Machine learning in data abstraction: A computable phenotype for sepsis and septic shock diagnosis in the intensive care unit.

BACKGROUND: With the recent change in the definition (Sepsis-3 Definition) of sepsis and septic shock, an electronic search algorithm was required to identify the cases for data automation. This supervised machine learning method would help screen a large amount of electronic medical records (EMR) for efficient research purposes. AIM: To develop and validate a computable phenotype via supervised machine learning method for retrospectively identifying sepsis and septic shock in critical care patients. METHODS: A supervised machine learning method was developed based on culture orders, Sequential Organ Failure Assessment (SOFA) scores, serum lactate levels and vasopressor use in the intensive care units (ICUs). The computable phenotype was derived from a retrospective analysis of a random cohort of 100 patients admitted to the medical ICU. This was then validated in an independent cohort of 100 patients. We compared the results from computable phenotype to a gold standard by manual review of EMR by 2 blinded reviewers. Disagreement was resolved by a critical care clinician. A SOFA score ≥ 2 during the ICU stay with a culture 72 h before or after the time of admission was identified. Sepsis versions as V1 was defined as blood cultures with SOFA ≥ 2 and Sepsis V2 was defined as any culture with SOFA score ≥ 2. A serum lactate level ≥ 2 mmol/L from 24 h before admission till their stay in the ICU and vasopressor use with Sepsis-1 and-2 were identified as Septic Shock-V1 and-V2 respectively. RESULTS: In the derivation subset of 100 random patients, the final machine learning strategy achieved a sensitivity-specificity of 100% and 84% for Sepsis-1, 100% and 95% for Sepsis-2, 78% and 80% for Septic Shock-1, and 80% and 90% for Septic Shock-2. An overall percent of agreement between two blinded reviewers had a k = 0.86 and 0.90 for Sepsis 2 and Septic shock 2 respectively. In validation of the algorithm through a separate 100 random patient subset, the reported sensitivity and specificity for all 4 diagnoses were 100%-100% each. CONCLUSION: Supervised machine learning for identification of sepsis and septic shock is reliable and an efficient alternative to manual chart review.

Protective role of testosterone in ischemia-reperfusion-induced acute kidney injury.

Men are at greater risk for renal injury and dysfunction after acute ischemia-reperfusion (I/R) than are women. Studies in animals suggest that the reason for the sex difference in renal injury and dysfunction after I/R is the protective effect of estrogens in females. However, a reduction in testosterone in men is thought to play an important role in mediating cardiovascular and renal disease, in general. In the present study, we tested the hypothesis that I/R of the kidney reduces serum testosterone, and that contributes to renal dysfunction and injury. Male rats that were subjected to renal ischemia of 40 min followed by reperfusion had a 90% reduction in serum testosterone by 3 h after reperfusion that remained at 24 h. Acute infusion of testosterone 3 h after reperfusion attenuated the increase in plasma creatinine and urinary kidney injury molecule-1 (KIM-1) at 24 h, prevented the reduction in outer medullary blood flow, and attenuated the increase in intrarenal TNF-α and the decrease in intrarenal VEGF at 48 h. Castration of males caused greater increases in plasma creatinine and KIM-1 at 24 h than in intact males with renal I/R, and treatment with anastrozole, an aromatase inhibitor, plus testosterone almost normalized plasma creatinine and KIM-1 in rats with renal I/R. These data show that renal I/R is associated with sustained reductions in testosterone, that testosterone repletion protects the kidney, whereas castration promotes renal dysfunction and injury, and that the testosterone-mediated protection is not conferred by conversion to estradiol.

Testosterone supplementation in male obese Zucker rats reduces body weight and improves insulin sensitivity but increases blood pressure.

Androgen levels are lower in obese men as compared with normal weight individuals. However, there are no safety data regarding the chronic use of androgen supplements in middle-aged men. The present study was undertaken to determine the cardiovascular and metabolic effects of chronic (10 weeks) testosterone treatment in male obese Zucker rats, starting at 22 weeks of age, when testosterone levels were significantly decreased. Testosterone supplements increased plasma levels, 10-fold in both obese Zucker rats and lean Zucker rats. In obese Zucker rats, testosterone supplements reduced body weight, plasma insulin, and cholesterol levels and improved the oral glucose tolerance test. None of these parameters were affected in lean Zucker rats. Mean arterial pressure was significantly increased in obese Zucker rats but not lean Zucker rats. Testosterone supplements increased proteinuria and accelerated renal injury in lean Zucker rats only. Thus, treatment of obese men with chronic testosterone supplements should be done with careful monitoring of blood pressure.