1
|
Koseoglu M, Ramachandran RA, Ozdemir H, Ariani MD, Bayindir F, Sukotjo C. Automated facial landmark measurement using machine learning: A feasibility study. J Prosthet Dent 2024:S0022-3913(24)00282-8. [PMID: 38670909 DOI: 10.1016/j.prosdent.2024.04.007] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/03/2024] [Revised: 04/09/2024] [Accepted: 04/10/2024] [Indexed: 04/28/2024]
Abstract
STATEMENT OF PROBLEM Information regarding facial landmark measurement using machine learning (ML) techniques in prosthodontics is lacking. PURPOSE The objective of this study was to evaluate and compare the reliability, validity, and accuracy of facial anthropological measurements using both manual and ML landmark detection techniques. MATERIAL AND METHODS Two-dimensional (2D) frontal full-face photographs of 50 men and 50 women were made. The interpupillary width (IPW), interlateral canthus width (LCW), intermedial canthus width (MCW), interalar width (IAW), and intercommissural width (ICW) were measured on 2D digital images using manual and ML methods. The automated measurements were recorded using a programming language (Python), and a convolutional neural network (CNN) model was trained to detect human facial landmarks. The obtained data from the manual and ML methods were analyzed using intraclass correlation coefficients (ICCs), the paired sample t test, Bland-Altman plots, and the Pearson correlation analysis (α=.05). RESULTS Intrarater and interrater reliability values were greater than 0.90, indicating excellent reliability. The mean difference between the manual and ML measurements of IPW, MCW, IAW, and ICW was 0.02 mm, while it was 0.01 mm for LCW. No statistically significant differences were found between the measurements obtained by the manual and ML methods (P>.05). Highly significant positive correlations (P<.001) were obtained between the results of the manual and ML methods: (r=0.996[IPW], r=0.977[LCW], r=0.944[MCW], r=0.965[IAW], and r=0.997[ICW]). CONCLUSIONS In the field of prosthodontics, the use of ML methods provides a reliable alternative to manual digital techniques for carrying out facial anthropometric measurements.
Collapse
Affiliation(s)
- Merve Koseoglu
- Associate Professor, Department of Prosthodontics, Faculty of Dentistry, University of Sakarya, Sakarya, Turkey and Ph.D student, Department of Prosthodontics, Faculty of Dentistry, University of Ataturk, Erzurum, Turkey
| | - Remya Ampadi Ramachandran
- Fellow (Postdoc), 1DATA Consortium, Computational Comparative Medicine, Department of Mathematics, K- State Olathe, Olathe, Kansas
| | - Hatice Ozdemir
- Associate Professor, Department of Prosthodontics, Faculty of Dentistry, University of Ataturk, Erzurum, Turkey
| | - Maretaningtias Dwi Ariani
- Lecturer, Department of Prosthodontic, Faculty of Dental Medicine, Universitas Airlangga, Surabaya, Indonesia
| | - Funda Bayindir
- Professor, Department of Prosthodontics, Faculty of Dentistry, University of Ataturk, Erzurum, Turkey
| | - Cortino Sukotjo
- Professor, Department of Restorative Dentistry, College of Dentistry, University of Illinois, Chicago, Ill; and Adjunct Professor, Department of Prosthodontic, Faculty of Dental Medicine, Universitas Airlangga, Surabaya, Indonesia.
