Predicting pediatric cardiac surgery-associated acute kidney injury using machine learning.

BACKGROUND: Prediction of cardiac surgery-associated acute kidney injury (CS-AKI) in pediatric patients is crucial to improve outcomes and guide clinical decision-making. This study aimed to develop a supervised machine learning (ML) model for predicting moderate to severe CS-AKI at postoperative day 2 (POD2). METHODS: This retrospective cohort study analyzed data from 402 pediatric patients who underwent cardiac surgery at a university-affiliated children's hospital, who were separated into an 80%-20% train-test split. The ML model utilized demographic, preoperative, intraoperative, and POD0 clinical and laboratory data to predict moderate to severe AKI categorized by Kidney Disease: Improving Global Outcomes (KDIGO) stage 2 or 3 at POD2. Input feature importance was assessed by SHapley Additive exPlanations (SHAP) values. Model performance was evaluated using accuracy, area under the receiver operating curve (AUROC), precision, recall, area under the precision-recall curve (AUPRC), F1-score, and Brier score. RESULTS: Overall, 13.7% of children in the test set experienced moderate to severe AKI. The ML model achieved promising performance, with accuracy of 0.91 (95% CI: 0.82-1.00), AUROC of 0.88 (95% CI: 0.72-1.00), precision of 0.92 (95% CI: 0.70-1.00), recall of 0.63 (95% CI: 0.32-0.96), AUPRC of 0.81 (95% CI: 0.61-1.00), F1-score of 0.73 (95% CI: 0.46-0.99), and Brier score loss of 0.09 (95% CI: 0.00-0.17). The top ten most important features assessed by SHAP analyses in this model were preoperative serum creatinine, surgery duration, POD0 serum pH, POD0 lactate, cardiopulmonary bypass duration, POD0 vasoactive inotropic score, sex, POD0 hematocrit, preoperative weight, and POD0 serum creatinine. CONCLUSIONS: A supervised ML model utilizing demographic, preoperative, intraoperative, and immediate postoperative clinical and laboratory data showed promising performance in predicting moderate to severe CS-AKI at POD2 in pediatric patients.

Fecal microbiota of adolescent and young adult cancer survivors and metabolic syndrome: an exploratory study.

Metabolic syndrome and obesity occur commonly in long-term pediatric cancer survivors. The intestinal microbiome is associated with metabolic syndrome and obesity in the general population, and is perturbed during cancer therapy. We aimed to determine if long-term survivors of pediatric cancer would have reduced bacterial microbiome diversity, and if these findings would be associated with components of the metabolic syndrome, obesity, and chronic inflammation. We performed a cross-sectional exploratory study examining the intestinal microbiome via 16S amplicon sequencing, treatment history, clinical measurements (blood pressure, body mass index) and biomarkers (hemoglobin A1c, lipoproteins, adiponectin: leptin ratio, C-reactive protein, TNFα, Interleukin-6, and Interleukin-10) between 35 long-term survivors and 32 age, sex, and race matched controls. All subjects were aged 10-40 years, and survivors were at least five years from therapy completion. Survivors had lower alpha diversity compared to controls (Shannon index p = .001, Simpson index p = .032) and differently abundant bacterial taxa. Further, among survivors, those who received radiation (18/35) to the central nervous system or abdomen/pelvis had decreased alpha diversity compared to those who did not receive radiation (Shannon and Simpson p < .05 for both). Although, no specific component of metabolic syndrome or cytokine was associated with measures of alpha diversity, survivors with low adiponectin-lectin ratio, elevated body mass index, and elevated C-reactive protein had differently abundant taxa compared to those with normal measures. The microbiome of cancer survivors remains less diverse than controls even many years after diagnosis, and exposure to radiation may lead to further loss of diversity in survivors.Supplemental data for this article is available online at https://doi.org/10.1080/08880018.2022.2049937.

Association between asthma, obesity, and health behaviors in African American youth.

