Visual Plate Waste in Hospitalized Patients: Length of Stay and Diet Order

Sodium Intake Estimation in Hospital Patients Using AI-Based Imaging: Prospective Pilot Study

BACKGROUND

Measurement of sodium intake in hospitalized patients is critical for their care. In this study, artificial intelligence (AI)-based imaging was performed to determine sodium intake in these patients.

OBJECTIVE

The applicability of a diet management system was evaluated using AI-based imaging to assess the sodium content of diets prescribed for hospitalized patients.

METHODS

Based on the information on the already investigated nutrients and quantity of food, consumed sodium was analyzed through photographs obtained before and after a meal. We used a hybrid model that first leveraged the capabilities of the You Only Look Once, version 4 (YOLOv4) architecture for the detection of food and dish areas in images. Following this initial detection, 2 distinct approaches were adopted for further classification: a custom ResNet-101 model and a hyperspectral imaging-based technique. These methodologies focused on accurate classification and estimation of the food quantity and sodium amount, respectively. The 24-hour urine sodium (UNa) value was measured as a reference for evaluating the sodium intake.

RESULTS

Results were analyzed using complete data from 25 participants out of the total 54 enrolled individuals. The median sodium intake calculated by the AI algorithm (AI-Na) was determined to be 2022.7 mg per day/person (adjusted by administered fluids). A significant correlation was observed between AI-Na and 24-hour UNa, while there was a notable disparity between them. A regression analysis, considering patient characteristics (eg, gender, age, renal function, the use of diuretics, and administered fluids) yielded a formula accounting for the interaction between AI-Na and 24-hour UNa. Consequently, it was concluded that AI-Na holds clinical significance in estimating salt intake for hospitalized patients using images without the need for 24-hour UNa measurements. The degree of correlation between AI-Na and 24-hour UNa was found to vary depending on the use of diuretics.

CONCLUSIONS

This study highlights the potential of AI-based imaging for determining sodium intake in hospitalized patients.

Dietary assessment methods for measurement of oral intake in acute care and critically ill hospitalised patients: a scoping review

Quantification of oral intake within the hospital setting is required to guide nutrition care. Multiple dietary assessment methods are available, yet details regarding their application in the acute care setting are scarce. This scoping review, conducted in accordance with JBI methodology, describes dietary assessment methods used to measure oral intake in acute and critical care hospital patients. The search was run across four databases to identify primary research conducted in adult acute or critical care settings from 1st of January 2000-15th March 2023 which quantified oral diet with any dietary assessment method. In total, 155 articles were included, predominantly from the acute care setting (n = 153, 99%). Studies were mainly single-centre (n = 138, 88%) and of observational design (n = 135, 87%). Estimated plate waste (n = 59, 38%) and food records (n = 43, 28%) were the most frequent assessment methods with energy and protein the main nutrients quantified (n = 81, 52%). Validation was completed in 23 (15%) studies, with the majority of these using a reference method reliant on estimation (n = 17, 74%). A quarter of studies (n = 39) quantified completion (either as complete versus incomplete or degree of completeness) and four studies (2.5%) explored factors influencing completion. Findings indicate a lack of high-quality evidence to guide selection and application of existing dietary assessment methods to quantify oral intake with a particular absence of evidence in the critical care setting. Further validation of existing tools and identification of factors influencing completion is needed to guide the optimal approach to quantification of oral intake in both research and clinical contexts.

How to improve food waste management in hospitals through focussing on the four most common measures for reducing plate waste

Hospitals have a responsibility to link human health and the environment, but food waste in hospitals has traditionally been much higher than in other areas of food supply. The cause of this situation has many negative impacts on health, economy, society, and environment. As a result, food waste has become a topic of discussion in hospital food departments. Part of this problem is plate waste, the served food that remains uneaten by patients. Given the magnitude of the food problem, this systematic review is aimed to identify the most common measures used to reduce plate waste in hospitals. PubMed, Scopus, and Google Scholar databases were comprehensively searched to identify food waste studies worldwide using related search terms. Many approaches have been recommended to increase patient food intake and minimise plate waste in hospitals. Up to date, the four most common include flexible portion sizes, increased food choices through selective menus, additional nutritional support and a better ordering and delivery system. Among them, the most used and effective are flexible portion sizes which may increase the ability of patients choosing their menus and upgrade ordering and delivery system by electronic format. In most studies, plate waste covers the most significant percentage of food waste produced in hospitals, while more than one approach is recommended to minimise it. In this aspect, further well-design, multicenter, clinical studies are strongly required to highlight and establish novel and effective approaches for improving food waste management in hospitals by reducing plate waste.

