1
|
Luna TB, Bello JLG, Carbonell AG, Montoya ADLCR, Lafargue AL, Ciria HMC, Zulueta YA. Integrating classification and regression learners with bioimpedance methods for estimating weight status in infants and juveniles from the southern Cuba region. BMC Pediatr 2024; 24:370. [PMID: 38811864 PMCID: PMC11134843 DOI: 10.1186/s12887-024-04841-9] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 03/21/2024] [Accepted: 05/17/2024] [Indexed: 05/31/2024] Open
Abstract
OBJECTIVE The search for other indicators to assess the weight and nutritional status of individuals is important as it may provide more accurate information and assist in personalized medicine. This work is aimed to develop a machine learning predictions of weigh status derived from bioimpedance measurements and other physical parameters of healthy younger volunteers from Southern Cuba Region. METHODS A pilot random study at the Pediatrics Hospital was conducted. The volunteers were selected between 2002 and 2008, ranging in age between 2 and 18 years old. In total, 776 female and male volunteers are studied. Along the age and sex in the cohort, volunteers with class I obesity, overweight, underweight and with normal weight are considered. The bioimpedance parameters are obtained by measuring standard tetrapolar whole-body configuration. The bioimpedance analyser is used, collecting fundamental bioelectrical and other parameters of interest. A classification model are performed, followed by a prediction of the body mass index. RESULTS The results derived from the classification leaner reveal that the size, body density, phase angle, body mass index, fat-free mass, total body water volume according to Kotler, body surface area, extracellular water according to Kotler and sex largely govern the weight status of this population. In particular, the regression model shows that other bioparameters derived from impedance measurements can be associated with weight status estimation with high accuracy. CONCLUSION The classification and regression predictive models developed in this work are of the great importance to assist the diagnosis of weigh status with high accuracy. These models can be used for prompt weight status evaluation of younger individuals at the Pediatrics Hospital in Santiago de Cuba, Cuba.
Collapse
Affiliation(s)
- Taira Batista Luna
- Autonomous University of Santo Domingo (UASD), UASD Nagua Center, Nagua, Dominican Republic.
| | - Jose Luis García Bello
- Autonomous University of Santo Domingo (UASD), San Francisco de Macorís Campus, Santo Domingo, Dominican Republic
| | - Agustín Garzón Carbonell
- National Center for Applied Electromagnetism (CNEA), Universidad de Oriente CP 90500, Santiago de Cuba, Cuba
| | | | - Alcibíades Lara Lafargue
- National Center for Applied Electromagnetism (CNEA), Universidad de Oriente CP 90500, Santiago de Cuba, Cuba
| | - Héctor Manuel Camué Ciria
- National Center for Applied Electromagnetism (CNEA), Universidad de Oriente CP 90500, Santiago de Cuba, Cuba
| | - Yohandys A Zulueta
- Departamento de Física, Facultad de Ciencias Naturales y Exactas, Universidad de Oriente, Santiago de Cuba, 90500, CP, Cuba.
| |
Collapse
|
2
|
Luna TB, Bello JLG, Carbonell AG, Montoya ADLCR, Lafargue AL, Ciria HMC, Zulueta YA. The role of various physiological and bioelectrical parameters for estimating the weight status in infants and juveniles cohort from the Southern Cuba region: a machine learning study. BMC Pediatr 2024; 24:313. [PMID: 38711132 DOI: 10.1186/s12887-024-04789-w] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 02/18/2024] [Accepted: 04/24/2024] [Indexed: 05/08/2024] Open
Abstract
OBJECTIVE The search for other indicators to assess the weight status of individuals is important as it may provide more accurate information and assist in personalized medicine.This work is aimed to develop a machine learning predictions of weigh status derived from bioimpedance measurements and other physical parameters of healthy infant juvenile cohort from the Southern Cuba Region, Santiago de Cuba. METHODS The volunteers were selected between 2002 and 2008, ranging in age between 2 and 18 years old. In total, 393 female and male infant and juvenile individuals are studied. The bioimpedance parameters are obtained by measuring standard tetrapolar whole-body configuration. A classification model are performed, followed by a prediction of other bioparameters influencing the weight status. RESULTS The results obtained from the classification model indicate that fat-free mass, reactance, and corrected resistance primarily influence the weight status of the studied population. Specifically, the regression model demonstrates that other bioparameters derived from impedance measurements can be highly accurate in estimating weight status. CONCLUSION The classification and regression predictive models developed in this work are of the great importance for accessing to the weigh status with high accuracy of younger individuals at the Oncological Hospital in Santiago de Cuba, Cuba.