Background: There is a clear relationship between obesity and asthma, with obesity recognized as a risk factor for asthma. There is mounting evidence, however, that asthma may predict obesity risk via behavioral pathways. Objectives: The purpose of this study was to assess the cross-sectional relationships between asthma, body mass index (BMI) percentile, and behavioral factors including caloric intake, dietary inflammatory index, moderate-vigorous physical activity (MVPA), and sedentary time (SED) among African American adolescents. Methods: A community-based sample of 195 African American youth (ages 11-18 years) were included in this analysis. Asthma status was based on self-report using the International Study of Asthma and Allergies in Children's Phase Three questionnaire. MVPA and SED were measured via accelerometry, and caloric intake and dietary inflammatory index were evaluated with the Food Frequency Questionnaire. Weight status was assessed via BMI percentile using measured weight, height, and CDC growth charts. Results: Adolescents with a history of asthma were significantly more overweight (62% vs. 43%, p = 0.04) and consumed a higher inflammatory diet (1.6 ± 0.3 vs. 1.0 ± 0.2, p = 0.02) than their peers who never had asthma. After adjusting for all covariates, activity and dietary variables, odds ratio analysis revealed adolescents who reported ever having asthma were 3.1 ± 1.5 times as likely to be overweight or obese than adolescents with no asthma history (p = 0.02). Conclusions: Presence of asthma history was associated with increased obesity risk in African American adolescents, independent of behavioral factors. Longitudinal studies are needed to better understand the relationship between asthma and obesity in African American adolescents.

Stress-Induced Suppression of Food Intake in Overweight and Obese Adolescents.

OBJECTIVE: Overweight adolescents exhibit greater cortisol reactivity in response to acute stress and are more likely to eat in response to emotional cues, which suggest an increased susceptibility to stress-induced eating. The purpose of this study was to examine the biological (cortisol and α-amylase reactivity) and behavioral (caloric intake) responses to an acute stressor in overweight adolescents. METHODS: Fifty-one adolescents ages 14 to 19 years (47% female, 55% white; body mass index, 31.2 ± 0.8 kg/m) were exposed to the Trier Social Stress Test and a control condition on separate days. Immediately after each condition, participants were provided with snacks to eat at their leisure. Reactivity was assessed via salivary cortisol and α-amylase area under the curve (AUC), and adolescents were categorized as high or low reactors. RESULTS: Cortisol AUC was higher during the stress condition (19.6 ± 0.2 µg/dl · min) compared with the control condition (11.4 ± 0.9 µg/dl · min, p < .001). α-Amylase AUC was not different during the stress condition (9999 ± 987 U/ml · min) compared with the control condition (8762 ± 865 U/ml · min, p = .145). Overall, adolescents consumed fewer calories during the stress condition (488 ± 51 kcal) compared with the control condition (637 ± 42 kcal, p = .007). High cortisol reactors decreased their calorie consumption from the control condition (716 ± 52 kcal) to the stress condition (457 ± 53 kcal, p = .001), whereas low cortisol reactors did not change their consumption (stress: 518 ± 87 kcal versus control: 561 ± 62 kcal, p = .574). CONCLUSION: High cortisol reactivity in overweight adolescents resulted in decreased calorie consumption after an acute stressor. Further research is needed to understand the mechanisms underlying stress-induced suppression of food intake in overweight adolescents.

Acute Effects of Interrupting Prolonged Sitting With Intermittent Physical Activity on Blood Pressure in Preadolescent Children.