Strategies to Reduce the Rate of Plate Waste in Hospitalized Patients: A Scoping Review

There is evidence that hospital waste is indisputably high, and various strategies have been used to reduce the hospital's rate of plate waste. This study aimed to map the currently implemented strategies in lowering the rate of plate waste in hospitals and categorize the different types of strategies used as interventions, as well as determine their impact based on specific parameters. The scoping review method included a search of three databases using the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA-SCR). The duplicate articles (n = 80) were removed. A total of 441 articles remained for the title and abstract screening. After 400 were excluded, 41 articles were reviewed for eligibility. Thirty-two full articles were eliminated due to a lack of focus on plate waste evaluation. Finally, nine accepted studies were grouped into five categories: menu modification, room service implementation, menu presentation, meal-serving system, and dietary monitoring tool. In conclusion, results showed that the majority of the studies implemented either of the five strategies to reduce plate waste; however, the cook-freeze system and staff training for both kitchen and ward staff were not yet part of any intervention strategy. The potential of this method should be explored in future interventions.

Can hospitalized patients adequately estimate their own food intake? A cross-sectional pilot study

ABSTRACT Objective To assess and identify factors linked to the accuracy of patients’ food intake estimations through a self-monitoring instrument filled in by the patient. Methods This cross-sectional study approached adult hospital patients subjected to regular or therapeutic diets. The actual food intake percentage was obtained by the ratio between the actual food intake and the amount of food served x 100. Patients had to complete a food chart including 9 circles representing plates of food in percentages (increasing scale of 12.5%) to represent their food intake at lunch and/or dinner. The Bland-Altman method assessed the agreement between the actual and the estimated values. The associations between variables (age, sex, hospitalization day, diet prescription, amount of food served and actual food intake percentage) and the accuracy of the food intake estimation (adequate ±10%, overestimated and underestimated) were evaluated through univariate multinomial logistic regression. Results Ninety-six patients were evaluated (51.0% male; 44.0±15.8 years of age). The Bland-Altman analysis showed good agreement between the actual and the estimated food intake. The actual food intake percentage was the only variable associated with the accuracy of the food intake estimation. Conclusion Most patients (~70%) adequately estimated their food intake using the 9-point food chart tested. Furthermore, the only factor linked to the accuracy of the food intake estimation was the actual food-intake percentage. These findings provide preliminary support for the usefulness of this instrument. However, it must be tested in a representative sample of hospitalized patients.

Plate waste study among hospitalised patients receiving texture-modified diet

BACKGROUND/OBJECTIVES

While plate waste has been widely investigated in hospitals, there have been minimal studies specific to the texture-modified diet (TMD). This study aims to determine the percentage of plate waste among patients prescribed with TMD and its contributory factors.

SUBJECTS/METHODS

This was a single-centre study conducted in the university hospital on three types of TMD (blended diet, mixed porridge, minced diet) during lunch and dinner meals. Weighing method and visual estimation method assisted by digital photograph were adopted in this study. Face to face interview was carried out to investigate on 1) the food/food service quality factors in terms of patients' satisfaction level towards sensorial quality of food and food services provided and 2) the clinical/external factors including appetite, the provision of oral nutrition support, time taking the diet, the need for feeding assistance and the length of hospital stay.

RESULTS

The mean percentage of overall plate waste of 95 patients receiving TMD was high (47.5%). Blended diet was identified as the most wasted diet (65%) followed by minced diet (56%) and mixed porridge (35%). Satisfaction level among patients was moderate. Patients on TMD in general had higher satisfaction level on the aspect of food service as compared to food quality. Substantial association between sensorial qualities of food and plate waste were varied according to individual TMD type. A multiple linear regression showed that only the satisfaction level toward the aspects of appearance and variety of foods were the predictors of TMD plate waste (R² = 0.254, P < 0.05).

CONCLUSIONS

A significant relationship between the percentage of plate waste and the overall satisfaction level of patients receiving TMD suggests that vigorous strategies are needed to reduce the food waste of TMD which will lead to a better nutritional status and clinical outcomes among the patients.

Measuring Food Waste and Consumption by Children Using Photography

A photography method was used to measure waste on food trays in school lunch in France, using the 5-point quarter-waste scale. While food waste has been studied extensively in US school lunches, the structure of the French lunch meal is quite different, with multiple courses, and vegetables (raw and cooked) in more than one course. Vegetables were the most wasted food category as usually seen in school lunch research, especially cooked vegetables, which were wasted at rates of 66%-83%. Raw vegetables were still wasted more than main dishes, starchy products, dairy, fruit, and desserts. Vegetables were also the most disliked food category, with the classes of vegetables falling in the same order as for waste. Waste and liking were highly correlated. Sensory characteristics of the food were cited as a main reason for liking/disliking. There is a strong connection between food liking and food consumption, and this connection should be the basis for future attempts to modify school lunch to improve consumption. The photographic method of measuring food waste at an individual level performed well.

