The future of artificial intelligence in clinical nutrition.

PURPOSE OF REVIEW: Artificial intelligence has reached the clinical nutrition field. To perform personalized medicine, numerous tools can be used. In this review, we describe how the physician can utilize the growing healthcare databases to develop deep learning and machine learning algorithms, thus helping to improve screening, assessment, prediction of clinical events and outcomes related to clinical nutrition. RECENT FINDINGS: Artificial intelligence can be applied to all the fields of clinical nutrition. Improving screening tools, identifying malnourished cancer patients or obesity using large databases has been achieved. In intensive care, machine learning has been able to predict enteral feeding intolerance, diarrhea, or refeeding hypophosphatemia. The outcome of patients with cancer can also be improved. Microbiota and metabolomics profiles are better integrated with the clinical condition using machine learning. However, ethical considerations and limitations of the use of artificial intelligence should be considered. SUMMARY: Artificial intelligence is here to support the decision-making process of health professionals. Knowing not only its limitations but also its power will allow precision medicine in clinical nutrition as well as in the rest of the medical practice.

Nutrition during noninvasive respiratory support.

PURPOSE OF REVIEW: The use of noninvasive techniques [noninvasive ventilation (NIV) or high flow nasal cannula (HFNC) oxygen therapy] to support oxygenation and/or ventilation in patients with respiratory failure has become widespread, even more so since the coronavirus disease 2019 pandemic. The use of these modalities may impair the patient's ability to eat. "To breath or to eat" may become a dilemma. In this review, we identify the patients at risk of malnutrition that require medical nutritional therapy and understand the mechanisms of function of the devices to better give adapted nutritional indications for noninvasive ventilation or high flow nasal cannula. RECENT FINDINGS: The Global Leadership Initiative for Malnutrition has been validated in the Intensive Care setting and can be used in patients requiring NIV. Many patients are underfed when receiving noninvasive ventilation therapies. HFNC may impair the swallowing ability and increase dysphagia while NIV may improve the swallowing reflexes. New technology preventing reflux and ensuring enteral feeding efficacy may increase the medical nutrition therapy safety and provide near-target energy and protein provision. SUMMARY: The patient requiring noninvasive ventilation presents one of the most challenging nutritional challenges. The main steps to improve nutrition administration are to assess nutritional status, evaluate the presence of dysphagia, choose the most adequate tool of respiratory support, and adapt nutritional therapy (oral, enteral, or parenteral) accordingly.

Gastrointestinal failure, big data and intensive care.

PURPOSE OF REVIEW: Enteral feeding is the main route of administration of medical nutritional therapy in the critically ill. However, its failure is associated with increased complications. Machine learning and artificial intelligence have been used in intensive care to predict complications. The aim of this review is to explore the ability of machine learning to support decision making to ensure successful nutritional therapy. RECENT FINDINGS: Numerous conditions such as sepsis, acute kidney injury or indication for mechanical ventilation can be predicted using machine learning. Recently, machine learning has been applied to explore how gastrointestinal symptoms in addition to demographic parameters and severity scores, can accurately predict outcomes and successful administration of medical nutritional therapy. SUMMARY: With the rise of precision and personalized medicine for support of medical decisions, machine learning is gaining popularity in the field of intensive care, first not only to predict acute renal failure or indication for intubation but also to define the best parameters for recognizing gastrointestinal intolerance and to recognize patients intolerant to enteral feeding. Large data availability and improvement in data science will make machine learning an important tool to improve medical nutritional therapy.

Direct oral anticoagulants in patients with venous thromboembolism and hematological malignancies.

Data are needed on direct oral anticoagulants (DOACs) for the treatment of venous thromboembolism (VTE) in hematological malignancies (HM). Retrospective studies to date lacked a control group and did not focus on patients with VTE. Out aim was to assess the incidence of VTE recurrence and bleeding in HM patients treated with low molecular weight heparin (LMWH) or DOACs for acute VTE. This is a retrospective cohort study including patients with active HM and newly-diagnosed VTE, indexed on the first day of anticoagulation and followed for 12 months. The outcome was a composite of recurrent VTE, major bleeding or clinically relevant non-major bleeding. Cumulative incidence [95% confidence interval (CI)] was calculated for each anticoagulation group (LMWH, DOAC) and hazard ratios (HR) were calculated using cox-proportional hazards model, with death as a competing risk. 143 HM patients treated with LMWH (96) or DOACs (47) for acute VTE were included. The most common HM types were lymphoma in 83 (58%) and plasma cell dyscrasia in 32 (22.3%). The 12-month cumulative incidence of the composite outcome was 24.2% (95% CI 15.9-33.5%; n = 22) in the LMWH group and 18.5% (8.5-31.5%; n = 8) in the DOAC group (HR 1.51 [0.695-3.297]). Two recurrent VTE occurred (both in the DOAC group while off-treatment). Nine (9.4%) LMWH-treated patients had major bleeding compared to 1 (2.1%) DOAC-treated patient (HR 4.85 [0.64-36.56]). This study generates the hypothesis that DOACs may be a safe and effective alternative to LMWH for VTE in patients with HM types represented in the study.

