Search

BackgroundMalnutrition affects many worldwide, necessitating accurate and timely nutritional risk assessment. This study aims to develop and validate a machine learning model using facial feature recognition for predicting nutritional risk. This innovative approach seeks to offer a non-invasive, efficient method for early identification and intervention, ultimately improving health outcomes.MethodsWe gathered medical examination data and facial images from 949 patients across multiple hospitals to predict nutritional status. In this multicenter investigation, facial images underwent preprocessing via face alignment and cropping. Orbital fat pads were isolated using the U-net model, with the histogram of oriented gradient (HOG) method employed for feature extraction. Standardized HOG features were subjected to principal component analysis (PCA) for dimensionality reduction. A support vector machine (SVM) classification model was utilized for NRS-2002 detection. Our approach established a non-linear mapping between facial features and NRS-2002 nutritional risk scores, providing an innovative method for evaluating patient nutritional status.ResultsIn context of orbital fat pad area segmentation with U-net model, the averaged dice coefficient is 88.3%. Our experimental results show that the proposed method to predict NRS-2002 scores achieves an accuracy of 73.1%. We also grouped the samples by gender, age, and the location of the hospital where the data were collected to evaluate the classification accuracy in different subsets. The classification accuracy rate for the elderly group was 85%, while the non-elderly group exhibited a classification accuracy rate of 71.1%; Furthermore, the classification accuracy rate for males and females were 69.2 and 78.6%, respectively. Hospitals located in remote areas, such as Tibet and Yunnan, yielded a classification accuracy rate of 76.5% for collected patient samples, whereas hospitals in non-remote areas achieved a classification accuracy rate of 71.1%.ConclusionThe attained accuracy rate of 73.1% holds significant implications for the feasibility of the method. While not impeccable, this level of accuracy highlights the potential for further improvements. The development of this algorithm has the potential to revolutionize nutritional risk assessment by providing healthcare professionals and individuals with a non-invasive, cost-effective, and easily accessible tool.

Background and aimStroke-associated infection (SAI) is a common and serious complication in patients with IS. This study aimed to evaluate the impact of nutritional status at admission assessed on SAI, explore the predictive value of the Nutritional Risk Screening 2002 (NRS-2002 for SAI.MethodsThis study included patients with IS who were admitted to five major hospitals in Chengdu from January 2017 to February 2019. The nutritional status was assessed using the NRS-2002 tool. Logistic regression analysis was performed to explore the predictive value of NRS-2002 for SAI.ResultsA total of 594 patients with IS were included in this study; among them, 215 (36.20%) patients were at risk of malnutrition, and 216 (36.36%) patients developed SAI. The area under the curve of the NRS-2002 scores was smaller than A2DS2 (0.644 vs. 0.779), and NRS-2002 improved the predictive values of the A2DS2 score(Age, Atrial fibrillation, Dysphagia, Sex, Stroke Severity) for SAI (P < 0.001). Logistic regression analysis showed that patients with NRS-2002 score ≥ 3 had significantly higher risks of SAI (NRS-2002: odds ratios (OR) = 1.450, 95% confidence interval (CI): 1.184–1.692, P < 0.001).ConclusionNRS-2002 is a useful and simple tool for identifying the risk of SAI. Malnutrition is related to the development of SAI. Malnourished patients with stroke may benefit from further nutritional supplements and management.

BackgroundNutritional risk is associated with adverse clinical outcomes and is more prevalent among pulmonology patients than among patients in other departments. High-altitude environments can affect patients with chronic respiratory diseases, but evidence of the prevalence of nutritional risk among hospitalized patients with respiratory diseases in high-altitude areas is limited. This study aimed to investigate the nutritional risk and status of inpatients with different major respiratory diagnoses permanently living on the Tibetan Plateau (≥3,000 m above sea level).MethodsIn this cross-sectional study, we consecutively recruited inpatients admitted to the Department of Respiratory and Critical Care Medicine at the Tibet Autonomous Region People's Hospital of Lhasa between November 2020 and May 2021. We used the Nutrition Risk Screening (NRS) 2002 tool to assess nutritional risk among these patients. An NRS 2002 score ≥3 points indicates nutritional risk; a score ≥5 indicates high nutritional risk. According to NRS-2002 scores, patients were divided into three groups (NRS-2002 0–2, 3–4, and ≥5). The differences in age, sex, major respiratory diagnoses, comorbidities, body mass index, and laboratory findings among the groups were analyzed.ResultsA total of 289 eligible Tibetan patients were enrolled in the study, and 46.1% (133/246) of them were at nutritional risk (NRS-2002 score ≥3). Twenty-one (7.3%) patients were at high nutritional risk (NRS-2002 score ≥5). The proportions of patients at nutritional risk were relatively high among patients with lung cancer (58.8%), interstitial lung disease (58.3%), pulmonary embolism (52.9%), and tuberculosis (50.0%). Laboratory findings showed that patients with NRS-2002 scores of 3–4 and ≥5 had lower red blood cell counts, serum albumin and hemoglobin levels, and higher C-reactive protein (CRP) levels than those with NRS-2002 scores < 3.ConclusionThe prevalence of nutritional risk was high among pulmonology department inpatients permanently living on the Tibetan Plateau. Patients with lung cancer, interstitial lung disease, pulmonary embolism or tuberculosis were more likely to have nutritional risk than patients with other diagnoses. The nutritional risk of inpatients in the respiratory department in the plateau area should not be ignored, and patients at high nutritional risk should receive timely intervention.

