IMPORTANCE Accumulating evidence suggests that children infected with severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) are more likely to manifest mild symptoms and are at a lower risk of developing severe respiratory disease compared with adults. It remains unknown how the immune response in children differs from that of adolescents and adults. OBJECTIVE To investigate the association of age with the quantity and quality of SARS-CoV-2 antibody responses. DESIGN, SETTING, AND PARTICIPANTS This cross-sectional study used 31 426 SARS-CoV-2 antibody test results from pediatric and adult patients. Data were collected from a New York City hospital from April 9 to August 31, 2020. The semiquantitative immunoglobin (Ig) G levels were compared between 85 pediatric and 3648 adult patients. Further analysis of SARS-CoV-2 antibody profiles was performed on sera from 126 patients aged 1 to 24 years. MAIN OUTCOMES AND MEASURES SARS-CoV-2 antibody positivity rates and IgG levels were evaluated in patients from a wide range of age groups (1-102 years). SARS-CoV-2 IgG level, total antibody (TAb) level, surrogate neutralizing antibody (SNAb) activity, and antibody binding avidity were compared between children (aged 1-10 years), adolescents (aged 11-18 years), and young adults (aged 19-24 years). RESULTS Among 31 426 antibody test results (19 797 [63.0%] female patients), with 1194 pediatric patients (mean [SD] age, 11.0 [5.3] years) and 30 232 adult patients (mean [SD] age, 49.2 [17.1] years), the seroprevalence in the pediatric (197 [16.5%; 95% CI, 14.4%-18.7%]) and adult (5630 [18.6%; 95% CI, 18.2%-19.1%]) patient populations was similar. The SARS-CoV-2 IgG level showed a negative correlation with age in the pediatric population (r = −0.45, P < .001) and a moderate but positive correlation with age in adults (r = 0.24, P < .001). Patients aged 19 to 30 years exhibited the lowest IgG levels (eg, aged 25-30 years vs 1-10 years: 99 [44-180] relative fluorescence units [RFU] vs 443

Background Accurate diagnostic strategies to rapidly identify SARS-CoV-2 positive individuals for management of patient care and protection of health care personnel are urgently needed. The predominant diagnostic test is viral RNA detection by RT-PCR from nasopharyngeal swabs specimens, however the results are not promptly obtainable in all patient care locations. Routine laboratory testing, in contrast, is readily available with a turn-around time (TAT) usually within 1-2 hours. Method We developed a machine learning model incorporating patient demographic features (age, sex, race) with 27 routine laboratory tests to predict an individual’s SARS-CoV-2 infection status. Laboratory test results obtained within two days before the release of SARS-CoV-2-RT-PCR result were used to train a gradient boosted decision tree (GBDT) model from 3,356 SARS-CoV-2 RT-PCR tested patients (1,402 positive and 1,954 negative) evaluated at a metropolitan hospital. Results The model achieved an area under the receiver operating characteristic curve (AUC) of 0.854 (95% CI: 0.829-0.878). Application of this model to an independent patient dataset from a separate hospital resulted in a comparable AUC (0.838), validating the generalization of its use. Moreover, our model predicted initial SARS-CoV-2 RT-PCR positivity in 66% individuals whose RT-PCR result changed from negative to positive within two days. Conclusion This model employing routine laboratory test results offers opportunities for early and rapid identification of high-risk SARS-CoV-2 infected patients before their RT-PCR results are available. It may play an important role in assisting the identification of SARS-COV-2 infected patients in areas where RT-PCR testing is not accessible due to financial or supply constraints.