Learning from data to predict future symptoms of oncology patients.
Ontology highlight
ABSTRACT:
SUBMITTER: Papachristou N
PROVIDER: S-EPMC6312306 | biostudies-literature | 2018
REPOSITORIES: biostudies-literature
Publications
Learning from data to predict future symptoms of oncology patients.
Papachristou Nikolaos N Puschmann Daniel D Barnaghi Payam P Cooper Bruce B Hu Xiao X Maguire Roma R Apostolidis Kathi K Conley Yvette P YP Hammer Marilyn M Katsaragakis Stylianos S Kober Kord M KM Levine Jon D JD McCann Lisa L Patiraki Elisabeth E Furlong Eileen P EP Fox Patricia A PA Paul Steven M SM Ream Emma E Wright Fay F Miaskowski Christine C
PloS one 20181231 12
Effective symptom management is a critical component of cancer treatment. Computational tools that predict the course and severity of these symptoms have the potential to assist oncology clinicians to personalize the patient's treatment regimen more efficiently and provide more aggressive and timely interventions. Three common and inter-related symptoms in cancer patients are depression, anxiety, and sleep disturbance. In this paper, we elaborate on the efficiency of Support Vector Regression (S ...[more]
Similar Datasets
Project description:The early stages of Alzheimer's disease (AD) involve interactions between multiple pathophysiological processes. Although these processes are well studied, we still lack robust tools to predict individualised trajectories of disease progression. Here, we employ a robust and interpretable machine learning approach to combine multimodal biological data and predict future pathological tau accumulation. In particular, we use machine learning to quantify interactions between key pathological markers (β-amyloid, medial temporal lobe atrophy, tau and APOE 4) at mildly impaired and asymptomatic stages of AD. Using baseline non-tau markers we derive a prognostic index that: (a) stratifies patients based on future pathological tau accumulation, (b) predicts individualised regional future rate of tau accumulation, and (c) translates predictions from deep phenotyping patient cohorts to cognitively normal individuals. Our results propose a robust approach for fine scale stratification and prognostication with translation impact for clinical trial design targeting the earliest stages of AD.
| S-EPMC8989879 | biostudies-literature
Project description:Background:Major depressive disorder is a leading cause of disability worldwide; however, little is known about pathological mechanisms involved in its development. Research in adolescent depression has focused on reward sensitivity and striatal mechanisms implementing it. The contribution of loss sensitivity to future depression, as well as the orbitofrontal cortex (OFC) mechanisms critical for processing losses and rewards, remain unexplored. Furthermore, it is unclear whether OFC functioning interacts with familial history in predicting future depression. Methods:In this longitudinal study we recorded functional magnetic resonance imaging (fMRI) data while 229 adolescent females with or without parental history of depression completed a monetary gambling task. We examined if OFC blood-oxygen-level-dependent (BOLD) response and functional connectivity during loss and win feedback was associated with depression symptoms concurrently and prospectively (9 months later), and whether this relationship was moderated by parental history of depression. Results:Reduced OFC response during loss was associated with higher depression symptoms concurrently and prospectively, even after controlling for concurrent depression, specifically in adolescents with parental history of depression. Similarly, increased OFC-posterior insula connectivity during loss was associated with future depression symptoms but this relationship was not moderated by parental history of depression. Conclusions:This study provides the first evidence for loss-related alterations in OFC functioning and its interaction with familial history of depression as possible mechanisms in the development of depression. While the current fMRI literature has mainly focused on reward, the present findings underscore the need to include prefrontal loss processing in existing developmental models of depression.
| S-EPMC5720380 | biostudies-literature
Project description:BackgroundNeuropsychiatric symptoms (NPS) are the leading cause of the social burden of dementia but their role is underestimated.ObjectiveThe objective of the study was to validate predictive models to separately identify psychotic and depressive symptoms in patients diagnosed with dementia using clinical databases representing the whole population to inform decision-makers.MethodsFirst, we searched the electronic health records of 4,003 patients with dementia to identify NPS. Second, machine learning (random forest) algorithms were applied to build separate predictive models for psychotic and depressive symptom clusters in the training set (N = 3,003). Third, calibration and discrimination were assessed in the test set (N = 1,000) to assess the performance of the models.ResultsNeuropsychiatric symptoms were noted in the electronic health record of 58% of patients. The area under the receiver operating curve reached 0.80 for the psychotic cluster model and 0.74 for the depressive cluster model. The Kappa index and accuracy also showed better discrimination in the psychotic model. Calibration plots indicated that both types of model had less predictive accuracy when the probability of neuropsychiatric symptoms was <25%. The most important variables in the psychotic cluster model were use of risperidone, level of sedation, use of quetiapine and haloperidol and the number of antipsychotics prescribed. In the depressive cluster model, the most important variables were number of antidepressants prescribed, escitalopram use, level of sedation, and age.ConclusionGiven their relatively good performance, the predictive models can be used to estimate prevalence of NPS in population databases.
