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.

Presentation, management, and outcomes of older compared to younger adults with hospital-acquired bloodstream infections in the intensive care unit: a multicenter cohort study.

PURPOSE: Older adults admitted to the intensive care unit (ICU) usually have fair baseline functional capacity, yet their age and frailty may compromise their management. We compared the characteristics and management of older (≥ 75 years) versus younger adults hospitalized in ICU with hospital-acquired bloodstream infection (HA-BSI). METHODS: Nested cohort study within the EUROBACT-2 database, a multinational prospective cohort study including adults (≥ 18 years) hospitalized in the ICU during 2019-2021. We compared older versus younger adults in terms of infection characteristics (clinical signs and symptoms, source, and microbiological data), management (imaging, source control, antimicrobial therapy), and outcomes (28-day mortality and hospital discharge). RESULTS: Among 2111 individuals hospitalized in 219 ICUs with HA-BSI, 563 (27%) were ≥ 75 years old. Compared to younger patients, these individuals had higher comorbidity score and lower functional capacity; presented more often with a pulmonary, urinary, or unknown HA-BSI source; and had lower heart rate, blood pressure and temperature at presentation. Pathogens and resistance rates were similar in both groups. Differences in management included mainly lower rates of effective source control achievement among aged individuals. Older adults also had significantly higher day-28 mortality (50% versus 34%, p < 0.001), and lower rates of discharge from hospital (12% versus 20%, p < 0.001) by this time. CONCLUSIONS: Older adults with HA-BSI hospitalized in ICU have different baseline characteristics and source of infection compared to younger patients. Management of older adults differs mainly by lower probability to achieve source control. This should be targeted to improve outcomes among older ICU patients.

An immune-protein score combining TRAIL, IP-10 and CRP for predicting severe COVID-19 disease.

COVID-19 patients are oftentimes over- or under-treated due to a deficit in predictive management tools. This study reports derivation of an algorithm that integrates the host levels of TRAIL, IP-10, and CRP into a single numeric score that is an early indicator of severe outcome for COVID-19 patients and can identify patients at-risk to deteriorate. 394 COVID-19 patients were eligible; 29% meeting a severe outcome (intensive care unit admission/non-invasive or invasive ventilation/death). The score's area under the receiver operating characteristic curve (AUC) was 0.86, superior to IL-6 (AUC 0.77; p = 0.033) and CRP (AUC 0.78; p < 0.001). Likelihood of severe outcome increased significantly (p < 0.001) with higher scores. The score differentiated severe patients who further deteriorated from those who improved (p = 0.004) and projected 14-day survival probabilities (p < 0.001). The score accurately predicted COVID-19 patients at-risk for severe outcome, and therefore has potential to facilitate timely care escalation and de-escalation and appropriate resource allocation.

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.

The role of omega-3 polyunsaturated fatty acids in the intensive care unit.

PURPOSE OF REVIEW: This review provides an update on the actions of omega-3 polyunsaturated fatty acids (PUFAs) and presents the most recent findings from trials in patients in the intensive care unit (ICU) setting including relevant meta-analyses. Many specialized pro-resolving mediators (SPMs) are produced from bioactive omega-3 PUFAs and may explain many of the beneficial effects of omega-3 PUFAs, although other mechanisms of action of omega-3 PUFAs are being uncovered. RECENT FINDINGS: SPMs resolve inflammation, promote healing and support antiinfection activities of the immune system. Since publication of the ESPEN guidelines, numerous studies further support the use of omega-3 PUFAs. Recent meta-analyses favor the inclusion of omega-3 PUFAs in nutrition support of patients with acute respiratory distress syndrome or sepsis. Recent trials indicate that omega-3 PUFAs may protect against delirium and liver dysfunction in patients in the ICU, although effects on muscle loss are unclear and require further investigation. Critical illness may alter omega-3 PUFA turnover. There has been significant discussion about the potential for omega-3 PUFAs and SPMs in treatment of coronavirus disease 2019. SUMMARY: Evidence for benefits of omega-3 PUFAs in the ICU setting has strengthened through new trials and meta-analyses. Nevertheless, better quality trials are still needed. SPMs may explain many of the benefits of omega-3 PUFAs.

Early detection of oliguric events in critically ill patients in the ICU with a novel continuous urine flow measurement device: results of an initial validation study.