The impact of electronic meal ordering systems on hospital and patient outcomes: A systematic review

BACKGROUND

Malnutrition is a serious clinical issue associated with adverse patient and hospital outcomes. Hospitals need to consider interventions that support the provision of optimal nutritional management and care for patients. Electronic meal ordering (EMO) systems provide an alternative to traditional paper-based meal ordering with the capacity to support appropriate orders, monitor nutritional status, and potentially improve clinical outcomes.

METHODS

This review aimed to identify the impact of EMO systems on hospital and patient outcomes. We sought quantitative evidence (peer-reviewed and grey literature) from studies evaluating EMO systems in healthcare facilities, published after 1999 and available in the English language.

RESULTS

We identified 23 studies evaluating one of three distinct EMO system-supported models: spoken menu, room service, and self-service. While limited, the evidence indicated that EMO systems were associated with: improved patient satisfaction; decreased food waste; increased consumption; and, for spoken menus, more time with patients. There was no substantive evidence of impact on clinical outcomes.

CONCLUSIONS

Whether EMO systems meet their potential to support nutritional monitoring and positively impact clinical outcomes remains unanswered within the evidence. Thus, policy makers and hospital management currently have a poor evidence base upon which to make decisions about the value of implementing EMO. Whether these systems can provide support and guidance to patients during meal ordering, improve order appropriateness and accuracy through compliance checking, identify patients in need of dietary education or those at risk of malnutrition are critical areas of focus for future research.

A Prospective Study Identifying a Change in Energy and Protein Intake of Older Adults during Inpatient Rehabilitation

Understanding older patients' dietary intake patterns may improve the timing of strategies to address hospital malnutrition. The aims of this study were to explore longitudinally the change in daily energy (kJ/day) and protein (g/day) intake, and associated factors. Data were derived using a 5-point scale to visually estimate plate waste, and known nutrient composition data. Analyses determined the change in intake between admission and day 14, and admission, day 14 and day 28, respectively. Data were available for 39 participants between admission and day 14 (median (interquartile range) age 82 (78⁻87) years; 54% male) and 12 participants between admission, day 14 and day 28 (median (IQR) age 79 (69⁻84) years; 58% male). From admission to day 14 there was a significant increase in the mean (SD) daily intake of energy (6177 (1879) kJ/day vs. 7213 (1903), p < 0.001) and protein (63.7 (23) g/day vs. 76.4 (23.0) g/day, p = 0.003) but no change from admission to day 14 to day 28. There was a significant inverse relationship between amount consumed at admission and change in intake. Variability in elderly patients' intake over time has implications for the timing of nutritional care and data collection in research studies.

Comparing nutritional requirements, provision and intakes among patients prescribed therapeutic diets in hospital: An observational study

OBJECTIVE

Nutrition is an important part of recovery for hospitalized patients. The aim of this study was to assess the nutritional adequacy of meals provided to and consumed by patients prescribed a therapeutic diet.

METHODS

Patients (N = 110) prescribed a therapeutic diet (texture-modified, low-fiber, oral fluid, or food allergy or intolerance diets) for medical or nutritional reasons were recruited from six wards of a tertiary hospital. Complete (24-h) dietary provisions and intakes were directly observed and analyzed for energy (kJ) and protein (g) content. A chart audit gathered demographic, clinical, and nutrition-related information to calculate each patient's disease-specific estimated energy and protein requirements. Provisions and intake were considered adequate if they met ≥75% of the patient's estimated requirements.

RESULTS

Mean energy and protein provided to patients (5844 ± 2319 kJ, 53 ± 30 g) were significantly lower than their mean estimated requirements (8786 ± 1641 kJ, 86 ± 18 g). Consequently, mean nutrition intake (4088 ± 2423 kJ, 37 ± 28 g) were significantly lower than estimated requirements. Only 37% (41) of patients were provided with and 18% (20) consumed adequate nutrition to meet their estimated requirements. No therapeutic diet provided adequate food to meet the energy and protein requirements of all recipients. Patients on oral fluid diets had the highest estimated requirements (9497 ± 1455 kJ, 93 ± 16 g) and the lowest nutrient provision (3497 ± 1388 kJ, 25 ± 19 g) and intake (2156 ± 1394 kJ, 14 ± 14 g).