| S-EPMC7592688 | biostudies-literature
Project description:Pediatric cancer is a rare disease with a low annual incidence, which presents a significant challenge in being able to collect enough data to fuel clinical discoveries. Big data registry trials hold promise to advance the study of pediatric cancers by allowing for the combination of traditional randomized controlled trials with the power of larger cohort sizes. The emergence of big data resources and data-sharing initiatives are becoming transformative for pediatric cancer diagnosis and treatment. This review discusses the uses of big data in pediatric cancer, existing pediatric cancer registry initiatives and research, the challenges in harmonizing these data to improve accessibility for study, and building pediatric data commons and other important future endeavors.
| S-EPMC9036548 | biostudies-literature
Project description:BACKGROUND:Identifying individuals who are unlikely to adhere to a physical exercise regime has potential to improve physical activity interventions. The aim of this paper is to develop and test adherence prediction models using objectively measured physical activity data in the Mobile Phone-Based Physical Activity Education program (mPED) trial. To the best of our knowledge, this is the first to apply Machine Learning methods to predict exercise relapse using accelerometer-recorded physical activity data. METHODS:We use logistic regression and support vector machine methods to design two versions of a Discontinuation Prediction Score (DiPS), which uses objectively measured past data (e.g., steps and goal achievement) to provide a numerical quantity indicating the likelihood of exercise relapse in the upcoming week. The respective prediction accuracy of these two versions of DiPS are compared, and then numerical simulation is performed to explore the potential of using DiPS to selectively allocate financial incentives to participants to encourage them to increase physical activity. RESULTS:we had access to a physical activity trial data that were continuously collected every 60?sec every day for 9?months in 210 participants. By using the first 15?weeks of data as training and test on weeks 16-30, we show that both versions of DiPS have a test AUC of 0.9 with high sensitivity and specificity in predicting the probability of exercise adherence. Simulation results assuming different intervention regimes suggest the potential benefit of using DiPS as a score to allocate resources in physical activity intervention programs in reducing costs over other allocation schemes. CONCLUSIONS:DiPS is capable of making accurate and robust predictions for future weeks. The most predictive features are steps and physical activity intensity. Furthermore, the use of DiPS scores can be a promising approach to determine when or if to provide just-in-time messages and step goal adjustments to improve compliance. Further studies on the use of DiPS in the design of physical activity promotion programs are warranted. TRIAL REGISTRATION:ClinicalTrials.gov NCT01280812 Registered on January 21, 2011.
| S-EPMC6704548 | biostudies-literature
Project description:BackgroundStenosis, fistulization, and perforation of the bowel are severe outcomes which can occur in patients with Crohn's disease. Accurate prediction of these events may enable clinicians to alter treatment strategies and avoid these outcomes.AimsTo study the correlation between longitudinal laboratory testing and subsequent intestinal complications in patients with Crohn's disease.MethodsAn observational cohort of patients with Crohn's disease at a single center were analyzed between 01/01/1994 and 06/30/2016. A complication was defined as the development of an intestinal fistula, stenosis, or perforation. Exploratory analysis using Cox regression was performed to select the best statistical method to represent longitudinal laboratory data. Cox regression was used to identify laboratory variables independently associated with the development of a subsequent complication. A clinical scoring tool was designed.ResultsIn 246 patients observed over a median of 5.72 years, 134 complications occurred. Minimum or maximum value in a preceding window period of one year was most strongly associated with subsequent complication. A Longitudinal Laboratory score of ≥ 2 (maximum albumin level < 39 g/L = 1, maximum mean cell volume < 88 fL = 1, minimum platelet count > 355 × 109/L = 1, minimum C reactive protein > 5 mg/L = 1) was 62% sensitive and 91% specific in identifying patients who develop a subsequent complication.ConclusionA consistent reduction in serum albumin and mean cell volume, and a consistent increase in platelet count and C reactive protein were associated with a subsequent complication in patients with Crohn's disease. Longitudinal laboratory tests may be used as described in this paper to provide a rational for earlier escalation of therapy.
| S-EPMC9905172 | biostudies-literature
Project description:Predictive species distribution models are mostly based on statistical dependence between environmental and distributional data and therefore may fail to account for physiological limits and biological interactions that are fundamental when modelling species distributions under future climate conditions. Here, we developed a state-of-the-art method integrating biological theory with survey and experimental data in a way that allows us to explicitly model both physical tolerance limits of species and inherent natural variability in regional conditions and thereby improve the reliability of species distribution predictions under future climate conditions. By using a macroalga-herbivore association (Fucus vesiculosus - Idotea balthica) as a case study, we illustrated how salinity reduction and temperature increase under future climate conditions may significantly reduce the occurrence and biomass of these important coastal species. Moreover, we showed that the reduction of herbivore occurrence is linked to reduction of their host macroalgae. Spatial predictive modelling and experimental biology have been traditionally seen as separate fields but stronger interlinkages between these disciplines can improve species distribution projections under climate change. Experiments enable qualitative prior knowledge to be defined and identify cause-effect relationships, and thereby better foresee alterations in ecosystem structure and functioning under future climate conditions that are not necessarily seen in projections based on non-causal statistical relationships alone.