PURPOSE: To compare the acute effects of intermittent physical activity (PA) across 4 different intensities on blood pressure. METHODS: Thirty children (12 males and 18 females; aged 7-11 y; 33% overweight/obese; 53% nonwhite) completed 4 experimental conditions in random order: 8 hours sitting interrupted with 20, 2-minute low-, moderate-, high-intensity PA breaks, or sedentary screen-time breaks. PA intensity corresponded with 25%, 50%, and 75% of heart rate reserve. Blood pressure was measured during each condition in the morning (0800 h), noon (1200 h), and afternoon (1600 h). RESULTS: There were no significant differences across conditions for systolic blood pressure (SBP; all Ps > .05). There was a significant effect of time with SBP decreasing throughout the day for all conditions (average morning SBP: 106 [1] mm Hg, average noon SBP: 101 [2] mm Hg, average afternoon SBP: 103 [1] mm Hg; P = .01). There were no significant effects of condition or time on diastolic blood pressure (all Ps > .05). CONCLUSION: While sedentary behavior is known to be associated with hypertension in both adults and children, a single bout of prolonged sitting may be insufficient to produce hypertensive effects in otherwise healthy children. Future research should examine the appropriate dose of intermittent PA to accrue hypotensive responses in preadolescent children.

Acute Compensatory Responses to Interrupting Prolonged Sitting With Intermittent Activity in Preadolescent Children.

PURPOSE: The purpose of this study was to compare the effects of intermittent activity performed at varying intensities and of prolonged sitting on physical activity compensation. METHODS: A total of 33 children (14 boys and 19 girls; age 7-11 y; 24% overweight/obese; 61% nonwhite) completed 4 experimental conditions in random order: 8 hours of sitting interrupted with 20 two-minute low-, moderate-, or high-intensity activity breaks or 20 two-minute sedentary computer game breaks. Physical activity energy expenditure (PAEE) was assessed via accelerometry to establish baseline PAEE and throughout each condition day (8-h in-lab PAEE, out-of-lab PAEE, and 3-d postcondition). RESULTS: Compared with baseline PAEE, total daily PAEE was significantly higher during the high-intensity condition day (153 ± 43 kcal, P = .03), unchanged during the low-intensity (-40 ± 23 kcal, P > .05) and moderate-intensity condition days (-11 ± 18 kcal, P > .05), and decreased in response to prolonged sitting (-79 ± 22 kcal, P = .03). There were no significant differences in PAEE 3-day postcondition across conditions (P > .05). CONCLUSION: Despite the varying levels of PAEE accumulated during the 8-hour laboratory conditions, out-of-lab PAEE during each condition day and 3-day postcondition did not change from the baseline. These findings provide preliminary evidence that spontaneous physical activity in children does not change in response to intermittent activity or prolonged sitting.

Acute Effect of Intermittent Exercise and Action-Based Video Game Breaks on Math Performance in Preadolescent Children.

PURPOSE: The purpose of this study was to compare the acute effects of video game breaks and intermittent exercise breaks, performed at varying intensities, on math performance in preadolescent children. METHODS: A total of 39 children (18 males and 21 females; aged 7-11 y) completed 4 experimental conditions in random order: 8 hours of sitting interrupted with 20 two-minute low-, moderate-, or high-intensity exercise breaks or 20 two-minute sedentary computer game breaks. The intensity of exercise breaks for the low-, moderate-, and high-intensity conditions corresponded with 25%, 50%, and 75% of heart rate reserve, respectively. Math performance was assessed 3 times throughout each condition day using a 90-second math test consisting of 40 single-digit addition and subtraction questions. RESULTS: There were no significant differences in percent change in math scores (correct answers out of attempted) by condition [low: -1.3 (0.8), moderate: 0.1 (1.3), high: -1.8 (0.7), and computer: -2.5 (0.8); P > .05]. There were significant differences in percent change in math scores over the course of the condition days with lower math scores reported at end-of-day test compared with midday test [-2.4 (0.5) vs -0.4 (0.3); P = .01]. There were no significant condition × time, time × age, condition × age, or condition × time × age interactions (all Ps > .05). CONCLUSION: Action-based video game and exercise breaks elicit the same level of math performance in children; however, time of day may impact this relationship. These findings may have important implications for instructional time in elementary classrooms.

