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

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. We present KIDMATCH (KawasakI Disease vs Multisystem InflAmmaTory syndrome in CHildren), a deep learning algorithm for screening patients for MIS-C, KD, or other febrile illness. KIDMATCH incorporates 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. Using routinely collected clinical and laboratory data, KIDMATCH achieved a high area under the curve [0.95-0.98]. Additional external validation of this model on MIS-C patients from 16 hospitals across the United States achieved a positive detection rate of over 90%. Our algorithm 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.

Recurrence of SARS-CoV-2 PCR positivity in COVID-19 patients: a single center experience and potential implications (preprint)

IMPORTANCE How to appropriately care for patients who become PCR-negative for severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) is still not known. Patients who have recovered from coronavirus disease 2019 (COVID-19) could profoundly impact the health care system if a subset were to be PCR-positive again with reactivated SARS-CoV-2. OBJECTIVE To characterize a single center COVID-19 cohort with and without recurrence of PCR positivity, and develop an algorithm to identify patients at high risk of retest positivity after discharge to inform health care policy and case management decision-making. DESIGN, SETTING, AND PARTICIPANTS A cohort of 414 patients with confirmed SARS-CoV-2 infection, at The Second Affiliated Hospital of Southern University of Science and Technology in Shenzhen, China from January 11 to April 23, 2020. EXPOSURES Polymerase chain reaction (PCR) and IgM-IgG antibody confirmed SARS-CoV-2 infection. MAIN OUTCOMES AND MEASURES Univariable and multivariable statistical analysis of the clinical, laboratory, radiologic image, medical treatment, and clinical course of admission/quarantine/readmission data to develop an algorithm to predict patients at risk of recurrence of PCR positivity. RESULTS 16.7% (95CI: 13.0%-20.3%) patients retest PCR positive 1 to 3 times after discharge, despite being in strict quarantine. The driving factors in the recurrence prediction model included: age, BMI; lowest levels of the blood laboratory tests during hospitalization for cholinesterase, fibrinogen, albumin, prealbumin, calcium, eGFR, creatinine; highest levels of the blood laboratory tests during hospitalization for total bilirubin, lactate dehydrogenase, alkaline phosphatase; the first test results during hospitalization for partial pressure of oxygen, white blood cell and lymphocyte counts, blood procalcitonin; and the first test episodic Ct value and the lowest Ct value of the nasopharyngeal swab RT PCR results. Area under the ROC curve is 0.786. CONCLUSIONS AND RELEVANCE This case series provides clinical characteristics of COVID-19 patients with recurrent PCR positivity, despite strict quarantine, at a 16.7% rate. Use of a recurrence prediction algorithm may identify patients at high risk of PCR retest positivity of SARS-CoV-2 and help modify COVID-19 case management and health policy approaches.