The Effect of Individual Musculoskeletal Conditions on Depression: Updated Insights From an Irish Longitudinal Study on Aging

Jin, Wenyi; Liu, Zilin; Zhang, Yubiao; Che, Zhifei; Gao, Mingyong

doi:10.3389/fmed.2021.697649

Cited by 11 publications

(15 citation statements)

References 56 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As a state-of-the-art bioinformatic tool, deep learning has achieved an overwhelming advantage in disease diagnosis and treatment response prediction ( 12 , 15 , 26 ). Traditionally, diagnosing cancers relies highly on histopathology or cytopathology, which mainly involves assessment under microscopy to detect aberrant cells within a clinical sample, evaluate biomarkers of certain cancers and determine cancers’ subtype, stage, and grade ( 27 , 28 ).…”

Section: Discussionmentioning

confidence: 99%

“…The feature selection phase was conducted with R software, implementing logistic regression as per our previous study ( 15 ), for selecting features that impact outcomes significantly. Features met p-value < 0.001 in their corresponding logistic regression model were retained and considered as the important features for clinical outcomes.…”

Section: Methodsmentioning

confidence: 99%

“…The statistical results and interactive network data analysis were visualized with Cytoscape version 3.7.1 (Cytoscape Consortium, San Diego, California, USA). According to the previous study ( 15 ), Pearson’s and Spearman’s correlation coefficients were utilized to calculate continuous and categorical variables, respectively.…”

Section: Methodsmentioning

confidence: 99%

See 2 more Smart Citations

Ensemble deep learning enhanced with self-attention for predicting immunotherapeutic responses to cancers

et al. 2022

Self Cite

View full text Add to dashboard Cite

IntroductionDespite the many benefits immunotherapy has brought to patients with different cancers, its clinical applications and improvements are still hindered by drug resistance. Fostering a reliable approach to identifying sufferers who are sensitive to certain immunotherapeutic agents is of great clinical relevance.MethodsWe propose an ELISE (Ensemble Learning for Immunotherapeutic Response Evaluation) pipeline to generate a robust and highly accurate approach to predicting individual responses to immunotherapies. ELISE employed iterative univariable logistic regression to select genetic features of patients, using Monte Carlo Tree Search (MCTS) to tune hyperparameters. In each trial, ELISE selected multiple models for integration based on add or concatenate stacking strategies, including deep neural network, automatic feature interaction learning via self-attentive neural networks, deep factorization machine, compressed interaction network, and linear neural network, then adopted the best trial to generate a final approach. SHapley Additive exPlanations (SHAP) algorithm was applied to interpret ELISE, which was then validated in an independent test set.ResultRegarding prediction of responses to atezolizumab within esophageal adenocarcinoma (EAC) patients, ELISE demonstrated a superior accuracy (Area Under Curve [AUC] = 100.00%). AC005786.3 (Mean [|SHAP value|] = 0.0097) was distinguished as the most valuable contributor to ELISE output, followed by SNORD3D (0.0092), RN7SKP72 (0.0081), EREG (0.0069), IGHV4-80 (0.0063), and MIR4526 (0.0063). Mechanistically, immunoglobulin complex, immunoglobulin production, adaptive immune response, antigen binding and others, were downregulated in ELISE-neg EAC subtypes and resulted in unfavorable responses. More encouragingly, ELISE could be extended to accurately estimate the responsiveness of various immunotherapeutic agents against other cancers, including PD1/PD-L1 suppressor against metastatic urothelial cancer (AUC = 88.86%), and MAGE−A3 immunotherapy against metastatic melanoma (AUC = 100.00%).DiscussionThis study presented deep insights into integrating ensemble deep learning with self-attention as a mechanism for predicting immunotherapy responses to human cancers, highlighting ELISE as a potential tool to generate reliable approaches to individualized treatment.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Ensemble deep learning enhanced with self-attention for predicting immunotherapeutic responses to cancers

et al. 2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…Moreover, it is a key contributor to pain, poorer health status and life quality, productivity and activity impairments. In addition, the presence of depression, often linked to pain, and more evident in the face of severe pain [19,20] may increase the risk for restless sleep among cases with osteoarthritis of the knee [21], and according to Furlough et al [10] many reports state that osteoarthritis, the most common joint disease, often produces lengthy periods of chronically intractable joint stiffness and swelling, as well as multiple functional, social, occupational, and emotional challenges and restrictions, as well as feelings of depression that flow from this [19,20]. Depressive presence may also impact surgical outcomes negatively [6], as well as sleep disturbances, overweight or obesity, pain, plus the presence of comorbid health conditions [22], hence surgeons and others have been increasingly encouraged not to neglect to screen for any undue depressive manifestations in their osteoarthritis clients [23], especially in light of the possible associations between a subject's psychological profile and their somatosensory function and brain structure [30].…”