OBJECTIVES: Urine output is used to evaluate fluid status and is an important marker for acute kidney injury (AKI). Our primary aim was to validate a new automatic urine output monitoring device by comparison to the current practice - the standard urometer. METHODS: We conducted a prospective observational study in three ICUs. Urine flow measurements by Serenno Medical Automatic urine output measuring device (Serenno Medical, Yokneam, Israel) were compared to standard urometer readings taken automatically at 5-minutes intervals by a camera, and to hourly urometer readings by the nurses, both over 1 to 7 days. Our primary outcome was the difference between urine flow assessed by the Serenno device and reference camera-derived measurements (Camera). Our secondary outcome was the difference between urine flow assessed by the Serenno device and hourly nursing assessments (Nurse), and detection of oliguria. RESULTS: Thirty-seven patients completed the study, with 1,306 h of recording and a median of 25 measurement hours per patient. Bland and Altman analysis comparing the study device to camera measurements demonstrated good agreement, with a bias of -0.4 ml/h and 95% confidence intervals ranging from - 28 to 27ml/h. Concordance was 92%. The correlation between Camera and hourly nursing assessment of urine output was distinctly worse with a bias of 7.2 ml and limits of agreement extending from - 75 to + 107 ml. Severe oliguria (urine output < 0.3 ml/kg/h) lasting 2 h or more was common and observed in 8 (21%) of patients. Among the severe oliguric events lasting more than 3 consecutive hours, 6 (41%) were not detected or documented by the nursing staff. There were no device-related complications. CONCLUSION: The Serenno Medical Automatic urine output measuring device required minimal supervision, little ICU nursing staff attention, and is sufficiently accurate and precise. In addition to providing continuous assessments of urine output, it was considerably more accurate than hourly nursing assessments.

Feasibility of achieving different protein targets using a hypocaloric high-protein enteral formula in critically ill patients.

BACKGROUND AND AIMS: Combining energy and protein targets during the acute phase of critical illness is challenging. Energy should be provided progressively to reach targets while avoiding overfeeding and ensuring sufficient protein provision. This prospective observational study evaluated the feasibility of achieving protein targets guided by 24-h urinary nitrogen excretion while avoiding overfeeding when administering a high protein-to-energy ratio enteral nutrition (EN) formula. METHODS: Critically ill adult mechanically ventilated patients with an APACHE II score > 15, SOFA > 4 and without gastrointestinal dysfunction received EN with hypocaloric content for 7 days. Protein need was determined by 24-h urinary nitrogen excretion, up to 1.2 g/kg (Group A, N = 10) or up to 1.5 g/kg (Group B, N = 22). Variables assessed included nitrogen intake, excretion, balance; resting energy expenditure (REE); phase angle (PhA); gastrointestinal tolerance of EN. RESULTS: Demographic characteristics of groups were similar. Protein target was achieved using urinary nitrogen excretion measurements. Nitrogen balance worsened in Group A but improved in Group B. Daily protein and calorie intake and balance were significantly increased in Group B compared to Group A. REE was correlated to PhA measurements. Gastric tolerance of EN was good. CONCLUSIONS: Achieving the protein target using urinary nitrogen loss up to 1.5 g/kg/day was feasible in this hypercatabolic population. Reaching a higher protein and calorie target did not induce higher nitrogen excretion and was associated with improved nitrogen balance and a better energy intake without overfeeding. PhA appears to be related to REE and may reflect metabolism level, suggestive of a new phenotype for nutritional status. Trial registration 0795-18-RMC.

Evaluating the TARGET and EAT-ICU trials: how important are accurate caloric goals? Point-counterpoint: the pro position.

PURPOSE OF REVIEW: Controversies about the adequate amount of energy to deliver to critically ill patients are still going on, trying to find if hypocaloric or normocaloric regimen is beneficial in this population. Our purpose is to review recent publications using or not indirect calorimetry. RECENT FINDINGS: Numerous studies have compared hypocaloric to normocaloric regimen using predictive equations. However, these equations have been demonstrated to be inaccurate in most of the cases. Some recent PRCT using indirect calorimetry are finding some advantages to isocalorie regimens, but others not. Timing of the nutrition respecting or not the early substrate endogenous production, use of an adequate amount of protein, respect of the daily variability of needs may explain the divergent results observed. SUMMARY: Indirect calorimetry should be used to define the energy expenditure of the patient and to determine its requirements. More studies comparing isocalorie to hypocalorie regimens with fixed protein intake are necessary to confirm the observational and some of the PRCT-positive studies.

The best recipe: fat-based, protein-based, single amino acids?

PURPOSE OF REVIEW: Instead of comparing iso versus low energy or high versus low protein intake, the proportions between nutrients and the effects of specific amino or fatty acids may yield promising benefits for the nutritional therapy of critically ill patients. RECENT FINDINGS: Larger proportion of carbohydrates than lipids is usual in most of the commercial products. However, patients suffering from sepsis and from acute kidney injury preferentially utilize lipids. Parenteral omega-3-fatty acids, in particular, may be beneficial. Protein source and amount are important factors to achieve the best absorption and an improved nitrogen balance. Hydrolyzed whey protein reaches the highest amino acid plasma level if administered in large doses (35% of the measured energy expenditure). Muscle mass preservation may be achievable with large protein intake. ß-Hydroxy-ß-methylbutyrate has been shown to improve muscle strength in a large meta-analysis. SUMMARY: The nutritional therapy should take into account the fact that lipids are more oxidized. Intravenous lipid emulsions containing olive and fish oil are preferred, improving morbidity significantly in a recent meta-analysis. Enteral protein should be selected carefully according to protein source, origin and amount. Hydrolyzed whey protein improves nitrogen balance. The ultimate goal is to preserve muscle mass and muscle function. ß-Hydroxy-ß-methylbutyrate may improve muscle strength.

