A Novel Machine-Learning Algorithm to Predict the Early Termination of Nutrition Support Team Follow-Up in Hospitalized Adults: A Retrospective Cohort Study.

BACKGROUND: For hospitalized adults, it is important to initiate the early reintroduction of oral food in accordance with nutrition support team guidelines. The aim of this study was to develop and validate a machine learning-based algorithm that predicts the early termination of medical nutritional therapy (the transition to oral feeding). METHODS: This retrospective cohort study included consecutive adult patients admitted to the Hacettepe hospital (from 1 January 2018 to 31 December 2022). The outcome of the study was the prediction of an early transition to adequate oral feeding before discharge. The dataset was randomly (70/30) divided into training and test datasets. We used six ML algorithms with multiple features to construct prediction models. ML model performance was measured according to the accuracy, area under the receiver operating characteristic curve, and F1 score. We used the Boruta Method to determine the important features and interpret the selected features. RESULTS: A total of 2298 adult inpatients who were followed by a nutrition support team for medical nutritional therapy were included. Patients received parenteral nutrition (1471/2298, 64.01%), enteral nutrition (717/2298, 31.2%), or supplemental parenteral nutrition (110/2298, 4.79%). The median (interquartile range) Nutritional Risk Screening (NRS-2002) score was 5 (1). Six prediction algorithms were used, and the artificial neural network and elastic net models achieved the greatest area under the ROC in all outcomes (AUC = 0.770). Ranked by z-value, the 10 most important features in predicting an early transition to oral feeding in the artificial neural network and elastic net algorithms were parenteral nutrition, surgical wards, surgical outcomes, enteral nutrition, age, supplemental parenteral nutrition, digestive system diseases, gastrointestinal complications, NRS-2002, and impaired consciousness. CONCLUSIONS: We developed machine learning models for the prediction of an early transition to oral feeding before discharge. Overall, there was no discernible superiority among the models. Nevertheless, the artificial neural network and elastic net methods provided the highest AUC values. Since the machine learning model is interpretable, it can enable clinicians to better comprehend the features underlying the outcomes. Our study could support personalized treatment and nutritional follow-up strategies in clinical decision making for the prediction of an early transition to oral feeding in hospitalized adult patients.

Risk assessments of drug-related problems for cardiac surgery patients.

OBJECTIVES: Patients undergoing cardiac surgery are considered at high risk for developing drug-related problems (DRPs) due to comorbidities and complexity of drug treatment. This study aimed to identify DRPs in patients undergoing cardiac surgery and to develop and implement a framework to reduce potential risks associated with drug treatment. STUDY DESIGN: Prospectively designed quasi-experimental study. METHODS: This study consisted of observational (risk assessment and framework development) and interventional (framework implementation) periods and was conducted at a department of cardiovascular surgery in a university hospital. An expert panel evaluated the causes of DRPs. Then a framework was developed in consensus to identify safeguards to be implemented during the interventional period. RESULTS: A total of 200 patients (100 patients per study period) were included. During the observational period, a total of 275 DRPs and 487 causes were identified; 74.5% of DRPs were not solved. For the risk analysis, 487 causes were evaluated and only 32.6% were considered acceptable risk. By implementing the framework in the interventional period, 215 DRPs and 304 causes were identified and 386 interventions were recommended by a clinical pharmacist. A total of 342 (88.6%) interventions were accepted by a health care team, and 128 (59.5%) DRPs were completely solved. For the risk analysis, 304 causes were evaluated and 84.9% were considered acceptable risk ( P < .001 compared with the observational period). CONCLUSIONS: It is possible to reduce risk levels or prevent occurrence of DRPs by implementing a framework for risk management developed by a multidisciplinary care team in areas such as cardiac surgery where time is limited.

Drug-related problems at the heart of cardiac surgery.