| |
Collapse
|
2
|
Lafave LMZ, Hayek J, Lafave MR. Update and validation of the Canadian Behavior, Attitude and Nutrition Knowledge Survey (C-BANKS 2.0). Front Public Health 2023; 11:1261146. [PMID: 37860797 PMCID: PMC10584322 DOI: 10.3389/fpubh.2023.1261146] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/19/2023] [Accepted: 09/19/2023] [Indexed: 10/21/2023] Open
Abstract
Aim Understanding knowledge, attitudes and behaviors related to nutrition is crucial in developing effective intervention strategies to promote healthy eating habits. This study revised and updated the Canadian Behavior, Attitude and Nutrition Knowledge Survey (C-BANKS) to align with the current Canada's Food Guide and dietary guidance and report on its reliability and validity with a new population. Method Data from 167 early childhood educators were recruited to test the revised C-BANKS' reliability and validity. Reliability, as measured by internal consistency, was assessed using Cronbach's alpha, while concurrent validity was determined by correlating the C-BANKS 2.0 scores with the CHEERS (Creating Healthy Eating and Active Environments Survey) and Mindful Eating Questionnaire (MEQ). Responsiveness was assessed by comparing a baseline C-BANKS 2.0 score to a post-test score after completing an online healthy eating and physical activity educational intervention. Results The adapted C-BANKS 2.0 questionnaire demonstrated good internal consistency (Cronbach's alpha >0.70) and construct validity with related measures CHEERS and MEQ (p < 0.05). The C-BANKS 2.0 demonstrated strong responsiveness. Specifically, C-BANKS 2.0 scores increased after the nutrition education intervention (p < 0.001). Additionally, there were no signs of floor or ceiling effects. Conclusion The adapted C-BANKS 2.0 demonstrated satisfactory internal consistency, construct validity, and responsiveness to measure of nutrition knowledge, attitudes, and behaviors in an early childhood educator population. The revised C-BANKS 2.0 provides insight into the key factors that influence dietary habits thereby informing the design and evaluation of effective nutrition community intervention programs.
Collapse
Affiliation(s)
- Lynne M. Z. Lafave
- Department of Health and Physical Education, Mount Royal University, Calgary, AB, Canada
| | | | | |
Collapse
|
3
|
Lafave LMZ. Is the online 'creating healthy eating and active environments survey' (CHEERS) tool reliable for early childhood educators in Alberta, Canada: a randomized crossover trial. Arch Public Health 2023; 81:22. [PMID: 36782334 PMCID: PMC9926852 DOI: 10.1186/s13690-023-01036-z] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/15/2022] [Accepted: 02/06/2023] [Indexed: 02/15/2023] Open
Abstract
BACKGROUND The creating healthy eating and active environments survey (CHEERS) is an audit tool used to assess the nutrition and physical activity environment in early childhood education and care (ECEC) centres. Availability of the tool has been limited to paper-based versions. Digital health initiatives offer improved reach and immediacy of support for community-based clients through novel technology products. In order to provide increased access to the CHEERS tool, an online version was developed. The objective of this study was to assess the reliability of an online version of CHEERS. METHODS Utilizing a randomized crossover design, ECEC educators completed either a paper-based or online-based survey and then the opposite mode with a two to three-week interval. The intraclass correlation coefficient (ICC, with 95% confidence interval) was used to determine the reliability between test and retest. Absolute index of reliability in the original measurement was assessed through the standard error of measurement (SEM = SD × √1-ICC). The smallest amount of change not due to inherent variation was assessed by determining minimal detectable change at the 95% confidence level (MDC95 = SEM × 1.96 ×√2; MDC95% = MDC95/mean ×100). RESULTS Test-retest reliability was good to excellent for the online-based CHEERS total score (ICC = 0.86) and for each of the four subscales: food served (ICC = 0.82), healthy eating environment (ICC = 0.76), program planning (ICC = 0.76), and physical activity environment (ICC = 0.79). The SEM, MDC95, and MDC95% for the CHEERS overall score were 0.79, 2.19, and 9.6%, respectively. CONCLUSIONS The results of this study demonstrate that the online-based and paper-based versions of the CHEERS audit tool share comparable accuracy. The CHEERS tool can be reliably implemented in an online environment and this provides users an alternative means to complete the centre-based health assessment. The advantage of the online-based version includes user accessibility and the potential to develop a feedback response for participants using digitally collected data.