Nutrition of the COVID-19 patient in the intensive care unit (ICU): a practical guidance.

Five to 10% of the coronavirus SARS-CoV-2-infected patients, i.e., with new coronavirus disease 2019 (COVID-19), are presenting with an acute respiratory distress syndrome (ARDS) requiring urgent respiratory and hemodynamic support in the intensive care unit (ICU). However, nutrition is an important element of care. The nutritional assessment and the early nutritional care management of COVID-19 patients must be integrated into the overall therapeutic strategy. The international recommendations on nutrition in the ICU should be followed. Some specific issues about the nutrition of the COVID-19 patients in the ICU should be emphasized. We propose a flow chart and ten key issues for optimizing the nutrition management of COVID-19 patients in the ICU.

Preserving the quality of life: nutrition in the ICU.

Critically ill patients require adequate nutritional support to meet energy requirements both during and after intensive care unit (ICU) stay to protect against severe catabolism and prevent significant deconditioning. ICU patients often suffer from chronic critical illness causing an increase in energy expenditure, leading to proteolysis and related muscle loss. Careful supplementation and modulation of caloric and protein intake can avoid under- or overfeeding, both associated with poorer outcomes. Indirect calorimetry is the preferred method for assessing resting energy expenditure and the appropriate caloric and protein intake to counter energy and muscle loss. Physical exercise may have favorable effects on muscle preservation and should be considered even early in the hospital course of a critically ill patient. After liberation from the ventilator or during non-invasive ventilation, oral intake should be carefully evaluated and, in case of severe dysphagia, should be avoided and replaced by enteral of parenteral nutrition. Upon transfer from the ICU to the ward, adequate nutrition remains essential for long-term rehabilitation success and continued emphasis on sufficient nutritional supplementation in the ward is necessary to avoid a suboptimal nutritional state.

Thinking forward: promising but unproven ideas for future intensive care.

Progress toward determining the true worth of ongoing practices or value of recent innovations can be glacially slow when we insist on following the conventional stepwise scientific pathway. Moreover, a widely accepted but flawed conceptual paradigm often proves difficult to challenge, modify or reject. Yet, most experienced clinicians, educators and clinical scientists privately entertain untested ideas about how care could or should be improved, even if the supporting evidence base is currently thin or non-existent. This symposium encouraged experts to share such intriguing but unproven concepts, each based upon what the speaker considered a logical but unproven rationale. Such free interchange invited dialog that pointed toward new or neglected lines of research needed to improve care of the critically ill. In this summary of those presentations, a brief background outlines the rationale for each novel and deliberately provocative unconfirmed idea endorsed by the presenter.

Carbohydrate and Lipid Prescription, Administration, and Oxidation in Critically Ill Patients With Acute Kidney Injury: A Post Hoc Analysis.

OBJECTIVE: In a prospective multicenter study on adult patients with acute kidney injury (AKI) receiving enteral and/or parenteral nutrition, administered carbohydrates and lipids were compared to the prescribed amounts, as well as to substrate utilization data derived from indirect calorimetry measurements. METHODS: Resting energy expenditure (REE) was measured by indirect calorimetry. Nitrogen excretion was obtained from the protein catabolic rate calculated from urinary urea nitrogen when available and by urea kinetic-based methods in patients on renal replacement therapy. Fat and carbohydrate oxidations were derived from Frayn formulas. RESULTS: Ninety-two REE measurements were available in 35 critically ill patients with AKI (16 on renal replacement therapy). The mean lipid oxidation rate was 101 g/24 h (standard deviation [SD] 73.8), whereas prescribed lipids were 67 g/24 h (SD 32; P < .001). Carbohydrate utilization was derived from the same REE measurements yielding a mean carbohydrate oxidation of 105.8 g/24 h (SD 131.8), thus, much lower than the prescribed carbohydrates (186.7 g/24 h; SD 74.3; P < .001). The amount of fat and carbohydrates administered correlated to the prescribed amount (r = 0.896 and r = 0.829, respectively). Further analysis showed that this nutritional pattern was independent from the presence of sepsis. CONCLUSION: Our study suggests that critically ill patients with AKI do not receive an amount of carbohydrate and lipids adequate to support their needs on the basis of measured substrate utilization data. Thus, current nutritional approach in these patients, based on commercial formulas, should be challenged with measured substrate utilization-guided nutritional support.

