The Use of Technology in Identifying Hospital Malnutrition: Scoping Review

Patient-Led, Technology-Assisted Malnutrition Risk Screening in Hospital: A Feasibility Study

Malnutrition risk screening is crucial to identify at-risk patients in hospitals; however, screening rates can be suboptimal. This study evaluated the feasibility, acceptability, and potential cost-effectiveness of patient-led, technology-assisted malnutrition risk screening. A prospective multi-methods study was conducted in a 750-bed public hospital in Australia. Patients were recruited from seven wards and asked to complete an electronic version of the Malnutrition Screening Tool (e-MST) on bedside computer screens. Data were collected on feasibility, acceptability, and cost. Feasibility data were compared to pre-determined criteria on recruitment (≥50% recruitment rate) and e-MST completion (≥75% completion rate). Quantitative acceptability (survey) data were analyzed descriptively. Patient interview data were analyzed thematically. The economic evaluation was from the perspective of the health service using a decision tree analytic model. Both feasibility criteria were met; the recruitment rate was 78% and all 121 participants (52% male, median age 59 [IQR 48-69] years) completed the e-MST. Patient acceptability was high. Patient-led e-MST was modeled to save $3.23 AUD per patient and yield 6.5 more true malnutrition cases (per 121 patients) with an incremental cost saving per additional malnutrition case of 0.50 AUD. Patient-led, technology-assisted malnutrition risk screening was found to be feasible, acceptable to patients, and cost-effective (higher malnutrition yield and less costly) compared to current practice at this hospital.

Intervention-related, contextual and personal factors affecting the implementation of an evidence-based digital system for prevention and treatment of malnutrition in elderly institutionalized patients: a qualitative study

BACKGROUND

Malnutrition in elderly institutionalized patients is a significant challenge associated with adverse health outcomes. The 'MyFood' decision support system was designed to prevent and treat malnutrition and has previously been studied in a hospital setting. The aim of this study was to explore the experiences of nursing staff regarding the implementation of MyFood in settings treating elderly patients.

METHODS

The study was conducted in two settings treating elderly patients in Norway. Nursing staff received training in how to follow-up patients with MyFood. Qualitative interviews were conducted with 12 nursing staff. The Consolidated Framework for Implementation Research (CFIR) was used to guide the data collection and the thematic data analysis.

RESULTS

The implementation of a digital decision support system to prevent and treat malnutrition into settings treating elderly patients was found to be affected by intervention-related, contextual, and personal factors. Although nursing staff experienced several advantages, the leadership engagement was low and hampered the implementation.

CONCLUSION

Nursing staff experienced several advantages with implementing a digital decision support system for the prevention and treatment of malnutrition in institutionalized elderly patients, including quality improvements and time savings. The results indicate that the leadership engagement was weak and that some nursing staff experienced low self-efficacy in digital competence. Future improvements include increasing the level of training, using MyFood throughout the patient course and involving the patient's next-of-kin.

TRIAL REGISTRATION

The study was acknowledged by The Norwegian Centre for Research Data (NSD), ref. number 135175.

Implementation of an electronic solution to improve malnutrition identification and support clinical best practice

BACKGROUND

Routine malnutrition risk screening of patients is critical for optimal care and comprises part of the National Australian Hospital Standards. Identification of malnutrition also ensures reimbursement for hospitals to adequately treat these high-risk patients. However, timely, accurate screening, assessment and coding of malnutrition remains suboptimal. The present study aimed to investigate manual and digital interventions to overcome barriers to malnutrition identification for improvements in the hospital setting.

METHODS

Retrospective reporting on malnutrition identification processes was conducted through two stages: (1) manual auditing intervention and (2) development of a digital solution - the electronic malnutrition management solution (eMS). Repeated process audits were completed at approximately 6-monthly intervals through both stages between 2016 and 2019 and the results were analysed. In Stage 2, time investment and staff adoption of the digital solution were measured.

RESULTS

Overall, the combined effect of both regular auditing and use of the eMS resulted in statistically significant improvements across all six key measures: patients identified (97%-100%; p < 0.001), screened (68%-95%; p < 0.001), screened within 24 h (51%-89%; p < 0.001), assessed (72%-95%; p < 0.001), assessed within 24 h (66%-93%; p < 0.001) and coded (81%-100%; p = 0.017). The eMS demonstrated a reduction in screening time by over 60% with user adoption 100%. Data analytics enabled automated, real-time auditing with a 95% reduction in time taken to audit.

