Identifying cytokine predictors of cognitive functioning in breast cancer survivors up to 10?years post chemotherapy using machine learning.
Ontology highlight
ABSTRACT:
SUBMITTER: Henneghan AM
PROVIDER: S-EPMC6030687 | biostudies-literature | 2018 Jul
REPOSITORIES: biostudies-literature
Publications
Identifying cytokine predictors of cognitive functioning in breast cancer survivors up to 10 years post chemotherapy using machine learning.
Henneghan Ashley M AM Palesh Oxana O Harrison Michelle M Kesler Shelli R SR
Journal of neuroimmunology 20180419
<h4>Introduction</h4>The purpose of this study is to explore 13 cytokine predictors of chemotherapy-related cognitive impairment (CRCI) in breast cancer survivors (BCS) 6 months to 10 years after chemotherapy completion using a multivariate, non-parametric approach.<h4>Methods</h4>Cross sectional data collection included completion of a survey, cognitive testing, and non-fasting blood from 66 participants. Data were analyzed using random forest regression to identify the most significant predict ...[more]
Similar Datasets
Project description:BACKGROUND:Machine learning techniques, specifically classification algorithms, may be effective to help understand key health, nutritional, and environmental factors associated with cognitive function in aging populations. OBJECTIVE:This study aims to use classification techniques to identify the key patient predictors that are considered most important in the classification of poorer cognitive performance, which is an early risk factor for dementia. METHODS:Data were used from the Trinity-Ulster and Department of Agriculture study, which included detailed information on sociodemographic, clinical, biochemical, nutritional, and lifestyle factors in 5186 older adults recruited from the Republic of Ireland and Northern Ireland, a proportion of whom (987/5186, 19.03%) were followed up 5-7 years later for reassessment. Cognitive function at both time points was assessed using a battery of tests, including the Repeatable Battery for the Assessment of Neuropsychological Status (RBANS), with a score <70 classed as poorer cognitive performance. This study trained 3 classifiers-decision trees, Naïve Bayes, and random forests-to classify the RBANS score and to identify key health, nutritional, and environmental predictors of cognitive performance and cognitive decline over the follow-up period. It assessed their performance, taking note of the variables that were deemed important for the optimized classifiers for their computational diagnostics. RESULTS:In the classification of a low RBANS score (<70), our models performed well (F1 score range 0.73-0.93), all highlighting the individual's score from the Timed Up and Go (TUG) test, the age at which the participant stopped education, and whether or not the participant's family reported memory concerns to be of key importance. The classification models performed well in classifying a greater rate of decline in the RBANS score (F1 score range 0.66-0.85), also indicating the TUG score to be of key importance, followed by blood indicators: plasma homocysteine, vitamin B6 biomarker (plasma pyridoxal-5-phosphate), and glycated hemoglobin. CONCLUSIONS:The results suggest that it may be possible for a health care professional to make an initial evaluation, with a high level of confidence, of the potential for cognitive dysfunction using only a few short, noninvasive questions, thus providing a quick, efficient, and noninvasive way to help them decide whether or not a patient requires a full cognitive evaluation. This approach has the potential benefits of making time and cost savings for health service providers and avoiding stress created through unnecessary cognitive assessments in low-risk patients.
| S-EPMC7527918 | biostudies-literature
Project description:BACKGROUND:Treatment for cancer may lead to development of cognitive difficulties in cancer survivors. This study aimed to evaluate long-term cognitive functioning (CogF) in germ-cell tumor (GCT) survivors. SUBJECTS, MATERIALS, AND METHODS:GCT survivors (n?=?155) from the National Cancer Institute of Slovakia completed the Functional Assessment of Cancer Therapy Cognitive Function at a median of 10 years of follow-up (range: 5-32). The study group consisted of survivors receiving a cisplatin-based chemotherapy, radiotherapy to the retroperitoneal lymph nodes, or both, whereas the control group included survivors treated with orchiectomy only. RESULTS:Of the total survivors, 138 received treatment beyond orchiectomy and 17 controls had orchiectomy alone. Any treatment resulted in significantly greater cognitive difficulties on the overall cognitive function score. Treatment with radiotherapy was associated with cognitive declines in overall cognitive functioning and in subscales for perceived cognitive impairment and cognitive impairment perceived by others (both p?<?.05). The burden of chemotherapy plus radiotherapy or radiotherapy versus controls resulted in the impairment in all cognitive functioning domains (all p?<?.05). Overall long-term cognitive impairment was independent of age in the multivariable analysis. CONCLUSION:This prospective study shows that GCT survivors suffer from a long-term CogF impairment. These results may help guide clinicians' decisions in treatment and follow-up of GCTs. IMPLICATIONS FOR PRACTICE:In this study, long-term survivors of germ-cell tumors have reported cognitive impairment after curative treatment with radiotherapy and chemotherapy compared with controls who had treatment with orchiectomy only. These data provide an argument against the use of adjuvant radiotherapy for stage I seminoma. Unnecessary overtreatment with chemotherapy and additional radiotherapy after chemotherapy should be avoided.