Collapse
Affiliation(s)
- Lynne M. Z. Lafave
- grid.411852.b0000 0000 9943 9777Department of Health and Physical Education, Mount Royal University, Calgary, AB T3E 6K6 Canada
| |
Collapse
|
4
|
Inter-Rater and Intra-Rater Reliability of the INSPECT (Interactive Nutrition Specific Physical Exam Competency Tool) Measured in Multi-Site Acute Care Settings. Healthcare (Basel) 2022; 10:healthcare10020212. [PMID: 35206827 PMCID: PMC8872305 DOI: 10.3390/healthcare10020212] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/14/2021] [Revised: 01/17/2022] [Accepted: 01/19/2022] [Indexed: 02/05/2023] Open
Abstract
Even as new medical modalities, diagnostics, and technologies are rapidly changing healthcare, providing patients with safe, high-quality care remains the central focus. To provide safe patient care, healthcare providers are obligated to demonstrate and maintain the necessary competence. As more healthcare disciplines move toward a competency-based education model, it is essential to extend the competence verification from the academic educational level to the patient’s bedside. The nutrition-focused physical exam (NFPE) is a competency recently adopted by registered dietitian nutritionists (RDNs) for assessing patients’ nutritional status. Being a newly acquired skill, validated tools are required to measure NFPE competence during routine clinical practice. The Interactive Nutrition Specific Physical Exam Competency Tool (INSPECT) is a new tool developed specifically to observe and measure RDNs’ NFPE competence in clinical settings. The INSPECT was designed and validated for content using expert RDNs’ input in the first and second phases of the study. This current study aimed to assess the reliability of the INSPECT through multi-site observations by clinical supervisors evaluating RDNs’ NFPE competency during patient assessment. The INSPECT exhibited good inter-rater reliability (ICC = 0.78 for the first assessment and ICC = 0.68 for the second assessment), moderate to strong intra-rater reliability for 37 of 41 items (Spearman rho = 0.54 to 1.0), and excellent internal consistency (Cronbach’s α = 0.86 for the first assessment and α = 0.92 for the second assessment). In total, 10 out of the 11 INSPECT subsets showed good to excellent internal consistency (α ranging from 0.70 to 0.98). The results demonstrate that the INSPECT is a reliable tool, is stable over time, and has good agreement and excellent consistency between raters. The INSPECT can be a valuable tool to measure, promote and maintain RDNs’ NFPE competence in authentic acute care settings.
Collapse
|
5
|
Lafave LMZ, Webster AD, McConnell C, Van Wyk N, Lafave MR. The Impact of COVID-19 on Eating Environments and Activity in Early Childhood Education and Care in Alberta, Canada: A Cross-Sectional Study. Nutrients 2021; 13:4247. [PMID: 34959799 PMCID: PMC8706784 DOI: 10.3390/nu13124247] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/16/2021] [Revised: 11/23/2021] [Accepted: 11/25/2021] [Indexed: 11/24/2022] Open
Abstract
Early childhood education and care (ECEC) environments influence children's early development and habits that track across a lifespan. The purpose of this study was to explore the impact of COVID-19 government-mandated guidelines on physical activity (PA) and eating environments in ECEC settings. This cross-sectional study involved the recruitment of 19 ECEC centers pre-COVID (2019) and 15 ECEC centers during COVID (2020) in Alberta, Canada (n = 34 ECEC centers; n = 83 educators; n = 361 preschoolers). Educators completed the CHEERS (Creating Healthy Eating and activity Environments Survey) and MEQ (Mindful Eating Questionnaire) self-audit tools while GT3X+ ActiGraph accelerometers measured preschooler PA. The CHEERS healthy eating environment subscale was greater during COVID-19 (5.97 ± 0.52; 5.80 ± 0.62; p = 0.02) and the overall score positively correlated with the MEQ score (r = 0.20; p = 0.002). Preschoolers exhibited greater hourly step counts (800 ± 189; 649 ± 185), moderate-to-vigorous PA (MVPA) (9.3 ± 3.0 min/h; 7.9 ± 3.2 min/h) and lower sedentary times (42.4 ± 3.9 min/h; 44.1 ± 4.9 min/h) during COVID-19 compared to pre-COVID, respectively (p < 0.05). These findings suggest the eating environment and indices of child physical activity were better in 2020, which could possibly be attributed to a change in government-mandated COVID-19 guideline policy.