CONCLUSIONS

A single digital solution for management of malnutrition and automation of auditing demonstrated significant improvements where manual or combinations of manual and electronic systems continue to fall short.

A Digital Smartphone-Based Self-administered Tool (R+ Dietitian) for Nutritional Risk Screening and Dietary Assessment in Hospitalized Patients With Cancer: Evaluation and Diagnostic Accuracy Study

BACKGROUND

Malnutrition is a common and severe problem in patients with cancer that directly increases the incidence of complications and significantly deteriorates quality of life. Nutritional risk screening and dietary assessment are critical because they are the basis for providing personalized nutritional support. No digital smartphone-based self-administered tool for nutritional risk screening and dietary assessment among hospitalized patients with cancer has been developed and evaluated.

OBJECTIVE

This study aims to develop a digital smartphone-based self-administered mini program for nutritional risk screening and dietary assessment for hospitalized patients with cancer and to evaluate the validity of the mini program.

METHODS

We have developed the R+ Dietitian mini program, which consists of 3 parts: (1) collection of basic information of patients, (2) nutritional risk screening, and (3) dietary energy and protein assessment. The face-to-face paper-based Nutritional Risk Screening (NRS-2002), the Patient-Generated Subjective Global Assessment Short Form (PG-SGA-SF), and 3 days of 24-hour dietary recall (3d-24HRs) questionnaires were administered according to standard procedure by 2 trained dietitians as the reference methods. Sensitivity, specificity, positive predictive value, negative predictive value, κ value, and correlation coefficients (CCs) of nutritional risk screened in R+ Dietitian against the reference methods, as well as the difference and CCs of estimated dietary energy and protein intakes between R+ Dietitian and 3d-24HRs were calculated to evaluate the validity of R+ Dietitian.

RESULTS

A total of 244 hospitalized patients with cancer were recruited to evaluate the validity of R+ Dietitian. The NRS-2002 and PG-SGA-SF tools in R+ Dietitian showed high accuracy, sensitivity, and specificity (77.5%, 81.0%, and 76.7% and 69.3%, 84.5%, and 64.5%, respectively), and fair agreement (κ=0.42 and 0.37, respectively; CC 0.62 and 0.56, respectively) with the NRS-2002 and PG-SGA-SF tools administered by dietitians. The estimated intakes of dietary energy and protein were significantly higher (P<.001 for both) in R+ Dietitian (mean difference of energy intake: 144.2 kcal, SD 454.8; median difference of protein intake: 10.7 g, IQR 9.5-39.8), and showed fair agreement (CC 0.59 and 0.47, respectively), compared with 3d-24HRs performed by dietitians.

CONCLUSIONS

The identified nutritional risk and assessment of dietary intakes of energy and protein in R+ Dietitian displayed a fair agreement with the screening and assessment conducted by dietitians. R+ Dietitian has the potential to be a tool for nutritional risk screening and dietary intake assessment among hospitalized patients with cancer.

TRIAL REGISTRATION

Chinese Clinical Trial Registry ChiCTR1900026324; https://www.chictr.org.cn/showprojen.aspx?proj=41528.

Using an interactive nutrition technology platform to predict malnutrition risk

AIMS

The Nutrition Dashboard is an interactive nutrition technology platform that displays food provision and intake data used to categorise the nutrition risk of hospitalised individuals. This study aimed to investigate the Nutrition Dashboard's ability to identify malnutrition compared to a validated malnutrition screening tool.

METHODS

A retrospective observational study at a 99-bed hospital was conducted using medical record and food intake data presented via the Nutrition Dashboard. Inter-Rater Reliability of food intake estimation between hospital catering staff and a dietitian reported good agreement across 912 food items (κ = 0.69, 95% CI 0.65-0.72, p < 0.001). Default nutritional adequacy thresholds of 4500kJ and 50g protein were applied for Nutrition Dashboard categorisation of supply and intake. Generalised estimating equation regression models explored the association between the Nutrition Dashboard risk categories and the Malnutrition Screening Tool, with and without controlling for patient demographic characteristics.