OBJECTIVES: Optimal perioperative success in cardiac surgery requires precise management of drug treatment. This study aimed to determine the prevalence, types and associated factors of drug-related problems (DRPs) during the entire hospital stay. METHODS: A prospective observational study was conducted at the department of cardiovascular surgery in a university hospital between November 2019 and March 2020. Patients with planned elective cardiac surgery, aged ≥18 years, were included. A clinical pharmacist collaboratively reviewed medications on a daily basis and identified DRPs. RESULTS: A total of 100 patients (60 male) were included; median (range) age was 62 (19-86) years, and median (IQR) length of stay in hospital was 15 (9) days. A total of 275 DRPs were identified (median (IQR) 3 (2-4)). The number of patients who had at least one DRP was 47 preoperatively, 55 in the postoperative intensive care unit, 100 in the postoperative ward, and 16 at discharge. In order to reduce bias because of the small sample size, Firth's logistic regression analysis was conducted. Statistically significant variables according to univariate analysis were included into a logistic regression model. Therefore the length of hospital stay (OR 1.14, 95% CI 1.03 to 1.26, p=0.008), living arrangements (living alone) (OR 4.24, 95% CI 1.41 to 12.73, p=0.009), number of medications at admission (OR 1.32, 95% CI 1.09 to 1.59, p=0.002), and having coronary artery bypass graft surgery (OR 2.87, 95% CI 1.07 to 7.70, p=0.03) were associated with an increased risk for DRPs in the final model. CONCLUSION: Hospital stay carries an increased risk for DRPs, especially at the postoperative stage. Modifiable risk factors for DRPs can be managed by required interventions performed by a multidisciplinary healthcare team.

Assessment of the Appropriateness of Prescriptions in a Geriatric Outpatient Clinic

Objectives: Appropriateness of the geriatric outpatients' medications needs special attention due to risks of falls, fractures, depression, hospital admissions and mortality. This study aimed to identify current practice on medication usage by using the 2nd version of "Screening Tool of Older People's Potentially Inappropriate Prescriptions" and "Screening Tool to Alert Doctors to Right Treatment" criteria and affecting factors for the Turkish population. Materials and Methods: This cross-sectional study was conducted between September 2015 and May 2016 at a university research and training hospital's geriatric outpatient clinic. Patients aged ≥65 years and had ≥5 different prescribed medications (considered as polypharmacy) were recruited. The main outcome measure was the frequency of inappropriate medications identified by clinical pharmacist in the outpatient clinic according to the 2nd version of the criterion sets. Results: A total of 700 patients (440 female) were included in this study. According to the results, 316 patients (45.1%) with at least one potentially inappropriate medication and 668 patients (98.3%) with at least one potential prescription omission were detected. Potentially inappropriate medications were associated with the number of medications used per patient [odds ratio (OR): 1.20 p<0.001], living alone (OR: 4.12 p=0.02), and having congestive heart failure (OR: 2.41 p<0.001). Twenty-two (27.5%) out of 80 criteria and 4 (11.8%) out of 34 criteria did not apply to the study population. Conclusion: Detecting inappropriate medications to maintain treatment effectiveness is necessary to provide the optimum therapy. Despite the awareness of polypharmacy in outpatient clinics it is still one of the important causes of inappropriate prescription followed by vaccination rate. Therefore, with the contribution of clinical pharmacist using these available criteria is important, moreover modification of these criteria according to the local needs to be considered to achieve better outcomes.

How we Provide Nutritional Treatment in Hospitalized Patients?

BACKGROUND: In this study, we aimed to evaluate enteral nutrition (EN), parenteral nutrition (PN) and supplemental parenteral nutrition (SPN) in terms of achieving nutritional goals. METHODS: Patients receiving either EN, PN, or SPN treatment followed up by the clinical nutrition team between January and December 2017 at the university research and training hospital were included in the study. Daily nutritional requirements were calculated according to the recommendations. Total energy intake during nutritional treatment (NT) and all metabolic, mechanical, technical complications of NT were recorded. RESULTS: A total of 603 inpatients were included in the study. The nutritional goal was achieved in the majority of the SPN group patients (87.5%) statistically significant relation was found between the achievement of the target (or not) and PN access route (peripheral or central) (P < .001). However, none of the complications found statistically related to achieving the target, including gastrointestinal complications of EN (P = .46), metabolic complications of EN (P = .07), mechanical complications of EN (P = .79), metabolic complications of PN (P = .89), gastrointestinal complications in SPN group (P = .45), and metabolic complications in SPN group (P = .68). CONCLUSION: Nutritional goals could be achieved with SPN without increasing complications in the majority of patients. Commencement of SPN should be considered for positive outcomes in patients who failed to achieve desired nutritional outcomes.

Evaluation of the effect of antibiotics used during parenteral nutrition treatment on Candidemia

