Mark Henry DeLegge

Objectives To develop and evaluate machine learning models to detect suspected undiagnosed nonalcoholic steatohepatitis (NASH) patients for diagnostic screening and clinical management. Methods In this retrospective observational noninterventional study using administrative medical claims data from 1,463,089 patients, gradient-boosted decision trees were trained to detect likely NASH patients from an at-risk patient population with a history of obesity, type 2 diabetes mellitus (T2DM), metabolic disorder, or nonalcoholic fatty liver (NAFL). Models were trained to detect likely NASH in all at-risk patients or in the subset without a prior NAFL diagnosis (non-NAFL at-risk patients). Models were trained and validated using retrospective medical claims data and assessed using area under precision recall and receiver operating characteristic curves (AUPRCs, AUROCs). Results The 6-month incidence of NASH in claims data was 1 per 1,437 at-risk patients and 1 per 2,127 non-NAFL at-risk patients. The model trained to detect NASH in all at-risk patients had an AUPRC of 0.0107 (95% CI 0.0104 - 0.011) and an AUROC of 0.84. At 10% recall, model precision was 4.3%, which is 60x above NASH incidence. The model trained to detect NASH in non-NAFL patients had an AUPRC of 0.003 (95% CI 0.0029 - 0.0031) and an AUROC of 0.78. At 10% recall, model precision was 1%, which is 20x above NASH incidence. Conclusion The low incidence of NASH in medical claims data corroborates the pattern of NASH underdiagnosis in clinical practice. Claims-based machine learning could facilitate the detection of probable NASH patients for diagnostic testing and disease management.

Home Parenteral Nutrition (HPN) is often a life-saving therapy for patients. One of the most common complications for HPN is catheter-related blood stream infections (CRBSI). In the home setting there is no single defined “care bundle” for the on-going maintenance of central venous catheters (CVC) for the prevention of CRBSI. We evaluated the impact of a standardized catheter care bundle in patients receiving HPN on the incidence of CRBSI. Methods: Data collection included use of standardized tools and processes to capture patient demographics, catheter complications including CRBSI and some associated risk factors. Reported data was collected and analyzed annually and compared year-to-year from the years 2014-2017 from one national home infusion company. CRBSI reported as number of infections/1000 catheter days Results: The CRBSI rate/1000 days was reported as 0.43, 0.31, 0.30 and 0.23 (2014, 2015, 2016, 2017 respectively) statistically significant difference (p < .05) between the years 2014 and 2017. CRBSI. Conclusion: The use of a catheter care bundle in an HPN population may have contributed to a 4- year reported outcomes of low and continuously declining CRBSI in a large, diverse United States-based HPN population.

The incidence of malnutrition in hospitalized patients is relatively high (up to 55%) despite breakthroughs in nutrition support therapies. These patients have increased morbidity and mortality, extended hospital stays, and care that is associated with higher costs. These patients are often poorly managed due to inadequate nutrition assessment and poor medical knowledge and practice in the field of nutrition. Nutrition support teams (NSTs) are interdisciplinary support teams with specialty training in nutrition that are often comprised of physicians, dietitians, nurses, and pharmacists. Their role includes nutrition assessment, determination of nutrition needs, recommendations for appropriate nutrition therapy, and management of nutrition support therapy. Studies have demonstrated significant improvements in patient nutrition status and improved clinical outcomes as well as reductions in costs when patients were appropriately managed by a multispecialty NST vs individual caregivers. Despite this, there has been steady decline in the number of formal NST in recent years (65% of hospitals in 1995 to 42% in 2008) as hospitals and other healthcare organizations look for ways to cut costs. Given the importance of nutrition status on clinical outcomes and overall healthcare costs, a number of institutions have introduced and sustained strong nutrition training and support programs and teams, demonstrating both clinical and economic benefit. The benefits of NST, training and implementation strategies, and tips for justifying these clinically and economically beneficial groups to healthcare organizations and governing bodies are discussed in this review.

Nutrition intervention plays a significant role in changing patient clinical outcomes in the intensive care unit. Identifying patients at nutrition risk with a validated tool is essential. The decision to use enteral or parenteral nutrition is patient dependent and should include an assessment of the patient's gastrointestinal function. Protein is a critical component of the nutrition prescription, and prescribed levels may need to be higher than current guidelines recommend. Alternative lipids, such as olive oil and fish oil, are still being evaluated for their potential clinical impact. Avoiding nutrition therapy-associated complications, such as catheter infection and hyperglycemia, are important factors in being able to maximize the effectiveness of a nutritional intervention.

Parenteral nutrition (PN) is one of the most complex medical therapies prescribed by healthcare professionals because it is dependent on the compounding of multiple base solutions to arrive at the final formulation. The delivery of PN is associated with errors in ordering, transcribing, compounding, and delivery of the PN formulations. New compounding technologies will attempt to minimize the potential for these errors. In addition, the associated infectious complications associated with PN therapy need to be minimized. Commercially prepared, premixed, terminally sterilized PN solutions may have an impact. Broader decontamination technologies will be implemented to reduce the incidence of overall nosocomial infections. Modification of PN nutrients, particularly intravenous fat emulsions, will be provided by alternative biological sources, creating fats that may have an improved impact on the patient’s immune system and ultimately affecting clinical outcomes.