RESULTS

Analyses from 216 individuals (1783 hospital-stay days) found those in the highest risk Nutrition Dashboard Category were 1.93 times more likely to have a Malnutrition Screening Tool score indicating risk compared to the lowest Nutrition Dashboard Category (unadjusted odds ratio 1.93, 95% CI, 1.17-3.19, p<0.01). When patient weight was added to the model, lower weight became the only significant predictor of MST≥2 (p<0.01) CONCLUSIONS: This study indicates a role for nutrition intake technology in malnutrition screening. Further adaptions that address the complexities of applying this technology could improve the use of the Nutrition Dashboard to support identification of malnutrition. This article is protected by copyright. All rights reserved.

Digital health in older adults for the prevention and management of cardiovascular diseases and frailty. A clinical consensus statement from the ESC Council for Cardiology Practice/Taskforce on Geriatric Cardiology, the ESC Digital Health Committee and the ESC Working Group on e-Cardiology

Digital health technology is receiving increasing attention in cardiology. The rise of accessibility of digital health tools including wearable technologies and smart phone applications used in medical practice has created a new era in healthcare. The coronavirus pandemic has provided a new impetus for changes in delivering medical assistance across the world. This Consensus document discusses the potential implementation of digital health technology in older adults, suggesting a practical approach to general cardiologists working in an ambulatory outpatient clinic, highlighting the potential benefit and challenges of digital health in older patients with, or at risk of, cardiovascular disease. Advancing age may lead to a progressive loss of independence, to frailty, and to increasing degrees of disability. In geriatric cardiology, digital health technology may serve as an additional tool both in cardiovascular prevention and treatment that may help by (i) supporting self-caring patients with cardiovascular disease to maintain their independence and improve the management of their cardiovascular disease and (ii) improving the prevention, detection, and management of frailty and supporting collaboration with caregivers. Digital health technology has the potential to be useful for every field of cardiology, but notably in an office-based setting with frequent contact with ambulatory older adults who may be pre-frail or frail but who are still able to live at home. Cardiologists and other healthcare professionals should increase their digital health skills and learn how best to apply and integrate new technologies into daily practice and how to engage older people and their caregivers in a tailored programme of care.

Indicators of nutritional risk in hospital inpatients: a narrative review

Malnutrition is common in the acute care setting. Despite the existence of a plethora of screening tools, many malnourished patients remain undiagnosed and untreated, in part due to competing responsibilities for screening staff, under- or over-referral to dietetics services, and inadequate dietetics resources. Better identification of patients at risk of malnutrition would enable optimised care provision and streamlined care pathways. This narrative review of reviews aimed to collate and synthesise literature documenting nutritional risk factors in adult hospital inpatients, to generate a comprehensive list of nutritional risk indicators from high methodological quality review articles. Six electronic databases were searched (Medline, Cumulative Index to Nursing and Allied Health Literature, Cochrane Database of Systematic Reviews, Joanna Briggs Institute Database, Embase and Scopus) using a systematic search strategy. Three researchers screened the resulting 5889 citations, identifying 59 reviews summarising original studies that investigated associations between indicators and measures of malnutrition, undernutrition or nutritional risk. After quality appraisal by two researchers, using the American Dietetic Association Quality Criteria Checklist for Review Articles, seven reviews were classified as high quality, identifying fifty-seven unique indicators of nutritional risk (disease status/condition – twenty-three; eating/appetite/digestion – twelve; type of diet – five; cognition/psychology/social factors – five; medication-related – two; miscellaneous – ten). This is the first comprehensive list of nutritional risk factors in adult hospital inpatients, derived from only the highest methodological quality reviews. This list contributes to the development of practice and evidence-informed systems-level approaches to the identification of nutritional risk in the acute care setting.

Identification of nutritional risk in the acute care setting: progress towards a practice and evidence informed systems level approach

Background

To improve nutritional assessment and care pathways in the acute care setting, it is important to understand the indicators that may predict nutritional risk. Informed by a review of systematic reviews, this project engaged stakeholders to prioritise and reach consensus on a list of evidence based and clinically contextualised indicators for identifying malnutrition risk in the acute care setting.

Methods

A modified Delphi approach was employed which consisted of four rounds of consultation with 54 stakeholders and 10 experts to reach consensus and refine a list of 57 risk indicators identified from a review of systematic reviews. Weighted mean and variance scores for each indicator were evaluated. Consistency was tested with intra class correlation coefficient. Cronbach's alpha was used to determine the reliability of the indicators. The final list of indicators was subject to Cronbach’s alpha and exploratory principal component analysis.