Background: Malnutrition affects many worldwide, necessitating accurate and timely nutritional risk assessment. This study aims to develop and validate a machine learning model using facial feature recognition for predicting nutritional risk. This innovative approach seeks to offer a non-invasive, efficient method for early identification and intervention, ultimately improving health outcomes., Methods: We gathered medical examination data and facial images from 949 patients across multiple hospitals to predict nutritional status. In this multicenter investigation, facial images underwent preprocessing via face alignment and cropping. Orbital fat pads were isolated using the U-net model, with the histogram of oriented gradient (HOG) method employed for feature extraction. Standardized HOG features were subjected to principal component analysis (PCA) for dimensionality reduction. A support vector machine (SVM) classification model was utilized for NRS-2002 detection. Our approach established a non-linear mapping between facial features and NRS-2002 nutritional risk scores, providing an innovative method for evaluating patient nutritional status., Results: In context of orbital fat pad area segmentation with U-net model, the averaged dice coefficient is 88.3%. Our experimental results show that the proposed method to predict NRS-2002 scores achieves an accuracy of 73.1%. We also grouped the samples by gender, age, and the location of the hospital where the data were collected to evaluate the classification accuracy in different subsets. The classification accuracy rate for the elderly group was 85%, while the non-elderly group exhibited a classification accuracy rate of 71.1%; Furthermore, the classification accuracy rate for males and females were 69.2 and 78.6%, respectively. Hospitals located in remote areas, such as Tibet and Yunnan, yielded a classification accuracy rate of 76.5% for collected patient samples, whereas hospitals in non-remote areas achieved a classification accuracy rate of 71.1%., Conclusion: The attained accuracy rate of 73.1% holds significant implications for the feasibility of the method. While not impeccable, this level of accuracy highlights the potential for further improvements. The development of this algorithm has the potential to revolutionize nutritional risk assessment by providing healthcare professionals and individuals with a non-invasive, cost-effective, and easily accessible tool., Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2023 Wang, He and Long.)

Background and Aim: Stroke-associated infection (SAI) is a common and serious complication in patients with IS. This study aimed to evaluate the impact of nutritional status at admission assessed on SAI, explore the predictive value of the Nutritional Risk Screening 2002 (NRS-2002 for SAI., Methods: This study included patients with IS who were admitted to five major hospitals in Chengdu from January 2017 to February 2019. The nutritional status was assessed using the NRS-2002 tool. Logistic regression analysis was performed to explore the predictive value of NRS-2002 for SAI., Results: A total of 594 patients with IS were included in this study; among them, 215 (36.20%) patients were at risk of malnutrition, and 216 (36.36%) patients developed SAI. The area under the curve of the NRS-2002 scores was smaller than A2DS2 (0.644 vs. 0.779), and NRS-2002 improved the predictive values of the A 2 DS 2 score(Age, Atrial fibrillation, Dysphagia, Sex, Stroke Severity) for SAI ( P < 0.001). Logistic regression analysis showed that patients with NRS-2002 score ≥ 3 had significantly higher risks of SAI (NRS-2002: odds ratios (OR) = 1.450, 95% confidence interval (CI): 1.184-1.692, P < 0.001)., Conclusion: NRS-2002 is a useful and simple tool for identifying the risk of SAI. Malnutrition is related to the development of SAI. Malnourished patients with stroke may benefit from further nutritional supplements and management., Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2022 Chen, Li, Liu, Zhu, Jia and Gao.)

Background: Nutritional risk is associated with adverse clinical outcomes and is more prevalent among pulmonology patients than among patients in other departments. High-altitude environments can affect patients with chronic respiratory diseases, but evidence of the prevalence of nutritional risk among hospitalized patients with respiratory diseases in high-altitude areas is limited. This study aimed to investigate the nutritional risk and status of inpatients with different major respiratory diagnoses permanently living on the Tibetan Plateau (≥3,000 m above sea level)., Methods: In this cross-sectional study, we consecutively recruited inpatients admitted to the Department of Respiratory and Critical Care Medicine at the Tibet Autonomous Region People's Hospital of Lhasa between November 2020 and May 2021. We used the Nutrition Risk Screening (NRS) 2002 tool to assess nutritional risk among these patients. An NRS 2002 score ≥3 points indicates nutritional risk; a score ≥5 indicates high nutritional risk. According to NRS-2002 scores, patients were divided into three groups (NRS-2002 0-2, 3-4, and ≥5). The differences in age, sex, major respiratory diagnoses, comorbidities, body mass index, and laboratory findings among the groups were analyzed., Results: A total of 289 eligible Tibetan patients were enrolled in the study, and 46.1% (133/246) of them were at nutritional risk (NRS-2002 score ≥3). Twenty-one (7.3%) patients were at high nutritional risk (NRS-2002 score ≥5). The proportions of patients at nutritional risk were relatively high among patients with lung cancer (58.8%), interstitial lung disease (58.3%), pulmonary embolism (52.9%), and tuberculosis (50.0%). Laboratory findings showed that patients with NRS-2002 scores of 3-4 and ≥5 had lower red blood cell counts, serum albumin and hemoglobin levels, and higher C-reactive protein (CRP) levels than those with NRS-2002 scores < 3., Conclusion: The prevalence of nutritional risk was high among pulmonology department inpatients permanently living on the Tibetan Plateau. Patients with lung cancer, interstitial lung disease, pulmonary embolism or tuberculosis were more likely to have nutritional risk than patients with other diagnoses. The nutritional risk of inpatients in the respiratory department in the plateau area should not be ignored, and patients at high nutritional risk should receive timely intervention., Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2022 Quncuo, Liang, Li, She, Cuo, Qiongda, ChuTso and Sun.)