Search

Background More than 350 genetic disorders cause immune deficiencies; given the rarity of these conditions, in-depth study of infections associated with primary immune deficiencies (PID) requires extremely large sample sizes from broad populations. Using a large electronic health record (EHR) dataset, we linked clinical and microbiologic data to develop digital phenotypes for PID. Methods Using the Cerner HealthFacts EHR dataset from 2009 to 2017 we extracted clinical and microbiologic data for hospitalizations from patients <18 years old with ICD9/10 PID diagnoses and ≥1 positive culture for infection. Machine learning models were used to identify key features to predict PID diagnosis. Features included patient and hospitalization characteristics; infectious agent and infection site; and selected comorbidities. Model validation was done using the area under the receiver operating characteristic (AUC) curve. Results Overall 1316 patients with a PID were identified (Table 1). The 10 most common pathogens identified by PID are listed in Table 2. The models classified DiGeorge syndrome (positive predictive value 49%), functional disorders of polymorphonuclear neutrophils (PMN) (PPV 43%), and common variable immunodeficiency (CVID) (PPV 47%) better than combined immunodeficiency (CID) (PPV 20%); the overall true positive rate was 47% with an AUC of 0.73. Predictive features for each PID were as follows: CVID—having enteritis, hypertension, and pneumonia (Figure 1a); PMN—having hypoxia and hypertension (Figure 1b); DiGeorge syndrome—having congenital deformities and not having hypertension (Figure 1c); CID—finding Staphylococcus aureus in a wound or Escherichia coli in the blood were predictive of CID (Figure 1d). Conclusion Early models demonstrate some discrimination, specifically for more common PIDs (CVID) and those with highly identifying factors (DiGeorge syndrome). These models can be improved by including a wider array of clinical data, and they provide a first look at a new methodology to digitally phenotype PIDs for future diagnostic use. Disclosures All authors: No reported disclosures. [ABSTRACT FROM AUTHOR]

Background We noted a recent increase in the number of patients with CMV viremia among immunocompromised children at our institution. The study was undertaken to determine the prevalence of CMV viremia and to evaluate factors associated with the development of antiviral drug resistance. Methods A retrospective study of immunocompromised hosts 0–21 years of age who had CMV viremia (2007–2017). We collected demographic data as well as details of antiviral therapy and resistance testing. Results A total of 31 patients were identified including 10 (32%) during the last 2 years. The age range was 3 months to 20 years (median 12.6 years); 23 (74%) were male and 12 (39%) were African American. Among the 31 patients, 18 had hematopoietic stem cell transplantation, 5 had primary immunodeficiency (2 common variable immunodeficiency, 1 SCID, 1 Langerhans cell histiocytosis, 1 DiGeorge syndrome), 4 had malignancies receiving chemotherapy, 3 with heart transplantation and one 17 year old with newly diagnosed HIV infection who presented with CMV pneumonia and viremia. Antiviral resistance testing was performed on 7 CMV isolates: 5 due to persistent viremia (> 1 months) despite treatment, and 2 prior to starting antiviral therapy. CMV resistance was identified in 3 patients including 2 with CVID and one with Hodgkin's disease status post bone marrow transplantation. The 2 CVID patients had other comorbidities including chronic diarrhea and malabsorption and were TPN dependent. Both were diagnosed with CMV colitis and one also had pneumonitis. One had received a prolonged oral valganciclovir course (> 1 year) prior to diagnosis of resistance and the other received long-term intermittent oral valganciclovir courses. The patient with Hodgkin's disease received a prolonged IV ganciclovir course. All 3 tested positive for UL97 mutation and one had both UL97/UL54 gene mutations. Conclusion Most of our patients with CMV viremia were transplant patients. Antiviral drug resistance was detected among 3 of 31 (10%) of our patients during the study period. Two had malabsorption that may have resulted in sub-therapeutic blood levels. Treatment with oral valganciclovir should be avoided in patients with poor gut absorption because it may increase risk of drug resistance. Disclosures All authors: No reported disclosures. [ABSTRACT FROM AUTHOR]