Section: Resultsmentioning

confidence: 99%

Osteoarthritis Depression Impacts and Possible Solutions Among Older Adults: Year 2021-2022 in Review

Marks

2022

JARH

View full text Add to dashboard Cite

Background Osteoarthritis, a serious joint disease, said to represent a generally declining state of wellbeing and function among many older adults has been shown to be affected to a considerable degree by various negative beliefs and inactions rather than degradation alone. Aim This review examines the case of depression as this pertains to the older adult with osteoarthritis of one or more joints. Specifically, the most up to date information on this topic was sought, as care improvements over the past decade have not shown any impactful population wide results. Method Reviewed were relevant 2021-2022 research and review articles specifically pertaining to what is being observed currently by researchers as far as osteoarthritis-depression linkages goes, as these may reveal opportunities for more profound research, and practice-based endeavors. Results In line with 60 years of prior research, it appears a clinically important role for depression in some osteoarthritis cases cannot be ruled out. It further appears that if detected and addressed early on, many older adults suffering from osteoarthritis may yet be enabled to lead a quality life, rather than a distressing and excessively impaired state of being. Those older osteoarthritis cases requiring surgery who suffer from concomitant depressive symptoms are likely to be disadvantaged in the absence of efforts to treat and identify this psychosocial disease correlate. Conclusion Providers and researchers are encouraged to pursue this line of inquiry and begin to map clinical osteoarthritis measures with those that can track cognitive patterns, musculoskeletal, features and inflammatory reactions along with valid depression indicators among carefully selected osteoarthritis sub groups.

show abstract

“…The Irish Longitudinal Study on Ageing (TILDA) is a comprehensive, longitudinal study that focuses on ageing in Ireland. This research is nationally representative and involves two waves of demographically representative data, with participants aged 50 years and above who were selected using a geographic cohort-based RANSAM sampling system 13–15. We used TILDA data to create an ensemble learning model that provides an interpretation for predicting the risk of both type 1 and type 2 diabetes based on the clinical parameters of older individuals.…”

Section: Introductionmentioning

confidence: 99%

Tailored machine learning for evaluating the long-term diabetes risk in older individuals: findings from the Irish Longitudinal Study on Ageing (TILDA)

Xu,

Mingyang,

Yang

et al. 2023

BMJ Open

Self Cite

View full text Add to dashboard Cite

ObjectivesThe prevalence of diabetes has increased globally, leading to a significant disease burden and financial cost. Early prediction is crucial to control its prevalence.DesignA prospective cohort study.SettingNational representative study on Irish.Participants8504 individuals aged 50 years or older were included.Primary and secondary outcome measuresSurveys were conducted to collect over 40 000 variables related to social, financial, health, mental and family status. Feature selection was performed using logistic regression. Different machine/deep learning algorithms were trained, including distributed random forest, extremely randomised trees, a generalised linear model with regularisation, a gradient boosting machine and a deep neural network. These algorithms were integrated into a stacked ensemble to generate the best model. The model was tested using various metrics, such as the area under the curve (AUC), log loss, mean per classification error, mean square error (MSE) and root MSE (RMSE). The SHapley Additive exPlanations (SHAP) method was used to interpret the established model.ResultsAfter 2 years, 105 baseline features were identified as major contributors to diabetes risk, including sex, low-density lipoprotein cholesterol and cirrhosis. The best model achieved high accuracy, robustness and discrimination in predicting diabetes risk, with an AUC of 0.854, log loss of 0.187, mean per classification error of 0.267, RMSE of 0.229 and MSE of 0.052 in the independent test set. The model was also shown to be well calibrated. The SHAP algorithm provided insights into the decision-making process of the model.ConclusionsThese findings could help physicians in the early identification of high-risk patients and implement targeted interventions to reduce diabetes incidence.

show abstract

The Effect of Individual Musculoskeletal Conditions on Depression: Updated Insights From an Irish Longitudinal Study on Aging

Cited by 11 publications

References 56 publications

Ensemble deep learning enhanced with self-attention for predicting immunotherapeutic responses to cancers

Ensemble deep learning enhanced with self-attention for predicting immunotherapeutic responses to cancers

Osteoarthritis Depression Impacts and Possible Solutions Among Older Adults: Year 2021-2022 in Review

Tailored machine learning for evaluating the long-term diabetes risk in older individuals: findings from the Irish Longitudinal Study on Ageing (TILDA)

Contact Info

Product

Resources

About