Urea to creatinine ratio as a predictor of persistent critical illness.

INTRODUCTION: Persistent critical illness (PCI) is a syndrome in which the acute presenting problem has been stabilized, but the patient's clinical state does not allow ICU discharge. The burden associated with PCI is substantial. The most obvious marker of PCI is prolonged ICU length of stay (LOS), usually greater than 10 days. Urea to Creatinine ratio (UCr) has been suggested as an early marker of PCI development. METHODS: A single-center retrospective study. Data of patients admitted to a general mixed medical-surgical ICU during Jan 1st 2018 till Dec 31st 2022 was extracted, including demographic data, baseline characteristics, daily urea and creatinine results, renal replacement therapy (RRT) provided, and outcome measures - length of stay, and mortality (ICU, and 90 days). Patients were defined as PCI patients if their LOS was >10 days. We used Fisher exact test or Chi-square to compare PCI and non-PCI patients. The association between UCr with PCI development was assessed by repeated measures linear model. Multivariate Cox regression was used for 1 year mortality assessment. RESULTS: 2098 patients were included in the analysis. Patients who suffered from PCI were older, with higher admission prognostic scores. Their 90-day mortality was significantly higher than non-PCI patients (34.58% vs 12.18%, p < 0.0001). A significant difference in UCr was found only on the first admission day among all patients. This was not found when examining separately surgical, trauma, or transplantation patients. We did not find a difference in UCr in different KDIGO (Kidney Disease Improving Global Outcomes) stages. Elevated UCr and PCI were found to be significantly associated with 1 year mortality. CONCLUSION: In this single center retrospective cohort study, UCr was not found to be associated with PCI development.

Using Machine-Learning to Assess the Prognostic Value of Early Enteral Feeding Intolerance in Critically Ill Patients: A Retrospective Study.

BACKGROUND: The association between gastrointestinal intolerance during early enteral nutrition (EN) and adverse clinical outcomes in critically ill patients is controversial. We aimed to assess the prognostic value of enteral feeding intolerance (EFI) markers during early ICU stays and to predict early EN failure using a machine learning (ML) approach. METHODS: We performed a retrospective analysis of data from adult patients admitted to Beilinson Hospital ICU between January 2011 and December 2018 for more than 48 h and received EN. Clinical data, including demographics, severity scores, EFI markers, and medications, along with 72 h after admission, were analyzed by ML algorithms. Prediction performance was assessed by the area under the receiver operating characteristics (AUCROC) of a ten-fold cross-validation set. RESULTS: The datasets comprised 1584 patients. The means of the cross-validation AUCROCs for 90-day mortality and early EN failure were 0.73 (95% CI 0.71-0.75) and 0.71 (95% CI 0.67-0.74), respectively. Gastric residual volume above 250 mL on the second day was an important component of both prediction models. CONCLUSIONS: ML underlined the EFI markers that predict poor 90-day outcomes and early EN failure and supports early recognition of at-risk patients. Results have to be confirmed in further prospective and external validation studies.

Comparison of Mindray metabolic system and the GE S/5 metabolic system: Indirect calorimetry in critically ill, mechanically ventilated patients.