Collapse
Affiliation(s)
- Taira Batista Luna
- Autonomous University of Santo Domingo (UASD), UASD Nagua Center, Santo Domingo, Dominican Republic.
| | - Jose Luis García Bello
- Autonomous University of Santo Domingo (UASD), San Francisco de Macorís Campus, Santo Domingo, Dominican Republic
| | - Agustín Garzón Carbonell
- National Center for Applied Electromagnetism (CNEA), Universidad de Oriente CP 90500, Santiago de Cuba, Cuba
| | | | - Alcibíades Lara Lafargue
- National Center for Applied Electromagnetism (CNEA), Universidad de Oriente CP 90500, Santiago de Cuba, Cuba
| | - Héctor Manuel Camué Ciria
- National Center for Applied Electromagnetism (CNEA), Universidad de Oriente CP 90500, Santiago de Cuba, Cuba
| | - Yohandys A Zulueta
- Departamento de Física, Facultad de Ciencias Naturales y Exactas, Universidad de Oriente, Santiago de Cuba, CP 90500, CP, Cuba.
| |
Collapse
|
3
|
Pedro da Costa Pereira J, Santana Costa JH, Gomes de Miranda BL, de Sousa Rebouças A, Denise de Lima Bezerra A, Gomes Dantas Lopes MM, Trussardi Fayh AP. Prognostic value of overhydration and bioelectrical impedance vector on short- and long-term outcomes in hospitalized patients with cancer. Clin Nutr 2024; 43:756-764. [PMID: 38335800 DOI: 10.1016/j.clnu.2024.01.025] [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: 11/28/2023] [Revised: 01/03/2024] [Accepted: 01/19/2024] [Indexed: 02/12/2024]
Abstract
BACKGROUND & AIMS Water, an essential component of body composition, appears to be a significant predictor of adverse outcomes in clinical populations, despite being frequently underexplored. Bioelectrical impedance analysis (BIA) and vector analysis (BIVA) are easy and cost-effective bedside tools for estimating body composition, particularly water content. Therefore, our study aimed to assess the impact of hydration and fluid status using both BIA and BIVA on outcomes in hospitalized patients with cancer. METHODS A prospective cohort study involving hospitalized individuals with cancer was conducted. Total body water (TBW) was estimated using BIA. Extracellular-water/TBW (ECW/TBW) and ECW/intracellular-water (ECW/ICW) ratios were calculated. BIVA ellipses vectors were constructed to enhance our analysis of hydration status. Participants were followed during their hospital stay and up to six months after discharge to assess outcomes, including in-hospital mortality, 6-month non-elective rehospitalization, and 6-month mortality. RESULTS TBW, ECW/TBW, ECW/ICW ratios, and BIVA plots were not associated with non-elective rehospitalization during the follow-up period. However, TBW and an elevated ECW/ICW ratio were independent predictors of in-hospital mortality [hazard ratio (HR): 1.07 (1.01; 1.13) p = 0.020; HR: 4.23 (1.69; 10.58) p = 0.002]. Elevated ratios ECW/TBW and ECW/ICW were independent predictors of 6-month mortality [HR: 1.87 (1.10; 3.21) p = 0.022; HR: 2.49 (1.37; 4.51) p = 0.003]. BIVA vectors for in-hospital and 6-month mortality shifted significantly to the right, leading to cachexia and overhydration quadrants (p < 0.05). CONCLUSION Abnormalities related to overhydration were important predictors of short- and long-term mortality in hospitalized patients with cancer.