To eat or to breathe? The answer is both! Nutritional management during noninvasive ventilation.

Treating respiratory distress is a priority when managing critically ill patients. Non-invasive ventilation (NIV) is increasingly used as a tool to prevent endotracheal intubation. Providing oral or enteral nutritional support during NIV may be perceived as unsafe because of the possible risk of aspiration so that these patients are frequently denied adequate caloric and protein intake. Newly available therapies, such as high-flow nasal oxygen (HFNO) may allow for more appropriate oral feeding.

Prevention of Exposure Keratopathy in Critically Ill Patients: A Single-Center, Randomized, Pilot Trial Comparing Ocular Lubrication With Bandage Contact Lenses and Punctal Plugs.

OBJECTIVES: To compare the effectiveness of bandage contact lenses and punctal plugs with ocular lubricants in preventing corneal damage in mechanically ventilated and sedated critically ill patients. DESIGN: Single-center, prospective, randomized, pilot study. SETTING: Sixteen-bed, general ICU at a tertiary academic medical center. PATIENTS: Adults admitted to the ICU and anticipated to require mechanical ventilation and continuous sedation for greater than or equal to 4 days. INTERVENTIONS: Patients were randomized to receive eye care with ocular lubricants (n = 38), bandage contact lenses (n = 33), or punctal plugs (n = 33). The bandage contact lenses were changed every 4 days, whereas the punctal plugs remained in situ for the entire study. MEASUREMENTS AND MAIN RESULTS: The primary endpoint was the presence or absence of corneal damage as assessed by the grade of keratopathy. Patients were examined by an ophthalmologist blinded to the study group every 4 days and at the time of withdrawal from the study, due to cessation of sedation, discharge from the ICU, or death. The mean duration of the study was 8.6 ± 6.2 days. The grade of keratopathy in the ocular lubricant group increased significantly in both eyes (p = 0.01 for both eyes) while no worsening was noted in either the lens or punctal plugs groups. In a post hoc analysis of patients with an initially abnormal ophthalmic examination, significant healing of keratopathy was noted in the lens group (p = 0.02 and 0.018 for left and right eyes, respectively) and in the right eye of the plugs group (p = 0.005); no improvement was noted in the ocular lubricant group. CONCLUSIONS: Compared with ocular lubrication, bandage contact lenses and punctal plugs were more effective in limiting keratopathy, and their use, particularly of bandage contact lenses, was associated with significant healing of existing lesions.

Lipid metabolism in critical illness.

PURPOSE OF REVIEW: This article describes recent findings regarding lipid metabolism in critical illness as well as in lipid therapy. RECENT FINDINGS: In critical illness, in the presence of a decrease in lipid absorption, adipose tissue lipolysis raises triglyceride levels. High-density lipoprotein and low-density lipoprotein are decreased because of impairment of lecithin-cholesterol acyltransferase, mainly in sepsis. In septic patients, lipid profile may be a predictor of survival. Nonsurvivors have lower levels of high-density lipoprotein and low-density lipoprotein. In metabolomic studies, most of the changes from baseline in septic patients were related to lipid metabolism. Lysophosphatidylcholine was also significantly lower in nonsurviving septic patients. SUMMARY: Lipid profile results are too often neglected by the clinician despite increasing knowledge in the modifications related to septic state as well as the importance of these values in the prognosis of the critically ill. Lipid administration (enterally or parenterally) should be guided by better knowledge of the lipid metabolism of the patient.

Parenteral or enteral nutrition: do you have the choice?

PURPOSE OF REVIEW: The review focuses on the use of parenteral nutrition and enteral nutrition in critically ill patients to optimize the nutrition care throughout the ICU stay. The key message is: you have the choice! RECENT FINDINGS: Enteral nutrition has been recommended for critically ill patients, whereas parenteral nutrition has been considered harmful and to be avoided. However, recent studies have challenged this theory. They demonstrated that enteral nutrition is frequently associated with energy and protein undernutrition, whereas parenteral nutrition becomes deleterious only if overfeeding is induced. Measuring energy expenditure by indirect calorimetry, in most cases, enables accurate determination of the energy needs to optimize the prescription of nutrition. Protein targets should also be considered for adequate feeding. Parenteral nutrition can be used as a supplement or as an alternative to enteral nutrition in case of gastrointestinal intolerance, to enable adequate energy, and protein provision. SUMMARY: Parenteral nutrition is a powerful tool to optimize nutrition care of critically ill patients to improve clinical outcome, if prescribed according to the individual needs of the patients. After 3-4 days of attempt to feed enterally, enteral nutrition or parenteral nutrition can be used alternatively or combined, as long as the target is reached with special attention to avoid hypercaloric feeding.