Results

Fifteen indicators were considered to be the most important in identifying nutritional risk. These included difficulty self-feeding, polypharmacy, surgery and impaired gastro-intestinal function. There was 82% agreement for the final 15 indicators that they collectively would predict malnutrition risk in hospital inpatients.

Conclusion

The 15 indicators identified are supported by evidence and are clinically informed. This represents an opportunity for translation into a novel and automated systems level approach for identifying malnutrition risk in the acute care setting.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12913-021-07299-y.

Wearable Bioimpedance Monitoring: Viewpoint for Application in Chronic Conditions

Currently, nearly 6 in 10 US adults are suffering from at least one chronic condition. Wearable technology could help in controlling the health care costs by remote monitoring and early detection of disease worsening. However, in recent years, there have been disappointments in wearable technology with respect to reliability, lack of feedback, or lack of user comfort. One of the promising sensor techniques for wearable monitoring of chronic disease is bioimpedance, which is a noninvasive, versatile sensing method that can be applied in different ways to extract a wide range of health care parameters. Due to the changes in impedance caused by either breathing or blood flow, time-varying signals such as respiration and cardiac output can be obtained with bioimpedance. A second application area is related to body composition and fluid status (eg, pulmonary congestion monitoring in patients with heart failure). Finally, bioimpedance can be used for continuous and real-time imaging (eg, during mechanical ventilation). In this viewpoint, we evaluate the use of wearable bioimpedance monitoring for application in chronic conditions, focusing on the current status, recent improvements, and challenges that still need to be tackled.

The landscape of nutri-informatics: a review of current resources and challenges for integrative nutrition research

Informatics has become an essential component of research in the past few decades, capitalizing on the efficiency and power of computation to improve the knowledge gained from increasing quantities and types of data. While other fields of research such as genomics are well represented in informatics resources, nutrition remains underrepresented. Nutrition is one of the most integral components of human life, and it impacts individuals far beyond just nutrient provisions. For example, nutrition plays a role in cultural practices, interpersonal relationships and body image. Despite this, integrated computational investigations have been limited due to challenges within nutrition informatics (nutri-informatics) and nutrition data. The purpose of this review is to describe the landscape of nutri-informatics resources available for use in computational nutrition research and clinical utilization. In particular, we will focus on the application of biomedical ontologies and their potential to improve the standardization and interoperability of nutrition terminologies and relationships between nutrition and other biomedical disciplines such as disease and phenomics. Additionally, we will highlight challenges currently faced by the nutri-informatics community including experimental design, data aggregation and the roles scientific journals and primary nutrition researchers play in facilitating data reuse and successful computational research. Finally, we will conclude with a call to action to create and follow community standards regarding standardization of language, documentation specifications and requirements for data reuse. With the continued movement toward community standards of this kind, the entire nutrition research community can transition toward greater usage of Findability, Accessibility, Interoperability and Reusability principles and in turn more transparent science.

A Systematic Review of Nutrition Recommendation Systems: With Focus on Technical Aspects

Background:

Nutrition informatics has become a novel approach for registered dietitians to practice in this field and make a profit for health care. Recommendation systems considered as an effective technology into aid users to adjust their eating behavior and achieve the goal of healthier food and diet. The purpose of this study is to review nutrition recommendation systems (NRS) and their characteristics for the first time.

Material and Methods:

The systematic review was conducted using a comprehensive selection of scientific databases as reference sources, allowing access to diverse publications in the field. The process of articles selection was based on the PRISMA strategy. We identified keywords from our initial research, MeSH database and expert’s opinion. Databases of PubMed, Web of Sciences, Scopus, Embase, and IEEE were searched. After evaluating, they obtained records from databases by two independent reviewers and inclusion and exclusion criteria were applied to each retrieved work to select those of interest. Finally, 25 studies were included.

Results:

Hybrid recommender systems and knowledge-based recommender systems with 40% and 32%, respectively, were the mostly recommender types used in NRS. In NRS, rule-based and ontology techniques were used frequently. The frequented platform that applied in NRS was a mobile application with 28%.

Conclusion:

If NRS was properly designed, implemented and finally evaluated, it could be used as an effective tool to improve nutrition and promote a healthy lifestyle. This study can help to inform specialists in the nutrition informatics domain, which was necessary to design and develop NRS.