OBJECTIVE: Indirect calorimetry is the recommended, most accurate way to measure resting energy expenditure (REE) in critically ill, mechanically ventilated patients. We tested the agreement of two systems: the Mindray metabolic system (the system to be validated) and the GE S/5 metabolic system (the reference system). We also compared the measurements obtained to commonly used predictive equations. METHODS: This was a prospective single-center study, in a general 16-bed intensive care unit, with critically ill, mechanically ventilated patients eligible to undergo indirect calorimetry. REE was measured successively during the same session with two 30-min measurements. The agreement and bias between oxygen consumption, carbon dioxide production, REE, and respiratory quotient obtained by Mindray and GE systems were compared using Bland-Altman plots. A priori we defined an acceptable within-method error to be 20% or less and an acceptable between-methods error to be 30% or less, according to Critchley and Critchley. RESULTS: Forty measurements were performed with 16 participants. All measurements were included in the final analysis. The mean REE was 2478 ± 650 kcal/d for the GE system and 2166 ± 415 kcal/d for the Mindray system (P ˂ 0.0001), for a difference of 12.6%. This difference in REE is related to the variations between the two devices in both oxygen consumption and carbon dioxide production. CONCLUSIONS: The Mindray metabolic system, compared to the GE S/5 metabolic system (the reference method used), measured REE with a mean difference of 12.6%. The Mindray-measured REE was within an error limit we defined a priori.

Usefulness of cardiac biomarkers for prognosis of better outcomes in chronic heart failure: Retrospective 18-year follow-up study.

ABSTRACT: Brain natriuretic peptide is an established, surrogate follow-up marker, strongly correlated with heart failure severity. Several other biomarkers and tests are useful for assessing the prognosis of patients with HF, such as oxidized low-density lipoprotein antibodies and C-reactive protein. Some inflammatory cells, including monocytes, lymphocytes, and neutrophils, are involved in coronary heart disease and may be useful for prognosis also. This study assessed the potential usefulness of various laboratory biomarkers in predicting long-term outcomes and hospitalization among a cohort of outpatients with chronic, advanced HF.This retrospective, 18-year follow-up study included all patients admitted to the Heart Failure Outpatient Unit in our tertiary care medical center from 2000 through 2001 due to chronic HF. Excluded were patients with malignant disease, severe stroke, active inflammatory disease, or infection. At the first visit, blood was sampled for routine analysis and biomarkers NT-proBNP, C-reactive protein, myeloperoxidase, heat shock protein, and antibodies to oxidized low density lipoprotein. left ventricular ejection fraction and New York Heart Association class class were also established. Patients were followed every 3 months. Study endpoints were mortality or first hospitalization.Among 305 study patients, HF duration ranged from 2 months to 18 years. Mean follow-up was 9.1 ±â€Š6 years. Mean time to first hospitalization was 60 ±â€Š58.1 months, median = 38 (range 0-179). Mortality rate was 41%. Regression analysis showed New York Heart Association class, lymphocyte count and alkaline phosphatase were independent predictors of survival, with hazard ratios of 1.0, 0.973, and 1.006, respectively (P < .05).N-terminal pro-B-type natriuretic peptide, alkaline phosphatase, and lymphocyte count are important prognostic predictors for very long-term follow-up among patients with chronic HF.

Downregulation of CD45 Signaling in COVID-19 Patients Is Reversed by C24D, a Novel CD45 Targeting Peptide.

CD45, the predominant transmembrane tyrosine phosphatase in leukocytes, is required for the efficient induction of T cell receptor signaling and activation. We recently reported that the CD45-intracellular signals in peripheral blood mononuclear cells (PBMCs) of triple negative breast cancer (TNBC) patients are inhibited. We also reported that C24D, an immune modulating therapeutic peptide, binds to CD45 on immune-suppressed cells and resets the functionality of the immune system via the CD45 signaling pathway. Various studies have demonstrated that also viruses can interfere with the functions of CD45 and that patients with severe acute respiratory syndrome coronavirus-2 (SARS-CoV-2) are immune-suppressed. Given the similarity between the role of CD45 in viral immune suppression and our findings on TNBC, we hypothesized that the C24D peptide may have a similar "immune-resetting" effect on PBMCs from COVID-19 patients as it did on PBMCs from TNBC patients. We tested this hypothesis by comparing the CD45/TCR intracellular signaling in PBMCs from ten COVID-19 patients vs. PBMCs from ten healthy volunteers. Herein, we report our findings, demonstrating the immune reactivating effect of C24D via the phosphorylation of the tyrosine 505 and 394 in Lck, the tyrosine 493 in ZAP-70 and the tyrosine 172 in VAV-1 proteins in the CD45 signaling pathway. Despite the relatively small number of patients in this report, the results demonstrate that C24D rescued CD45 signaling. Given the central role played by CD45 in the immune system, we suggest CD45 as a potential therapeutic target.