CONCLUSION

Hospitalized patients prescribed therapeutic diets (particularly fluid-only diets) are at risk for malnutrition. Further research is required to determine the most effective strategies to improve nutritional provision and intake among patients prescribed therapeutic diets.

Determination of plate waste in primary school lunches by weighing and visual estimation methods: a validation study

The aim of this study was to validate the visual estimation method for aggregated plate waste of main dish at Portuguese primary school canteens. For this purpose plate waste at school lunch was measured for 505 individual servings, using weighing individual servings and plate waste and visual estimation method by a 6-point scale, as developed by Comstock et al. (1981). A high variability of initial serving weights was found with serving sizes ranging from 88.9 to 283.3g and with a coefficient of variation ranging from 5.5% to 24.7%. Mean plate waste was 27.5% according to the weighing method. There was a significant bias in the conversion of the visual waste estimations to actual waste, being overestimated by an average of 8.0 g (ranging from -12.9 g to 41.4 g). According to Bland and Altman plot, the mean difference between methods was of 8.0 g and the amplitude interval was 102.6g. The study showed that the visual estimation method is not as accurate as the weighing method in assessing nonselective aggregated plate waste at primary school canteens. Our findings are thus very important on considering plate waste assessment, since the wide variation on initial servings introduces a relevant bias when considering standard portions or a random sample of initial servings. Although, greater convenience, time-saving and the possibility to monitor plate waste of large groups, make the visual estimation method an important method to assess plate waste at school canteens, these results highlighted the need of portions standardization and control of initial servings to allow for its use.

Prognostic indices of poor nutritional status and their impact on prolonged hospital stay in a Greek university hospital

Background. To ascertain the potential contributors to nutritional risk manifestation and to disclose the factors exerting a negative impact on hospital length of stay (LOS), by means of poor nutritional status, in a nonselected hospitalized population. Materials and Methods. NutritionDay project questionnaires were applied to 295 adult patients. Study parameters included anthropometric data, demographics, medical history, dietary-related factors, and self-perception of health status. Body Mass Index (BMI) and Malnutrition Universal Screening Tool (MUST) were calculated for each participant. MUST score was applied for malnutrition assessment, while hospital LOS constituted the outcome of interest. Results. Of the total cohort, 42.3% were at nutritional risk and 21.4% malnourished. Age, gender, BMI, MUST score, autonomy, health quality, appetite, quantity of food intake, weight loss, arm or calf perimeter (P < 0.001, for all), and dietary type (P < 0.01) affected nutritional status. Poor nutrition status (P = 0.000), deteriorated appetite (P = 0.000) or food intake (P = 0.025), limited autonomy (P = 0.013), artificial nutrition (P = 0.012), weight loss (P = 0.010), and arm circumference <21 cm (P = 0.007) were the most powerful predictors of hospital LOS >7 days. Conclusion. Nutritional status and nutrition-related parameters such as weight loss, quantity of food intake, appetite, arm circumference, dietary type, and extent of dependence confer considerable prognostic value regarding hospital LOS in acute care setting.

Assessment of foodservice quality and identification of improvement strategies using hospital foodservice quality model

The purposes of this study were to assess hospital foodservice quality and to identify causes of quality problems and improvement strategies. Based on the review of literature, hospital foodservice quality was defined and the Hospital Foodservice Quality model was presented. The study was conducted in two steps. In Step 1, nutritional standards specified on diet manuals and nutrients of planned menus, served meals, and consumed meals for regular, diabetic, and low-sodium diets were assessed in three general hospitals. Quality problems were found in all three hospitals since patients consumed less than their nutritional requirements. Considering the effects of four gaps in the Hospital Foodservice Quality model, Gaps 3 and 4 were selected as critical control points (CCPs) for hospital foodservice quality management. In Step 2, the causes of the gaps and improvement strategies at CCPs were labeled as "quality hazards" and "corrective actions", respectively and were identified using a case study. At Gap 3, inaccurate forecasting and a lack of control during production were identified as quality hazards and corrective actions proposed were establishing an accurate forecasting system, improving standardized recipes, emphasizing the use of standardized recipes, and conducting employee training. At Gap 4, quality hazards were menus of low preferences, inconsistency of menu quality, a lack of menu variety, improper food temperatures, and patients' lack of understanding of their nutritional requirements. To reduce Gap 4, the dietary departments should conduct patient surveys on menu preferences on a regular basis, develop new menus, especially for therapeutic diets, maintain food temperatures during distribution, provide more choices, conduct meal rounds, and provide nutrition education and counseling. The Hospital Foodservice Quality Model was a useful tool for identifying causes of the foodservice quality problems and improvement strategies from a holistic point of view.