Comparison of preoperative Nutritional Risk Index and Body Mass Index for predicting immediate postoperative outcomes following major gastrointestinal surgery: Cohort-study

Background

Malnutrition is a major risk factor for morbidity and mortality following gastrointestinal (GI) surgery. Nutritional Risk Index (NRI) and Body Mass Index (BMI) are the two well-validated tools that are readily available and do not add financial burden to the patients. The study aimed to analyze NRI and BMI as a preoperative nutritional indicator of postoperative complications following GI surgeries.

Methods

It is an observational study, where preoperative nutritional status and early postoperative complications <30 days (infectious or noninfectious) were studied. The patients admitted between July 2015 to May 2017, who underwent major GI surgeries were included in the study. The correlation between NRI and BMI of these patients were evaluated.

Results

The rate of wound infection was 4 (30.7%) out of 13 in severe malnutrition subgroup defined by NRI <83.5 which was found to be statistically significant (p = 0.003). However, it was not significant in a subgroup of patients with undernutrition defined by BMI <18.49%. In a subgroup analysis, abnormal NRI was found to be statistically significant (p = 0.004) in patients with malignant disease and malnutrition 64 (47.76%) out of 97 (72.3%). The mean NRI (94.49 ± 9.164) better correlated with advancing age (p < 0.05) and the correlation coefficient of 0.3100 showed a significant negative correlation. With 10 fold increase in age (r² = 0.096) the likelihood of malnutrition was 9.6% and subsequently increased postoperative complications.

Conclusion

In cases of malignancy and advanced age, NRI is a better predictor of immediate postoperative outcome than BMI.

•

Nutritional Risk Index (NRI) and Body mass Index (BMI) were used to screen the preoperative patients.

•

NRI and BMI are the two well validated tools which is readily available and does not add financial burden to the patients.

•

NRI better correlated with postoperative wound infections and the length of hospital stay.

•

The patients with advanced age and malignant diseases were at higher risk of malnutrition and postoperative complications.

Barriers and Facilitators for Implementing a Decision Support System to Prevent and Treat Disease-Related Malnutrition in a Hospital Setting: Qualitative Study

Background

Disease-related malnutrition is a challenge among hospitalized patients. Despite guidelines and recommendations for prevention and treatment, the condition continues to be prevalent. The MyFood system is a recently developed decision support system to prevent and treat disease-related malnutrition.

Objective

To investigate the possible implementation of the MyFood system in clinical practice, the aims of the study were (1) to identify current practice, routines, barriers, and facilitators of nutritional care; (2) to identify potential barriers and facilitators for the use of MyFood; and (3) to identify the key aspects of an implementation plan.

Methods

A qualitative study was performed among nurses, physicians, registered dietitians, and middle managers in 2 departments in a university hospital in Norway. Focus group discussions and semistructured interviews were used to collect data. The Consolidated Framework for Implementation Research (CFIR) was used to create the interview guide and analyze the results. The transcripts were analyzed using a thematic analysis.

Results

A total of 27 health care professionals participated in the interviews and focus groups, including nurses (n=20), physicians (n=2), registered dietitians (n=2), and middle managers (n=3). The data were analyzed within 22 of the 39 CFIR constructs. Using the 5 CFIR domains as themes, we obtained the following results: (1) Intervention characteristics: MyFood was perceived to have a relative advantage of being more trustworthy, systematic, and motivational and providing increased awareness of nutritional treatment compared with the current practice. Its lack of communication with the existing digital systems was perceived as a potential barrier; (2) Outer settings: patients from different cultural backgrounds with language barriers and of older age were potential barriers for the use of the MyFood system; (3) Inner settings: no culture for specific routines or systems related to nutritional care existed in the departments. However, tension for change regarding screening for malnutrition risk, monitoring and nutritional treatment was highlighted in all categories of interviewees; (4) Characteristics of the individuals: positive attitudes toward MyFood were present among the majority of the interviewees, and they expressed self-efficacy toward the perceived use of MyFood; (5) Process: providing sufficient information to everyone in the department was highlighted as key to the success of the implementation. The involvement of opinion leaders, implementation leaders, and champions was also suggested for the implementation plan.

Conclusions

This study identified several challenges in the nutritional care of hospitalized patients at risk of malnutrition and deviations from recommendations and guidelines. The MyFood system was perceived as being more precise, trustworthy, and motivational than the current practice. However, several potential barriers were identified. The assessment of the current situation and the identification of perceived barriers and facilitators will be used in planning an implementation and effect study, including the creation of an implementation plan.

