wheezing progression sequences as key predictors. The model demonstrated moderate discriminative ability in the development cohort [area under the receiver operating characteristic curve (AUROC), 0.746; 95% confidence interval (CI): 0.715–0.777] and maintained its performance in the validation cohort (AUROC, 0.712; 95% CI: 0.626–0.798). Risk stratification effectively identified RSV-positive cases, with RSV probability rates of 5.6%, 7.2%, 22.6% and 41.2% across baseline, moderate, elevated and high-risk groups, respectively. Conclusions: This symptom-based index provides reliable risk stratification for RSV infection through systematic assessment of respiratory symptoms, offering a potential screening method for various clinical settings.

Background: Respiratory syncytial virus (RSV) affects children, causing serious infections, particularly in high-risk groups. Given the seasonality of RSV and the importance of rapid isolation of infected individuals, there is an urgent need for more efficient diagnostic methods to expedite this process. Objective: This study aimed to investigate the performance of a machine learning model that leverages the temporal diversity of symptom onset for detecting RSV infections and elucidate its discriminatory ability. Methods: The study was conducted in pediatric and emergency outpatient settings in Japan. We developed a detection model that remotely confirms RSV infection based on patient-reported symptom information obtained using a structured electronic template incorporating the differential points of skilled pediatricians. An extreme gradient boosting–based machine learning model was developed using the data of 4174 patients aged ≤24 months who underwent RSV rapid antigen testing. These patients visited either the pediatric or emergency department of Yokohama City Municipal Hospital between January 1, 2009, and December 31, 2015. The primary outcome was the diagnostic accuracy of the machine learning model for RSV infection, as determined by rapid antigen testing, measured using the area under the receiver operating characteristic curve. The clinical efficacy was evaluated by calculating the discriminative performance based on the number of days elapsed since the onset of the first symptom and exclusion rates based on thresholds of reasonable sensitivity and specificity. Results: Our model demonstrated an area under the receiver operating characteristic curve of 0.811 (95% CI 0.784-0.833) with good calibration and 0.746 (95% CI 0.694-0.794) for patients within 3 days of onset. It accurately captured the temporal evolution of symptoms; based on adjusted thresholds equivalent to those of a rapid antigen test, our model predicted that 6.9% (95% CI 5.4%-8.5%) of patients in the entire cohort would be positive and 68.7% (95% CI 65.4%-71.9%) would be negative. Our model could eliminate the need for additional testing in approximately three-quarters of all patients. Conclusions: Our model may facilitate the immediate detection of RSV infection in outpatient settings and, potentially, in home environments. This approach could streamline the diagnostic process, reduce discomfort caused by invasive tests in children, and allow rapid implementation of appropriate treatments and isolation at home. The findings underscore the potential of machine learning in augmenting clinical decision-making in the early detection of RSV infection.

Abstract Background: Prior literature suggests that cold temperature strongly influences the immune function of animals and human behaviors, which may allow for the transmission of respiratory viral infections. However, information on the impact of cold stimuli, especially the impact of temporal change in the ambient temperature on influenza virus transmission, is limited. Methods: A susceptible-infected-recovered-susceptible model was applied to evaluate the effect of temperature change on influenza virus transmission. Results: The mean temperature of the prior week was positively associated with the number of newly diagnosed cases (0.107 [95% Bayesian credible interval {BCI}, .106-.109]), whereas the mean difference in the temperature of the prior week was negatively associated (-0.835 [95% BCI, -.840 to -.830]). The product of the mean temperature and mean difference in the temperature of the previous week were also negatively associated with the number of newly diagnosed cases (-0.192 [95% BCI, -.197 to -.187]). Conclusions: The mean temperature and the mean difference in temperature affected the number of newly diagnosed influenza cases differently. Our data suggest that high ambient temperature and a drop in the temperature and their interaction increase the risk of infection. Therefore, the highest risk of infection is attributable to a steep fall in temperature in a relatively warm environment. Keywords: SIRS model; cold stimuli; influenza.