Halalau, Alexandra

Objective We aimed to use machine learning (ML) models to investigate the impact of clinical, social and behavioural factors on 1-year progression from pre-diabetes to type 2 diabetes mellitus (DM). Design A retrospective cohort study. Setting A large health system including eight sites in southeast Michigan. Participants Adults with haemoglobin A1c (HbA1c) between 5.7% and 6.4% for two consecutive years between 1 January 2008 and 31 December 2023, and no prior history of type 2 DM or metformin use. Primary outcome measure New-onset type 2 DM (HbA1c ≥6.5%) in 1 year. Results Among 11 809 individuals, 815 (6.9%) progressed to type 2 DM within 1 year. CatBoost demonstrated the best performance (average area under the curve 0.78). Prior-year HbA1c was the most influential covariate (SHapley Additive exPlanations 1.02). Traditional metabolic factors (high-density lipoprotein, body mass index (BMI), white blood cell, age, gender, triglycerides) also contributed. Lastly, while inclusion of social and behavioural determinants of health (SBDH) did not significantly improve the overall model performance, depression emerged as the prominent SBDH covariate. Depression was a stronger predictor of diabetes progression in individuals with higher baseline BMI and lower baseline HbA1c. Conclusions Inclusion of social and behavioural covariates provided no incremental value for prediction of diabetes progression from pre-diabetes. However, machine learning revealed that depression may play a role in progression to type 2 DM.

Background. Clostridium difficile infection (CDI) is the leading cause of hospital-associated gastrointestinal illness. Previous studies reported that patients with active malignancy are at high risk for CDIs, and yet they are still classified as nonsevere CDI and initially treated with metronidazole. Our aim is to investigate the need for the escalation of antibiotic therapy in patients with CDI and active cancer treated with oral metronidazole versus oral vancomycin. Methods. This is a retrospective study of adult patients admitted with CDI and any underlying active malignancy at Beaumont Hospital, Royal Oak, Michigan, from January 2008 to December 2014. Inclusion criteria included age > 18 years old, polymerase chain reaction- (PCR-) proven CDI, and active malignancy. Results. 197 patients were included in the final analysis. 44.8% of the metronidazole group required escalation of therapy compared to 15.2% in the vancomycin group (p value = 0.001). 29.8% of the combination group (metronidazole and vancomycin) underwent deescalation of antibiotics, which was significantly higher compared to 2.2% of patients in the vancomycin group (p value < 0.001). Discussion. Our results support the initial use of vancomycin or a combination (metronidazole and vancomycin) versus metronidazole in patients with CDI and active malignancy.

Acute myeloid leukemia (AML) is a complex disease with a variety of presentations. A large pericardial effusion is rare, occurring in less than 0.5% of all patients with AML prior to treatment. A 34-year-old male presented with dyspnea, malaise, and weight loss. On physical exam, he was noted to be hypoxic, tachypneic, tachycardic, and hypotensive. He had cervical lymphadenopathy and jugular venous distention. His WBC count was 110 bil/L with 33% blasts. Bone marrow biopsy confirmed AML with 60% blasts. Leukemic cells were also seen in the cerebrospinal fluid on lumbar puncture. An echocardiogram revealed a large pericardial effusion causing tamponade. He underwent emergent pericardiocentesis, and malignant cells were present in the pericardial fluid. Induction therapy with standard dose cytarabine and daunorubicin was initiated, and bone marrow biopsy 14 days later showed no residual AML. This case demonstrates the importance of a thorough evaluation of each organ system when caring for a patient with AML.