Decreasing urgent repeat cesarean sections by offering complimentary ultrasounds and consultation in rural Burundi: The zigama mama project.

Objective: Repeat urgent cesarean sections (CS) carry an increased risk of severe maternal outcomes. As CS increase in sub-Saharan Africa, creative strategies are necessary to reduce the rate of urgent repeat CS. The Zigama-Mama Project in rural Burundi uses complimentary ultrasounds to create a clinical touchpoint to counsel women with a prior CS for a hospital-based delivery. Methods: From July 2019 to June 2020, complimentary ultrasounds were offered to all antenatal patients with prior CS, along with counseling for monitored trial of labor after cesarean (TOLAC) or scheduled repeat CS. Community engagement and feedback from district health centers were evaluated. Results: In total, 500 women with a prior CS presented for a complimentary ultrasound. During the intervention year, a relative and absolute reduction in urgent repeat CS (baseline: n = 114 {70.8%}, intervention: n = 97{49.7%}, p < 0.001) was observed, with no significant change in maternal mortality or ruptured uteri. All health center personnel agreed the project improved their confidence in referring women with prior CS. Conclusion: Offering complimentary ultrasounds as a clinical touchpoint for scheduling a monitored delivery or CS for women at high risk for delivery complication may be an affordable and creative strategy to care for women with previous CS during subsequent deliveries.

A Pilot Remote Curriculum to Enhance Resident and Medical Student Understanding of Machine Learning in Healthcare.

BACKGROUND: Despite the expanding role of machine learning (ML) in health care and patient expectations for clinicians to understand ML-based tools, few for-credit curricula exist specifically for neurosurgical trainees to learn basic principles and implications of ML for medical research and clinical practice. We implemented a novel, remotely delivered curriculum designed to develop literacy in ML for neurosurgical trainees. METHODS: A 4-week pilot medical elective was designed specifically for trainees to build literacy in basic ML concepts. Qualitative feedback from interested and enrolled students was collected to assess students' and trainees' reactions, learning, and future application of course content. RESULTS: Despite 15 interested learners, only 3 medical students and 1 neurosurgical resident completed the course. Enrollment included students and trainees from 3 different institutions. All learners who completed the course found the lectures relevant to their future practice as clinicians and researchers and reported improved confidence in applying and understanding published literature applying ML techniques in health care. Barriers to ample enrollment and retention (e.g., balancing clinical responsibilities) were identified. CONCLUSIONS: This pilot elective demonstrated the interest, value, and feasibility of a remote elective to establish ML literacy; however, feedback to increase accessibility and flexibility of the course encouraged our team to implement changes. Future elective iterations will have a semiannual, 2-week format, splitting lectures more clearly between theory (the method and its value) and application (coding instructions) and will make lectures open-source prerequisites to allow tailoring of student learning to their planned application of these methods in their practice and research.

Deactivation of ligand-receptor interactions enhancing lymphocyte infiltration drives melanoma resistance to Immune Checkpoint Blockade.

Immune checkpoint blockade (ICB) is a promising cancer therapy; however, resistance often develops. To learn more about ICB resistance mechanisms, we developed IRIS (Immunotherapy Resistance cell-cell Interaction Scanner), a machine learning model aimed at identifying candidate ligand-receptor interactions (LRI) that are likely to mediate ICB resistance in the tumor microenvironment (TME). We developed and applied IRIS to identify resistance-mediating cell-type-specific ligand-receptor interactions by analyzing deconvolved transcriptomics data of the five largest melanoma ICB therapy cohorts. This analysis identifies a set of specific ligand-receptor pairs that are deactivated as tumors develop resistance, which we refer to as resistance deactivated interactions (RDI). Quite strikingly, the activity of these RDIs in pre-treatment samples offers a markedly stronger predictive signal for ICB therapy response compared to those that are activated as tumors develop resistance. Their predictive accuracy surpasses the state-of-the-art published transcriptomics biomarker signatures across an array of melanoma ICB datasets. Many of these RDIs are involved in chemokine signaling. Indeed, we further validate on an independent large melanoma patient cohort that their activity is associated with CD8+ T cell infiltration and enriched in hot/brisk tumors. Taken together, this study presents a new strongly predictive ICB response biomarker signature, showing that following ICB treatment resistant tumors turn inhibit lymphocyte infiltration by deactivating specific key ligand-receptor interactions.