| S-EPMC5947452 | biostudies-literature
Project description:BackgroundAlterations in multiple domains of cognition have been observed in individuals who have experienced a traumatic stressor. These domains may provide important insights in identifying underlying neurobiological dysfunction driving an individual's clinical response to trauma. However, such assessments are burdensome, costly, and time-consuming. To overcome barriers, efforts have emerged to measure multiple domains of cognitive functioning through the application of machine learning (ML) models to passive data sources.MethodsWe utilized automated computer vision and voice analysis methods to extract facial, movement, and speech characteristics from semi-structured clinical interviews in 81 trauma survivors who additionally completed a cognitive assessment battery. A ML-based regression framework was used to identify variance in visual and auditory measures that relate to multiple cognitive domains.ResultsModels derived from visual and auditory measures collectively accounted for a large variance in multiple domains of cognitive functioning, including motor coordination (R2 = 0.52), processing speed (R2 = 0.42), emotional bias (R2 = 0.52), sustained attention (R2 = 0.51), controlled attention (R2 = 0.44), cognitive flexibility (R2 = 0.43), cognitive inhibition (R2 = 0.64), and executive functioning (R2 = 0.63), consistent with the high test-retest reliability of traditional cognitive assessments. Face, voice, speech content, and movement have all significantly contributed to explaining the variance in predicting functioning in all cognitive domains.ConclusionsThe results demonstrate the feasibility of automated measurement of reliable proxies of cognitive functioning through low-burden passive patient evaluations. This makes it easier to monitor cognitive functions and to intervene earlier and at a lower threshold without requiring a time-consuming neurocognitive assessment by, for instance, a licensed psychologist with specialized training in neuropsychology.
| S-EPMC7879325 | biostudies-literature
Project description:IntroductionThe relationship between cognitive function and frailty in older, long-term breast cancer survivors was examined.Materials and methodsBreast cancer survivors who were diagnosed and treated at 60 years of age or above and were 5-15 year disease-free survivors and non-cancer controls matched on age and education were evaluated with neuropsychological tests and the Comprehensive Geriatric Assessment which was used to assess frailty based on a deficit accumulation frailty index (DAFI).ResultsUnadjusted regression analyses revealed that cancer survivors scored significantly lower on the Language (P = 0.015), Attention, Processing Speed, Executive Function (APE) (P = 0.015), and Learning and Memory (LM) (P = 0.023) domains compared to controls. However, only the LM domain remained significantly different (P = 0.002) in the adjusted analysis. Survivors had significantly higher DAFI scores compared to controls (p = 0.006) and significantly more survivors were categorized as pre-frail or frail (35%) compared to controls (23%, P = 0.009). Increasing frailty scores were associated with worse cognitive performance across all domains (all Ps ≤ 0.004). For the LM domain, there was a significant interaction (P = 0.019) between DAFI score and survivorship vs control status. Survivors demonstrated a significant linear decline in LM scores as DAFI scores increased, whereas controls demonstrated comparable scores between the robust and pre-frail DAFI groups, demonstrating decline in the frailty group only.ConclusionOlder, long-term breast cancer survivors had lower cognitive performance and higher levels of frailty compared to controls. For the Learning and Memory domain, the decline in performance began in the pre-frail range for survivors, but not controls.