Collapse
Affiliation(s)
- Lynne M. Z. Lafave
- Department of Health and Physical Education, Mount Royal University, Calgary, AB T3E 6K6, Canada; (A.D.W.); (C.M.); (N.V.W.); (M.R.L.)
| | | | | | | | | |
Collapse
|
6
|
Zechariah S, Waller JL, De Leo G, Stallings J, Gess AJ, Lehman L. Content and Face Validation of a Novel, Interactive Nutrition Specific Physical Exam Competency Tool (INSPECT) to Evaluate Registered Dietitians' Competence: A Delphi Consensus from the United States. Healthcare (Basel) 2021; 9:healthcare9091225. [PMID: 34574998 PMCID: PMC8472113 DOI: 10.3390/healthcare9091225] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/21/2021] [Revised: 09/13/2021] [Accepted: 09/14/2021] [Indexed: 11/16/2022] Open
Abstract
The nutrition-focused physical examination (NFPE) is an integral component of nutrition assessment performed by registered dietitian nutritionists (RDNs) to determine signs of malnutrition and other nutrition-related complications. Increased use of this essential skill among RDNs and the transformation of dietetics education to a competency-based model in the near future calls for appropriately validated tools to measure RDNs' NFPE competence. To fill the need for a validated competency tool, this study developed an Interactive Nutrition-Specific Physical Exam Competency Tool (INSPECT) utilizing the initial 70 items identified in the first phase of the study. The second phase of this study aimed to test the preliminary version of the INSPECT for content and face validity. An expert panel of 17 members provided consensus recommendations through the Delphi process. Internal consistency of the consensus was measured with Cronbach's alpha (α) and α of ≥0.70 was defined as acceptable a priori. Inter-rater agreement among the expert panel was determined using the intraclass correlation coefficient (ICC) and an a priori ICC of 0.75 to 0.9 was established as good and >0.9 as excellent agreement. The results showed acceptable face validity (α = 0.71) and excellent content validity for the INSPECT, with an internal consistency of α = 0.97 in the first round and α = 0.96 in the second round. The inter-rater agreement was also excellent with ICC = 0.95 for each of the Delphi rounds. A total of 52 items were retained from the preliminary version of the INSPECT. Open feedback from the experts allowed for the consolidation of 11 similar items for better scoring and evaluation and thus, a total of 41 items were included in the final version of the INSPECT. The final version of the INSPECT is currently being studied in real-life, multi-site clinical settings among practicing RDNs to examine construct validity, reliability, and item-level psychometric properties. Ultimately, the validated INSPECT will be available for the competency evaluation of RDNs practicing in clinical settings.
Collapse
Affiliation(s)
- Sunitha Zechariah
- College of Allied Health Sciences, Augusta University, Augusta, GA 30912, USA; (G.D.L.); (J.S.)
- Correspondence:
| | | | - Gianluca De Leo
- College of Allied Health Sciences, Augusta University, Augusta, GA 30912, USA; (G.D.L.); (J.S.)
| | - Judith Stallings
- College of Allied Health Sciences, Augusta University, Augusta, GA 30912, USA; (G.D.L.); (J.S.)
| | - Ashley J. Gess
- College of Education, Augusta University, Augusta, GA 30912, USA;
| | - Leigh Lehman
- School of Occupational Therapy, Brenau University, Gainesville, GA 30501, USA;
| |
Collapse
|
7
|
Babashahi M, Omidvar N, Joulaei H, Zargaraan A, Zayeri F, Veisi E, Doustmohammadian A, Kelishadi R. Scrutinize of healthy school canteen policy in Iran's primary schools: a mixed method study. BMC Public Health 2021; 21:1566. [PMID: 34407797 PMCID: PMC8375065 DOI: 10.1186/s12889-021-11587-x] [Citation(s) in RCA: 6] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/03/2020] [Accepted: 08/02/2021] [Indexed: 11/19/2022] Open
Abstract
BACKGROUND Schools provide an opportunity for developing strategies to create healthy food environments for children. The present study aimed to analyze the Healthy School Canteen (HSC) policy and identify challenges of its implementation to improve the school food environment in Iran. METHODS This mixed method study included two qualitative and quantitative phases. In the qualitative phase, triangulation approach was applied by using semi-structured interviews with key informants, documents review and direct observation. Data content analysis was conducted through policy analysis triangle framework. In the quantitative phase, food items available in 64 canteens of primary schools of Tehran province were gathered. The food's nutrient data were evaluated using their nutrition facts label. The number and proportion of foods that met the criteria based on Iran's HSC guideline and the World Health Organization nutrient profile model for the Eastern Mediterranean Region (WHO-EMR) were determined. RESULTS The main contextual factors that affected adoption of HSC policy included health (nutritional transition, high prevalence of non-communicable diseases and unhealthy food environment in and around the schools), political (upstream supportive policies and joint memorandums about health children between the Ministry of Health and Medical Education and Ministry of Education), structural (the lack of unified stewardship, inadequate human resource capacity, poor inter-sectional cooperation), economic (school financial problems, poor fiscal supportive of food policies), and socio-cultural (mothers working outside the home, the role of children's peer group, low nutrition knowledge of school principals) factors. Assessment of the school canteens showed that a large proportion of available foods did not comply with the national guidelines (54.7 ± 2.54%) and WHO-EMR model (85.6 ± 2.34%). The main reasons identified for incomplete implementation of the policy were inadequate physical and economic infrastructure to set up standard school canteens, lack of scientific criteria for food categorization, poor monitoring, high price of healthy foods, and conflict of interest among the actors. CONCLUSION The majority of foods and beverages available in the school canteens did not comply with national and regional standards. Iran HSC policy needs to be improved by using an evidence-based approach and active interaction between all key actors.