Is High Body Mass Index Protective or Detrimental in Surgical Fixation of Hip Fractures?: A Spline Regression Analysis of 22,388 Patients.

OBJECTIVE: We aimed to characterize the association between BMI as a continuous variable and 30-day postoperative outcomes following hip fracture surgery through (1) 30-day readmission and reoperation; (2) local wound-related; and (3) systemic complications. METHODS: The National Surgical Quality Improvement Program database (January 2016-December 2019) was queried for patients undergoing hip fracture open reduction and internal fixation. Baseline patient demographics, comorbidities, and patient outcomes were recorded. Multivariable regression models accounted for baseline demographics, comorbidities, and fracture patterns. Significant associations were analyzed using spline regression models to evaluate the continuous association between BMI and the aforementioned outcomes. RESULTS: Spline models demonstrated a U-shaped curve for the odds of 30-day readmission and 30-day reoperation with nadirs at the BMI of 27.5 and 22.0 kg/m 2 . The odd ratios of superficial infection, deep infection, any wound complication, and inability to weight bear on POD 1 rose progressively starting at a BMI of 25.6, 35.5, 25.6, and 32.7 kg/m 2 respectively. Odds of 30-day mortality, transfusion, pneumonia, and delirium were greatest at the lowest recorded BMI (11.9 kg/m 2 ). CONCLUSION: BMI has a U-shaped association with 30-day readmission and reoperation. Conversely, the highest risk of mortality and systemic complications (transfusion, pneumonia, and delirium) were within the lower BMI range, with diminishing risk as BMI increased. Local wound complications and systemic sepsis exhibited a third unique pattern with progressive rise in odds as BMI increased. The odds of any complications demonstrated a U-shaped pattern with a nadir in the overweight to obese I categories, suggesting that patients may be at lowest risk within this range. LEVEL OF EVIDENCE: Prognostic Level III. See Instructions for Authors for a complete description of levels of evidence.

Why Machine Learning Should Be Taught in Medical Schools.

The rapid development of machine learning (ML) applications in healthcare promises to transform the landscape of healthcare. In order for ML advancements to be effectively utilized in clinical care, it is necessary for the medical workforce to be prepared to handle these changes. As physicians in training are exposed to a wide breadth of clinical tools during medical school, this offers an ideal opportunity to introduce ML concepts. A foundational understanding of ML will not only be practically useful for clinicians, but will also address ethical concerns for clinical decision making. While select medical schools have made effort to integrate ML didactics and practice into their curriculum, we argue that foundational ML principles should be taught broadly to medical students across the country.

Ambient air pollution is associated with vascular disease in Ugandan HIV-positive adolescents.