Improving Digital Hospital Transformation: Development of an Outcomes-Based Infrastructure Maturity Assessment Framework

Background

Digital transformation in health care is being driven by the need to improve quality, reduce costs, and enhance the patient experience of health care delivery. It does this through both the direct intervention of technology to create new diagnostic and treatment opportunities and also through the improved use of information to create more engaging and efficient care processes.

Objective

In a modern digital hospital, improved clinical and business processes are often driven through enhancing the information flows that support them. To understand an organization’s ability to transform their information flows requires a clear understanding of the capabilities of an organization’s information technology infrastructure. To date, hospital facilities have been challenged by the absence of uniform ways of describing this infrastructure that would enable them to benchmark where they are and create a vision of where they would like to be. While there is an industry assessment measure for electronic medical record (EMR) adoption using the Healthcare Information and Management Systems Society Analytics EMR Adoption Model, there is no equivalent for assessing the infrastructure and associated technology capabilities for digital hospitals. Our aim is to fill this gap, as hospital administrators and clinicians need to know how and why to invest in information infrastructure to support health information technology that benefits patient safety and care.

Methods

Based on an operational framework for the Capability Maturity Model, devised specifically for health care, we applied information use characteristics to define eight information systems maturity levels and associated technology infrastructure capabilities. These levels are mapped to user experiences to create a linkage between technology infrastructure and experience outcomes. Subsequently, specific technology capabilities are deconstructed to identify the technology features required to meet each maturity level.

Results

The resulting assessment framework clearly defines 164 individual capabilities across the five technology domains and eight maturity levels for hospital infrastructure. These level-dependent capabilities characterize the ability of the hospital’s information infrastructure to support the business of digital hospitals including clinical and administrative requirements. Further, it allows the addition of a scoring calculation for each capability, domain, and the overall infrastructure, and it identifies critical requirements to meet each of the maturity levels.

Conclusions

This new Infrastructure Maturity Assessment framework will allow digital hospitals to assess the maturity of their infrastructure in terms of their digital transformation aligning to business outcomes and supporting the desired level of clinical and operational competency. It provides the ability to establish an international benchmark of hospital infrastructure performance, while identifying weaknesses in current infrastructure capability. Further, it provides a business case justification through increased functionality and a roadmap for subsequent digital transformation while moving from one maturity level to the next. As such, this framework will encourage and guide information-driven, digital transformation in health care.

A Dietary Assessment App for Hospitalized Patients at Nutritional Risk: Development and Evaluation of the MyFood App

Background

Disease-related malnutrition is a common challenge among hospitalized patients. There seems to be a lack of an effective system to follow-up nutritional monitoring and treatment of patients at nutritional risk after risk assessment. We identify a need for a more standardized system to prevent and treat disease-related malnutrition.

Objective

We aimed to develop a dietary assessment app for tablets for use in a hospital setting and to evaluate the app’s ability to measure individual intake of energy, protein, liquid, and food and beverage items among hospitalized patients for two days. We also aimed to measure patients’ experiences using the app.

Methods

We have developed the MyFood app, which consists of three modules: 1) collection of information about the patient, 2) dietary assessment function, and 3) evaluation of recorded intake compared to individual needs. We used observations from digital photography of the meals, combined with partial weighing of the meal components, as a reference method to evaluate the app’s dietary assessment system for two days. Differences in the intake estimations of energy, protein, liquid, and food and beverage items between MyFood and the photograph method were analyzed on both group and individual level.

Results

Thirty-two patients hospitalized at Oslo University Hospital were included in the study. The data collection period ran from March to May 2017. About half of the patients had ≥90% agreement between MyFood and the photograph method for energy, protein, and liquid intake on both recording days. Dinner was the meal with the lowest percent agreement between methods. MyFood overestimated patients’ intake of bread and cereals and underestimated fruit consumption. Agreement between methods increased from day 1 to day 2 for bread and cereals, spreads, egg, yogurt, soup, hot dishes, and desserts. Ninety percent of participants reported that MyFood was easy to use, and 97% found the app easy to navigate.

Conclusions

We developed the MyFood app as a tool to monitor dietary intake among hospitalized patients at nutritional risk. The recorded intake of energy, protein, and liquid using MyFood showed good agreement with the photograph method for the majority of participants. The app’s ability to estimate intake within food groups was good, except for bread and cereals which were overestimated and fruits which were underestimated. The app was well accepted among study participants and has the potential to be a dietary assessment tool for use among patients in clinical practice.