| S-EPMC9262141 | biostudies-literature
Project description:ObjectivesGenetic risks for cognitive decline are not modifiable; however their relative importance compared to modifiable factors is unclear. We used machine learning to evaluate modifiable and genetic risk factors for Alzheimer's disease (AD), to predict cognitive decline.MethodsHealth and Retirement Study participants, aged 65-90 years, with DNA and >2 cognitive evaluations, were included (n = 7,142). Predictors included age, body mass index, gender, education, APOE ε4, cardiovascular, hypertension, diabetes, stroke, neighborhood socioeconomic status (NSES), and AD risk genes. Latent class trajectory analyses of cognitive scores determined the form and number of classes. Random Forests (RF) classification investigated predictors of cognitive trajectories. Performance metrics (accuracy, sensitivity, and specificity) were reported.ResultsThree classes were identified. Discriminating highest from lowest classes produced the best RF performance: accuracy = 78% (1.0%), sensitivity = 75% (1.0%), and specificity = 81% (1.0%). Top ranked predictors were education, age, gender, stroke, NSES, and diabetes, APOE ε4 carrier status, and body mass index (BMI). When discriminating high from medium classes, top predictors were education, age, gender, stroke, diabetes, NSES, and BMI. When discriminating medium from the low classes, education, NSES, age, diabetes, and stroke were top predictors.DiscussionThe combination of latent trajectories and RF classification techniques suggested that nongenetic factors contribute more to cognitive decline than genetic factors. Education was the most relevant predictor for discrimination.
| S-EPMC7205421 | biostudies-literature
Project description:Scientific understanding about the psychological impact of the COVID-19 global pandemic is in its nascent stage. Prior research suggests that demographic factors, such as gender and age, are associated with greater distress during a global health crisis. Less is known about how emotion regulation impacts levels of distress during a pandemic. The present study aimed to identify predictors of psychological distress during the COVID-19 pandemic. Participants (N = 2,787) provided demographics, history of adverse childhood experiences, current coping strategies (use of implicit and explicit emotion regulation), and current psychological distress. The overall prevalence of clinical levels of anxiety, depression, and post-traumatic stress was higher than the prevalence outside a pandemic and was higher than rates reported among healthcare workers and survivors of severe acute respiratory syndrome. Younger participants (<45 years), women, and non-binary individuals reported higher prevalence of symptoms across all measures of distress. A random forest machine learning algorithm was used to identify the strongest predictors of distress. Regression trees were developed to identify individuals at greater risk for anxiety, depression, and post-traumatic stress. Somatization and less reliance on adaptive defense mechanisms were associated with greater distress. These findings highlight the importance of assessing individuals' physical experiences of psychological distress and emotion regulation strategies to help mental health providers tailor assessments and treatment during a global health crisis.
| S-EPMC7682196 | biostudies-literature
Project description:Translation Environment Tools make translators' work easier by providing them with term lists, translation memories and machine translation output. Ideally, such tools automatically predict whether it is more effortful to post-edit than to translate from scratch, and determine whether or not to provide translators with machine translation output. Current machine translation quality estimation systems heavily rely on automatic metrics, even though they do not accurately capture actual post-editing effort. In addition, these systems do not take translator experience into account, even though novices' translation processes are different from those of professional translators. In this paper, we report on the impact of machine translation errors on various types of post-editing effort indicators, for professional translators as well as student translators. We compare the impact of MT quality on a product effort indicator (HTER) with that on various process effort indicators. The translation and post-editing process of student translators and professional translators was logged with a combination of keystroke logging and eye-tracking, and the MT output was analyzed with a fine-grained translation quality assessment approach. We find that most post-editing effort indicators (product as well as process) are influenced by machine translation quality, but that different error types affect different post-editing effort indicators, confirming that a more fine-grained MT quality analysis is needed to correctly estimate actual post-editing effort. Coherence, meaning shifts, and structural issues are shown to be good indicators of post-editing effort. The additional impact of experience on these interactions between MT quality and post-editing effort is smaller than expected.