OBJECTIVE: In this study, we aim to investigate the relationship between particulate matter, a common proxy indicator for air pollution, and markers of inflammation, monocyte activation, and subclinical vascular disease. DESIGN: A cross-sectional study. METHODS: Adolescents with perinatally acquired HIV (PHIV) and HIV-uninfected adolescents between 10 and 18years living near Kampala, Uganda were included. Daily ambient concentrations of particulate matter (PM2.5) were measured from the Eastern Arica GEOHealth Hub. Outcome variables measured were carotid intima-media thickness (IMT), as well as plasma markers of systemic inflammation, oxidized lipids, and gut integrity. Multivariable quantile regression models were used to explore the relationship between PM2.5 and IMT. RESULTS: One hundred and nineteen participants (69 PHIV, 50 HIV-uninfected) were included. The median (Q1, Q3) age was 12.7 (11.4,14.2) years, 55% were girls. Median daily PM2.5 exposure was 29.08 µg/m3 (23.40, 41.70). There was no significant difference in exposure of PM2.5 between groups (P  = 0.073). PM2.5 significantly correlated with intestinal permeability (zonulin; r = 0.43, P < 0.001), monocyte activation (soluble CD163: r  = 0.25, P = 0.053), and IMT (r  = 0.35, P = 0.004) in PHIV but not in HIV-uninfected (P ≥ 0.05). In multivariable quantile regression, after adjusting for age, sex, poverty level, soluble CD163, and zonulin, daily PM2.5 concentrations remained associated with IMT [ß  = 0.005, 95% CI (0.0003-0.010), P = 0.037] in adolescents with PHIV. CONCLUSION: Adolescents in urban Uganda are exposed to high levels of air pollution. Both PM2.5 and HIV have independently been observed to contribute to atherosclerotic disease, and our findings suggest the combined effects of HIV and air pollution may amplify the development of cardiovascular disease.

Simplified Pediatric Index of Mortality 3 Score by Explainable Machine Learning Algorithm.

Pediatric Index of Mortality 3 is a validated tool including 11 variables for the assessment of mortality risk in PICU patients. With the recent advances in explainable machine learning algorithms, we aimed to assess feasibility of application of these machine learning models to simplify the Pediatric Index of Mortality 3 scoring system in order to decrease time and labor required for data collection and entry for Pediatric Index of Mortality 3. DESIGN: Single-center, retrospective cohort study. Data from the Virtual Pediatric Systems for patients admitted to Cleveland Clinic Children`s PICU between January 2008 and December 2019 was obtained. Light Gradient Boosting Machine Regressor (a gradient boosting decision tree algorithm) was used for building the machine learning models. Variable importance was analyzed by SHapley Additive exPlanations. All of the 11 Pediatric Index of Mortality 3 variables were used as input variables in the machine learning models to predict Pediatric Index of Mortality 3 risk of mortality as the outcome variable. Mean absolute error, root mean squared error, and R-squared were calculated for each of the 11 machine learning models as model performance parameters. SETTING: Quaternary children's hospital. PATIENTS: PICU patients. INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: Five-thousand sixty-eight patients were analyzed. The machine learning models were able to maintain similar predictive error until the number of input variables decreased to four. The machine learning model with five input variables (mechanical ventilation in the first hour of PICU admission, very-high-risk diagnosis, surgical recovery from a noncardiac procedure, low-risk diagnosis, and base excess) produced lowest mean root mean squared error of 1.49 (95% CI, 1.05-1.93) and highest R-squared of 0.73 (95% CI, 0.6-0.86) with mean absolute error of 0.43 (95% CI, 0.35-0.5) among all the 11 machine learning models. CONCLUSIONS: Explainable machine learning methods were feasible in simplifying the Pediatric Index of Mortality 3 scoring system with similar risk of mortality predictions compared to the original Pediatric Index of Mortality 3 model tested in a single-center dataset.

How Will Artificial Intelligence Affect Patient-Clinician Relationships?

Artificial intelligence (AI) could improve the efficiency and accuracy of health care delivery, but how will AI influence the patient-clinician relationship? While many suggest that AI might improve the patient-clinician relationship, various underlying assumptions will need to be addressed to bring these potential benefits to fruition. Will off-loading tedious work result in less time spent on administrative burden during patient visits? If so, will clinicians use this extra time to engage relationally with their patients? Moreover, given the desire and opportunity, will clinicians have the ability to engage in effective relationship building with their patients? In order for the best-case scenario to become a reality, clinicians and technology developers must recognize and address these assumptions during the development of AI and its implementation in health care.