Collapse
Affiliation(s)
- Mina Babashahi
- Department of Community Nutrition, National Nutrition and Food Technology Research Institute, Faculty of Nutrition Sciences and Food Technology, Shahid Beheshti University of Medical Sciences, Tehran, Iran
| | - Nasrin Omidvar
- Department of Community Nutrition, National Nutrition and Food Technology Research Institute, Faculty of Nutrition Sciences and Food Technology, Shahid Beheshti University of Medical Sciences, Tehran, Iran.
| | - Hassan Joulaei
- Health Policy Research Center, Institute of Health, Shiraz University of Medical Sciences, Shiraz, Iran
| | - Azizollaah Zargaraan
- Department of Food and Nutrition Policy and Planning Research, National Nutrition and Food Technology Research Institute, Faculty of Nutrition Sciences and Food Technology, Shahid Beheshti University of Medical Sciences, Tehran, Iran
| | - Farid Zayeri
- Proteomics Research Center and Department of Biostatistics, Faculty of Allied Medical Sciences, Shahid Beheshti University of Medical Sciences, Tehran, Iran
| | - Elnaz Veisi
- Department of Community Nutrition, National Nutrition and Food Technology Research Institute, Faculty of Nutrition Sciences and Food Technology, Shahid Beheshti University of Medical Sciences, Tehran, Iran
| | - Azam Doustmohammadian
- Gastrointestinal and Liver Diseases Research Center, Iran University of Medical Sciences, Tehran, Iran
| | - Roya Kelishadi
- Department of Pediatrics, Child Growth and Development Research Center, Research Institute for Primordial Prevention of Non-Communicable Disease, Isfahan University of Medical Sciences, Isfahan, Iran
| |
Collapse
|
8
|
Ng WM, Cheung K. A feasibility study of a WhatsApp-delivered Transtheoretical Model-based intervention to promote healthy eating habits for firefighters in Hong Kong: a cluster randomized controlled trial. Trials 2020; 21:518. [PMID: 32532313 PMCID: PMC7291567 DOI: 10.1186/s13063-020-04258-6] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/31/2019] [Accepted: 03/15/2020] [Indexed: 11/10/2022] Open
Abstract
BACKGROUND Firefighters' health is often affected by a high prevalence of obesity and cardiovascular diseases, which are common risk factors for sudden cardiac death. The aim of this study is to investigate the feasibility of enhancing healthy eating habits in firefighters through an education programme. METHODS This will be a cluster randomized control trial study. The participants will be assigned randomly into either control (health promotion pamphlet) or intervention (health promotion pamphlet and education materials through WhatsApp) groups. Changes in healthy eating habits will be assessed by a self-administered questionnaire and anthropometric measurements at three different time points. DISCUSSION More education is required in order to improve firefighters' eating habits. TRIAL REGISTRATION ISRCTN registry identifier: Registered on 8 April 2019 ISRCTN95472464.
Collapse
Affiliation(s)
- Wing Man Ng
- Division of Science, Engineering and Health Studies, College of Professional and Continuing Education, The Hong Kong Polytechnic University, Hung Hom, Hong Kong.
| | - Kin Cheung
- School of Nursing, The Hong Kong Polytechnic University, Hung Hom, Hong Kong
| |
Collapse
|