The Machine Learned Stethoscope Provides Accurate Operator Independent Diagnosis of Chest Disease.

INTRODUCTION: Contemporary stethoscope has limitations in diagnosis of chest conditions, necessitating further imaging modalities. METHODS: We created 2 diagnostic computer aided non-invasive machine-learning models to recognize chest sounds. Model A was interpreter independent based on hidden markov model and mel frequency cepstral coefficient (MFCC). Model B was based on MFCC, hidden markov model, and chest sound wave image interpreter dependent analysis (phonopulmonography (PPG)). RESULTS: We studied 464 records of actual chest sounds belonging to 116 children diagnosed by clinicians and confirmed by other imaging diagnostic modalities. Model A had 96.7% overall correct classification rate (CCR), 100% sensitivity and 100% specificity in discrimination between normal and abnormal sounds. CCR was 100% for normal vesicular sounds, crepitations 89.1%, wheezes 97.6%, and bronchial breathing 100%. Model B's CCR was 100% for normal vesicular sounds, crepitations 97.3%, wheezes 97.6%, and bronchial breathing 100%. The overall CCR was 98.7%, sensitivity and specificity were 100%. CONCLUSION: Both models demonstrated very high precision in the diagnosis of chest conditions and in differentiating normal from abnormal chest sounds irrespective of operator expertise. Incorporation of computer-aided models in stethoscopes promises prompt, precise, accurate, cost-effective, non-invasive, operator independent, objective diagnosis of chest conditions and reduces number of unnecessary imaging studies.

Ursodeoxycholic acid use is associated with significant risk of morbidity and mortality in infants with cholestasis: A strobe compliant study.

The off-label use of medications is a "right" for pediatricians, owing to lack of enough safety and effectiveness drug trials in pediatric age group. Pediatricians have to rely on their personal judicial use of medications in children.We studied off-label use of ursodeoxycholic acid (UDCA) retrospectively during 2005 to 2015 among those who attended the Pediatic Hepatology Unit, Cairo University.We analyzed data of 779 neonates and infants with cholestasis. 15% dropped out. Males comprised 374 (56.5%). Cholestasis was due to surgical causes in 129 (19.5%), neonatal hepatitis in 445 (67.2%), and paucity of intrahepatic bile ducts in 88 (13.3%). Three hundred sixty (54.4%) received UDCA (15-30 mg/kg/d), and 302 (45.6%) did not. Both groups were matched as regards causes and severity of cholestasis. Those who received UDCA had worse outcome (P < .001), and more complications (P < .001). A total of 73.1% (221) achieved cure without UDCA compared to only 45.8% (165) of those on UDCA (P < .001).UDCA is not effective and not safe in Egyptian neonates and infants with cholestasis. UDCA use compromises chance of cure, and is associated with serious morbidity, progression of disease, and death. UDCA off-label use mortality was absolutely preventable. Off- label use of UDCA in neonates and children should be utterly prohibited. Information of use of off-label medications, effectiveness, and safety, should be recorded, analyzed, and made available within context of Off-label Use Registry Studies with informed consent of parents.

Combined liver-kidney transplantation for primary hyperoxaluria type I in children: Single Center Experience.

Primary hyperoxalurias are rare inborn errors of metabolism with deficiency of hepatic enzymes that lead to excessive urinary oxalate excretion and overproduction of oxalate which is deposited in various organs. Hyperoxaluria results in serious morbid-ity, end stage kidney disease (ESKD), and mortality if left untreated. Combined liver kidney transplantation (CLKT) is recognized as a management of ESKD for children with hyperoxaluria type 1 (PH1). This study aimed to report outcome of CLKT in a pediatric cohort of PH1 patients, through retrospective analysis of data of 8 children (2 girls and 6 boys) who presented by PH1 to Wadi El Nil Pediatric Living Related Liver Transplant Unit during 2001-2017. Mean age at transplant was 8.2 ± 4 years. Only three of the children underwent confirmatory genotyping. Three patients died prior to surgery on waiting list. The first attempt at CLKT was consecutive, and despite initial successful liver transplant, the girl died of biliary peritonitis prior to scheduled renal transplant. Of the four who underwent simultaneous CLKT, only two survived and are well, one with insignificant complications, and other suffered from abdominal Burkitt lymphoma managed by excision and resection anastomosis, four cycles of rituximab, cyclophosphamide, vincristine, and prednisone. The other two died, one due to uncontrollable bleeding within 36 hours of procedure, while the other died awaiting renal transplant after loss of renal graft to recurrent renal oxalosis 6 months post-transplant. PH1 with ESKD is a rare disease; simultaneous CLKT offers good quality of life for afflicted children. Graft shortage and renal graft loss to oxalosis challenge the outcome.