Collapse
Affiliation(s)
- Jarson Pedro da Costa Pereira
- Postgraduate Program in Nutrition and Public Health, Department of Nutrition, Federal University of Pernambuco, Recife, PE, Brazil
| | | | - Bruna Luisa Gomes de Miranda
- Postgraduate Program in Nutrition, Health Science Center, Federal University of Rio Grande do Norte, Natal, RN, Brazil
| | - Amanda de Sousa Rebouças
- Postgraduate Program in Health Science, Health Science Center, Federal University of Rio Grande do Norte, Natal, RN, Brazil
| | - Agnes Denise de Lima Bezerra
- Postgraduate Program in Health Science, Health Science Center, Federal University of Rio Grande do Norte, Natal, RN, Brazil
| | - Márcia Marília Gomes Dantas Lopes
- Department of Nutrition, Federal University of Rio Grande do Norte, Natal, RN, Brazil; Postgraduate Program in Applied Sciences to Women's Health, Health Sciences Center, Federal University of Rio Grande do Norte, Natal, Brazil
| | - Ana Paula Trussardi Fayh
- Department of Nutrition, Federal University of Rio Grande do Norte, Natal, RN, Brazil; Postgraduate Program in Nutrition, Health Science Center, Federal University of Rio Grande do Norte, Natal, RN, Brazil; Postgraduate Program in Health Science, Health Science Center, Federal University of Rio Grande do Norte, Natal, RN, Brazil; PesqClin Lab, Onofre Lopes University Hospital, Brazilian Company of Hospital Services (EBSERH), Federal University of Rio Grande do Norte, Natal, Brazil.
| |
Collapse
|
4
|
Sasmita BR, Zhao Y, Gong M, Luo S, Huang B. Edema Index Predicts Mortality in Patients with Chronic Heart Failure: A Prospective, Observational Study. Glob Heart 2024; 19:5. [PMID: 38250704 PMCID: PMC10798169 DOI: 10.5334/gh.1287] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/15/2023] [Accepted: 12/18/2023] [Indexed: 01/23/2024] Open
Abstract
Introduction Chronic fluid accumulation or congestion is considered an important pathophysiologic mechanism in heart failure, leading to cardinal symptoms such as dyspnea, pulmonary congestion, and pitting edema. Edema index (EI) recently emerged as a surrogate for extracellular volume status and has been proven to be able to reflect one's congestion status. In this study, we aimed to evaluate the prognostic value of EI in patients with chronic heart failure (CHF). Methods A total of 401 consecutive patients with CHF between August 2019 and October 2021 were prospectively enrolled. EI was obtained by InBody S10. The primary endpoint was long-term all-cause and cardiovascular mortality. Results Patients with high EI (>0.397) tended to be older, presented with atrial fibrillation, have higher N-terminal brain natriuretic peptide, and have higher creatinine (all p < 0.05). During a median follow-up of 1200 days, the all-cause and cardiovascular mortality rate was significantly higher in the high EI group compared to the low EI group (all-cause mortality rate 43.8% vs. 30.3%, p < 0.001, and cardiovascular mortality rate 17.5% vs. 13.0%, p < 0.001, respectively). In the multivariate Cox proportional hazard analysis, EI > 0.397 was an independent predictor for both all-cause mortality (HR 1.959; 95% CI 1.304, 2.944; p = 0.001) and cardiovascular mortality (HR 2.051; 95% CI 1.276, 3.296; p = 0.003). Conclusions Admission EI could be used as a marker for predicting long-term mortality in patients with CHF, and higher EI was associated with an increased risk of all-cause and cardiovascular mortality. Furthermore, EI-guided management could be a promising therapy in patients with CHF.