| S-EPMC6372580 | biostudies-literature
Project description:Propensity for alcohol misuse may be linked to an individuals' response to alcohol. This study examined the role of alcohol response phenotypes to future drinking problems.One hundred four young heavy social drinkers participated in a within-subject, double-blind, placebo-controlled laboratory alcohol challenge study with 6-year follow-up. Participants were examined for subjective responses before and after receiving an intoxicating dose of alcohol (.8 g/kg) or a placebo beverage, given in random order. Follow-up was conducted in 5 waves over 6 years after the sessions to assess drinking behaviors and alcohol use disorder (AUD) symptoms. Retention was high with 98% (509 of 520) of possible follow-ups completed.Greater sensitivity to alcohol, in terms of stimulation and rewarding effects (like, want more) and lower sensitivity to alcohol sedation predicted greater number of AUD symptoms through 6 years of follow-up. Cluster analyses revealed that for half the sample, increasing levels of stimulation and liking were predictors of more AUD symptoms with the other half divided between those showing like and want more and want more alone as significant predictors.The findings extend previous findings and offer new empirical insights into the propensity for excessive drinking and alcohol problems. Heightened alcohol stimulation and reward sensitivity robustly predicted more alcohol use disorder symptoms over time associated with greater binge-drinking frequency. These drinking problems were maintained and progressed as these participants were entering their third decade of life, a developmental interval when continued alcohol misuse becomes more deviant.
| S-EPMC4280017 | biostudies-literature
Project description:Recent advances in clinical oncology is based on exploiting the capacity of the immune system to combat cancer: immuno-oncology. Thus, immunotherapy of cancer is now used to treat a variety of malignant diseases. A striking feature is that even patients with late-stage disease may experience curative responses. However, most patients still succumb to disease, and do not benefit from treatment. Exercise has gained attention in clinical oncology and has been used for many years to improve quality of life, as well as to counteract chemotherapy-related complications. However, more recently, exercise has garnered interest, largely due to data from animal studies suggesting a striking therapeutic effect in preclinical cancer models; an effect largely mediated by the immune system. In humans, physical activity is associated with a lower risk for a variety of malignancies, and some data suggest a positive clinical effect for cancer patients. Exercise leads to mobilization of cells of the immune system, resulting in redistribution to different body compartments, and in preclinical models, exercise has been shown to lead to immunological changes in the tumor microenvironment. This suggests that exercise and immunotherapy could have a synergistic effect if combined.
| S-EPMC7312459 | biostudies-literature
Project description:BackgroundPeople with cancer frequently experience severe and distressing symptoms associated with cancer and its treatments. Predicting symptoms in patients with cancer continues to be a significant challenge for both clinicians and researchers. The rapid evolution of machine learning (ML) highlights the need for a current systematic review to improve cancer symptom prediction.ObjectiveThis systematic review aims to synthesize the literature that has used ML algorithms to predict the development of cancer symptoms and to identify the predictors of these symptoms. This is essential for integrating new developments and identifying gaps in existing literature.MethodsWe conducted this systematic review in accordance with the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) checklist. We conducted a systematic search of CINAHL, Embase, and PubMed for English records published from 1984 to August 11, 2023, using the following search terms: cancer, neoplasm, specific symptoms, neural networks, machine learning, specific algorithm names, and deep learning. All records that met the eligibility criteria were individually reviewed by 2 coauthors, and key findings were extracted and synthesized. We focused on studies using ML algorithms to predict cancer symptoms, excluding nonhuman research, technical reports, reviews, book chapters, conference proceedings, and inaccessible full texts.ResultsA total of 42 studies were included, the majority of which were published after 2017. Most studies were conducted in North America (18/42, 43%) and Asia (16/42, 38%). The sample sizes in most studies (27/42, 64%) typically ranged from 100 to 1000 participants. The most prevalent category of algorithms was supervised ML, accounting for 39 (93%) of the 42 studies. Each of the methods-deep learning, ensemble classifiers, and unsupervised ML-constituted 3 (3%) of the 42 studies. The ML algorithms with the best performance were logistic regression (9/42, 17%), random forest (7/42, 13%), artificial neural networks (5/42, 9%), and decision trees (5/42, 9%). The most commonly included primary cancer sites were the head and neck (9/42, 22%) and breast (8/42, 19%), with 17 (41%) of the 42 studies not specifying the site. The most frequently studied symptoms were xerostomia (9/42, 14%), depression (8/42, 13%), pain (8/42, 13%), and fatigue (6/42, 10%). The significant predictors were age, gender, treatment type, treatment number, cancer site, cancer stage, chemotherapy, radiotherapy, chronic diseases, comorbidities, physical factors, and psychological factors.ConclusionsThis review outlines the algorithms used for predicting symptoms in individuals with cancer. Given the diversity of symptoms people with cancer experience, analytic approaches that can handle complex and nonlinear relationships are critical. This knowledge can pave the way for crafting algorithms tailored to a specific symptom. In addition, to improve prediction precision, future research should compare cutting-edge ML strategies such as deep learning and ensemble methods with traditional statistical models.
| S-EPMC10988375 | biostudies-literature