SUMMARY OBJECTIVE: Parenteral nutrition is an important risk factor for candidemia. In this risk analysis study, the effect of previous antibiotic administration apart from the length of hospital stay, duration of Parenteral nutrition treatment, and Candida score parameters on developing candidemia was evaluated in the non-neutropenic patients receiving Parenteral nutrition treatment. METHODS: In this double center, retrospective, and cross-sectional study, the data of patients who received Parenteral nutrition treatment were collected. Patients with or without candidemia after the initiation of Parenteral nutrition treatment were compared in terms of demographic features, Candida score, length of hospital stay, duration of Parenteral nutrition treatment, and previous use of antibiotics. Then, predictor factors affecting the probability of candidemia during Candida growth time were determined by the Cox regression analysis. RESULTS: A total of 148 patients (59.5% males) were included and 16 (10.81%) of these had candidemia after initiation of parenteral nutrition treatment. The median (min-max) duration of parenteral nutrition treatment was 11 (4-72) days and the Candida growth time was 13 (7-29) days. Statistically significant differences were found between patients with or without candidemia groups in terms of length of hospital stay (p<0.001), duration of parenteral nutrition treatment (p<0.001), and Candida score (p<0.001). To determine the effect of these variables and antibiotics on candidemia, length of hospital stay [Hazard Ratio 1.030; p=0.021] and piperacillin-tazobactam (Hazard Ratio 5.626; p=0.030) were found significant and independent risk factors on the development of candidemia. CONCLUSION: There are some well-known risk factors including length of hospital stay, duration of Parenteral nutrition treatment, and Candida score; the potential impact of piperacillin-tazobactam administration should also be considered since they may be effective on the development of candidemia.

Impact of Clinical Pharmacist-led Interventions in Turkey

Detecting drug-related problems (DRPs) is important in pharmaceutical care in for better therapeutic outcomes. Clinical pharmacists-led comprehensive medication management plays a crucial role in the rational use of drugs by preventing, identifying, and resolving DRPs. In this review, we aimed to determine the effect of interventions on patient outcomes performed by clinical pharmacists in Turkey. A systematic literature search was performed on PubMed, Google Scholar, EMBASE, Cochrane Library, and Turkish databases (ULAKBIM, Dergipark). The main categories were "clinical pharmacist", "intervention", and "Turkey". Two reviewers reviewed each article independently. Two independent reviewers screened all records and extracted data; disagreements were resolved through a consensus. Randomized controlled studies, pre- to post-intervention comparison studies, and cross-sectional studies including pharmacist-led interventions were included in the review. This review included 15 articles evaluating clinical pharmacist interventions. Ten studies (66.7%) focused on DRPs and pharmacist interventions to these problems, while the remaining 5 (33.3%) studies focused on patient education and adherence issues. Studies were conducted in oncology (33.3%), geriatrics (20.0%), chest diseases (13.3%), psychiatry (6.7%), cardiology (6.7%), and infectious diseases (6.7%) clinics. When results of studies are reviewed, most of the interventions were made at the prescriber level followed by the drug level and patient level. Problems were solved in 54.2-93.2% of DRPs, and adherence, patient knowledge, or skills were improved in most of the studies. Most of the studies were carried out within the scope of a postgraduate or doctorate thesis and yet various positive outcomes such as the prevention of side effects, increased quality of life, and decreased duration of hospital stay were observed with high positive rates of interventions, which indicate that other healthcare workers are ready to collaborate with the clinical pharmacists in Turkey.

Evaluation of the effect of antibiotics used during parenteral nutrition treatment on Candidemia.

OBJECTIVE: Parenteral nutrition is an important risk factor for candidemia. In this risk analysis study, the effect of previous antibiotic administration apart from the length of hospital stay, duration of Parenteral nutrition treatment, and Candida score parameters on developing candidemia was evaluated in the non-neutropenic patients receiving Parenteral nutrition treatment. METHODS: In this double center, retrospective, and cross-sectional study, the data of patients who received Parenteral nutrition treatment were collected. Patients with or without candidemia after the initiation of Parenteral nutrition treatment were compared in terms of demographic features, Candida score, length of hospital stay, duration of Parenteral nutrition treatment, and previous use of antibiotics. Then, predictor factors affecting the probability of candidemia during Candida growth time were determined by the Cox regression analysis. RESULTS: A total of 148 patients (59.5% males) were included and 16 (10.81%) of these had candidemia after initiation of parenteral nutrition treatment. The median (min-max) duration of parenteral nutrition treatment was 11 (4-72) days and the Candida growth time was 13 (7-29) days. Statistically significant differences were found between patients with or without candidemia groups in terms of length of hospital stay (p<0.001), duration of parenteral nutrition treatment (p<0.001), and Candida score (p<0.001). To determine the effect of these variables and antibiotics on candidemia, length of hospital stay [Hazard Ratio 1.030; p=0.021] and piperacillin-tazobactam (Hazard Ratio 5.626; p=0.030) were found significant and independent risk factors on the development of candidemia. CONCLUSION: There are some well-known risk factors including length of hospital stay, duration of Parenteral nutrition treatment, and Candida score; the potential impact of piperacillin-tazobactam administration should also be considered since they may be effective on the development of candidemia.