Collapse
Affiliation(s)
- Bryan Richard Sasmita
- Department of Cardiology, the First Affiliated Hospital of Chongqing Medical University, 400016, Chongqing, China
| | - Yuhe Zhao
- Department of Cardiology, the First Affiliated Hospital of Chongqing Medical University, 400016, Chongqing, China
- Department of Cardiology, Chongqing Seventh People’s Hospital, Chongqing, China
| | - Ming Gong
- Department of Cardiology, the First Affiliated Hospital of Chongqing Medical University, 400016, Chongqing, China
| | - Suxin Luo
- Department of Cardiology, the First Affiliated Hospital of Chongqing Medical University, 400016, Chongqing, China
| | - Bi Huang
- Department of Cardiology, the First Affiliated Hospital of Chongqing Medical University, 400016, Chongqing, China
| |
Collapse
|
5
|
Inami T, Yamaguchi S, Nishioka T, Chida K, Hoshina K, Ito O, Hashimoto T, Murayama M. The Effect of Contrast Water Therapy on Dehydration during Endurance Training Camps in Moderate-Altitude Environments. Sports (Basel) 2023; 11:232. [PMID: 38133099 PMCID: PMC10747241 DOI: 10.3390/sports11120232] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/28/2023] [Revised: 11/03/2023] [Accepted: 11/20/2023] [Indexed: 12/23/2023] Open
Abstract
The effects of contrast water therapy (CWT) on dehydration at moderate altitudes during training camps remain unknown. We hypothesized that CWT reduces dehydration resulting from training at moderate altitudes and improves performance, akin to conditions at sea level. A 13-day endurance training camp was held at a moderate altitude of 1100 m and included 22 university athletes, who were divided into two groups (CWT group, n = 12; control (CON) group, n = 10). The sample size was calculated based on an α level of 0.05, power (1 β) of 0.8, and effect size of 0.25 based on two-way ANOVA. Longitudinal changes over 13 days were compared using a two-group comparison model. Additionally, 16 athletes participated in an additional performance verification analysis. Subjective fatigue, body mass, and water content (total body water (TBW), extracellular water (ECW), and intracellular water) were measured using bioimpedance analysis every morning, and the titin N-terminal fragment in urine (UTF) was measured as an index of muscle damage. For performance verification, 10 consecutive jump performances (with the reactive strength index (RSI) as an indicator) were evaluated as neuromuscular function indices. The results indicated that the UTF did not significantly differ between the two groups. Moreover, the ECW/TBW values, indicative of dehydration, on days 4 and 5 in the CWT group were significantly lower than those in the CON group. However, there was no significant difference in RSI between the two groups. Therefore, although CWT reduces dehydration in the early stages of the training camp, it may not affect performance.
Collapse
Affiliation(s)
- Takayuki Inami
- Institute of Physical Education, Keio University, 4-1-1, Hiyoshi, Yokohama 223-8521, Japan
| | - Shota Yamaguchi
- Institute of Physical Education, Keio University, 4-1-1, Hiyoshi, Yokohama 223-8521, Japan
| | - Takuya Nishioka
- Institute of Physical Education, Keio University, 4-1-1, Hiyoshi, Yokohama 223-8521, Japan
| | - Kenta Chida
- Graduate School of System Design, Management, Keio University, 4-1-1, Hiyoshi, Yokohama 223-8521, Japan
| | - Kosaku Hoshina
- Graduate School of Media and Governance, Keio University, 5322, Fujisawa 252-0883, Japan
| | - Osamu Ito
- Sports Medicine Research Center, Keio University, 4-1-1, Hiyoshi, Yokohama 223-8521, Japan
- FOCS Inc., 1-3-47, Nakahara-Ward, Kawasaki 211-0025, Japan
| | - Takeshi Hashimoto
- Sports Medicine Research Center, Keio University, 4-1-1, Hiyoshi, Yokohama 223-8521, Japan
| | - Mitsuyoshi Murayama
- Institute of Physical Education, Keio University, 4-1-1, Hiyoshi, Yokohama 223-8521, Japan
| |
Collapse
|