| S-EPMC5539081 | biostudies-other
Project description:Childhood cancer survivors are at risk for cognitive and social deficits. Previous findings indicate computerized cognitive training can result in an improvement of cognitive skills. The current objective was to investigate whether these cognitive gains generalize to social functioning benefits. Sixty-eight survivors of childhood cancer were randomly assigned to a computerized cognitive intervention (mean age 12.21 ± 2.47 years, 4.97 ± 3.02 years off-treatment) or waitlist control group (mean age 11.82 ± 2.42 years, 5.04 ± 2.41 years off-treatment). Conners 3 Parent and Self-Report forms were completed pre-intervention, immediately post-intervention and six-months post-intervention. Piecewise linear mixed-effects models indicated no significant differences in Peer Relations between groups at baseline and no difference in change between groups from pre- to immediate post-intervention or post- to six-months post-intervention (ps > 0.40). Baseline Family Relations problems were significantly elevated in the control group relative to the intervention group (p < 0.01), with a significantly greater decline from pre- to immediate post-intervention (p < 0.05) and no difference in change between groups from post- to six-months post-intervention (p > 0.80). The study results suggest cognitive gains from computerized training do not generalize to social functioning. Training focused on skill-based social processing (e.g., affect recognition) may be more efficacious.
| S-EPMC6826733 | biostudies-literature
Project description:ObjectiveA long-term decline in health-related quality of life (HRQoL) has been reported after coronavirus disease 2019 (COVID-19). Studies with people with persistent symptoms showed inconsistent outcomes. Cognition and emotion are important determinants in HRQoL, but few studies have examined their prognostic significance for HRQoL and functionality in post-COVID patients with persisting symptoms. We aimed to describe QoL, HRQoL, and functioning in individuals post-COVID with varying COVID-19 severities and to investigate the predictive value of cognitive and emotional variables for QoL, HRQoL, and functioning.MethodsIn total, 492 participants (398 post-COVID and 124 healthy controls) underwent a neurobehavioral examination that included assessments of cognition, mood, QoL/HRQoL (WHOQOL-BREF, EQ-5D), and functioning (WHODAS-II). Analysis of covariance and linear regression models were used to study intergroup differences and the relationship between cognitive and emotional variables and QoL and functioning.ResultsThe Physical and Psychological dimensions of WHOQoL, EQ-5D, and WHODAS Cognition, Mobility, Life Activities, and Participation dimensions were significantly lower in post-COVID groups compared with a control group. Regression models explaining 23.9%-53.9% of variance were obtained for the WHOQoL-BREF dimensions and EQ-5D, with depressive symptoms, post-COVID symptoms, employment status, income, and mental speed processing as main predictors. For the WHODAS, models explaining 17%-60.2% of the variance were obtained. Fatigue, depressive symptoms, mental speed processing, and post-COVID symptoms were the main predictors.InterpretationQoL/HRQoL and functioning after COVID-19 in individuals with persistent symptoms were lower than in non-affected persons. Depressive symptoms, fatigue, and slower mental processing speed were predictors of lower QoL/HRQoL and functioning.
| S-EPMC10863915 | biostudies-literature
Project description:PURPOSE:Further research on patient experience and involvement is recommended in order to develop evidence-based and meaningful care pathways for lymphoma survivors. This study aims to explore the experience of a sample of lymphoma survivors participating in a home-based intervention following chemotherapy. METHODS:Eligible participants who completed a 12-week home-based intervention were invited to complete the End of Study Questionnaire designed to explore perceptions, preferences and barriers to participation. Content analysis was used to generate codes, describe frequencies and identify themes. RESULTS:Participating in a home-based intervention post-treatment was a positive experience overall, and aided recovery in this sample of lymphoma survivors (n?=?35). Participants felt the programme provided structure, motivation and liked contact with the researcher. Participants highlighted their need for advice on healthy lifestyle, diet in particular. CONCLUSIONS:Lymphoma survivors in this study reported participation in a home-based intervention following treatment beneficial and aided recovery. IMPLICATIONS FOR CANCER SURVIVORS:A large proportion of lymphoma survivors would benefit from a rehabilitation intervention post-chemotherapy. Intervention programmes should include follow-ups to monitor progress and provide support and motivation. Health professionals should recommend healthy lifestyle guidelines to survivors on completion of treatment or refer patients to appropriate services for rehabilitation and advice.
| S-EPMC6803568 | biostudies-literature