Machine Learning in Oncology: What Should Clinicians Know?

The volume and complexity of scientific and clinical data in oncology have grown markedly over recent years, including but not limited to the realms of electronic health data, radiographic and histologic data, and genomics. This growth holds promise for a deeper understanding of malignancy and, accordingly, more personalized and effective oncologic care. Such goals require, however, the development of new methods to fully make use of the wealth of available data. Improvements in computer processing power and algorithm development have positioned machine learning, a branch of artificial intelligence, to play a prominent role in oncology research and practice. This review provides an overview of the basics of machine learning and highlights current progress and challenges in applying this technology to cancer diagnosis, prognosis, and treatment recommendations, including a discussion of current takeaways for clinicians.

Artificial Intelligence in Hematology: Current Challenges and Opportunities.

PURPOSE OF REVIEW: Artificial intelligence (AI), and in particular its subcategory machine learning, is finding an increasing number of applications in medicine, driven in large part by an abundance of data and powerful, accessible tools that have made AI accessible to a larger circle of investigators. RECENT FINDINGS: AI has been employed in the analysis of hematopathological, radiographic, laboratory, genomic, pharmacological, and chemical data to better inform diagnosis, prognosis, treatment planning, and foundational knowledge related to benign and malignant hematology. As more widespread implementation of clinical AI nears, attention has also turned to the effects this will have on other areas in medicine. AI offers many promising tools to clinicians broadly, and specifically in the practice of hematology. Ongoing research into its various applications will likely result in an increasing utilization of AI by a broader swath of clinicians.

Machine learning in haematological malignancies.

Machine learning is a branch of computer science and statistics that generates predictive or descriptive models by learning from training data rather than by being rigidly programmed. It has attracted substantial attention for its many applications in medicine, both as a catalyst for research and as a means of improving clinical care across the cycle of diagnosis, prognosis, and treatment of disease. These applications include the management of haematological malignancy, in which machine learning has created inroads in pathology, radiology, genomics, and the analysis of electronic health record data. As computational power becomes cheaper and the tools for implementing machine learning become increasingly democratised, it is likely to become increasingly integrated into the research and practice landscape of haematology. As such, machine learning merits understanding and attention from researchers and clinicians alike. This narrative Review describes important concepts in machine learning for unfamiliar readers, details machine learning's current applications in haematological malignancy, and summarises important concepts for clinicians to be aware of when appraising research that uses machine learning.

Acute Effects of Intermittent Physical Activity on Perceptions of Exercise-Related Fatigue in Children.

PURPOSE: To investigate the acute effects of intermittent activity performed at varying intensities on the perceptions of exercise-related fatigue in children. METHODS: A total of 30 children completed 4 experimental conditions in random order, which consisted of 8 hours of sitting interrupted with 20 two-minute low-, moderate-, or high-intensity activity breaks or 20 two-minute sedentary breaks. The perceptions of exercise-related fatigue were determined via the Subjective Exercise Experience Scale at the beginning (0 breaks), middle (after 10 breaks), and end (after 20 breaks) of each condition. RESULTS: The average heart rate was significantly higher with increasing exercise intensity (sedentary: 89.6 ± 1.2 beats/min, low: 114.6 ± 1.8 beats/min, moderate: 147.2 ± 1.8 beats/min, and high: 172.3 ± 1.8 beats/min, P < .0001). There was no significant main effect of condition (sedentary: -0.5 ± 0.6, low: -1.0 ± 0.7, moderate: -0.2 ± 0.5, and high: -0.6 ± 1.2; P = .86) and time (10-0 breaks: -0.7 ± 0.5 and 20-0 breaks: -0.5 ± 0.5; P = .45), nor time by condition interaction (P = .99) on change in exercise-related fatigue. CONCLUSIONS: Incorporating intermittent activity into physical activity programs may help to reduce barriers to regular exercise by minimizing perceptions of exercise-related fatigue in children.