Remote assessment of cognition and quality of life following radiotherapy for nasopharyngeal carcinoma: deep-learning-based predictive models and MRI correlates.
Noor Shatirah Voon, Hanani Abdul Manan, Noorazrul Yahya
{"title":"Remote assessment of cognition and quality of life following radiotherapy for nasopharyngeal carcinoma: deep-learning-based predictive models and MRI correlates.","authors":"Noor Shatirah Voon, Hanani Abdul Manan, Noorazrul Yahya","doi":"10.1007/s11764-023-01371-8","DOIUrl":null,"url":null,"abstract":"<p><strong>Purpose: </strong>Irradiation of the brain regions from nasopharyngeal carcinoma (NPC) radiotherapy (RT) is frequently unavoidable, which may result in radiation-induced cognitive deficit. Using deep learning (DL), the study aims to develop prediction models in predicting compromised cognition in patients following NPC RT using remote assessments and determine their relation to the quality of life (QoL) and MRI changes.</p><p><strong>Methods: </strong>Seventy patients (20-76 aged) with MRI imaging (pre- and post-RT (6 months-1 year)) and complete cognitive assessments were recruited. Hippocampus, temporal lobes (TLs), and cerebellum were delineated and dosimetry parameters were extracted. Assessments were given post-RT via telephone (Telephone Interview Cognitive Status (TICS), Telephone Montreal Cognitive Assessment (T-MoCA), Telephone Mini Addenbrooke's Cognitive Examination (Tele-MACE), and QLQ-H&N 43). Regression and deep neural network (DNN) models were used to predict post-RT cognition using anatomical and treatment dose features.</p><p><strong>Results: </strong>Remote cognitive assessments were inter-correlated (r > 0.9). TLs showed significance in pre- and post-RT volume differences and cognitive deficits, that are correlated with RT-associated volume atrophy and dose distribution. Good classification accuracy based on DNN area under receiver operating curve (AUROC) for cognitive prediction (T-MoCA AUROC = 0.878, TICS AUROC = 0.89, Tele-MACE AUROC = 0.919).</p><p><strong>Conclusion: </strong>DL-based prediction models assessed using remote assessments can assist in predicting cognitive deficit following NPC RT. Comparable results of remote assessments in assessing cognition suggest its possibility in replacing standard assessments.</p><p><strong>Implications for cancer survivors: </strong>Application of prediction models in individual patient enables tailored interventions to be provided in managing cognitive changes following NPC RT.</p>","PeriodicalId":15284,"journal":{"name":"Journal of Cancer Survivorship","volume":null,"pages":null},"PeriodicalIF":3.1000,"publicationDate":"2024-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10069366/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Cancer Survivorship","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1007/s11764-023-01371-8","RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2023/4/3 0:00:00","PubModel":"Epub","JCR":"Q2","JCRName":"ONCOLOGY","Score":null,"Total":0}
引用次数: 0
Abstract
Purpose: Irradiation of the brain regions from nasopharyngeal carcinoma (NPC) radiotherapy (RT) is frequently unavoidable, which may result in radiation-induced cognitive deficit. Using deep learning (DL), the study aims to develop prediction models in predicting compromised cognition in patients following NPC RT using remote assessments and determine their relation to the quality of life (QoL) and MRI changes.
Methods: Seventy patients (20-76 aged) with MRI imaging (pre- and post-RT (6 months-1 year)) and complete cognitive assessments were recruited. Hippocampus, temporal lobes (TLs), and cerebellum were delineated and dosimetry parameters were extracted. Assessments were given post-RT via telephone (Telephone Interview Cognitive Status (TICS), Telephone Montreal Cognitive Assessment (T-MoCA), Telephone Mini Addenbrooke's Cognitive Examination (Tele-MACE), and QLQ-H&N 43). Regression and deep neural network (DNN) models were used to predict post-RT cognition using anatomical and treatment dose features.
Results: Remote cognitive assessments were inter-correlated (r > 0.9). TLs showed significance in pre- and post-RT volume differences and cognitive deficits, that are correlated with RT-associated volume atrophy and dose distribution. Good classification accuracy based on DNN area under receiver operating curve (AUROC) for cognitive prediction (T-MoCA AUROC = 0.878, TICS AUROC = 0.89, Tele-MACE AUROC = 0.919).
Conclusion: DL-based prediction models assessed using remote assessments can assist in predicting cognitive deficit following NPC RT. Comparable results of remote assessments in assessing cognition suggest its possibility in replacing standard assessments.
Implications for cancer survivors: Application of prediction models in individual patient enables tailored interventions to be provided in managing cognitive changes following NPC RT.
期刊介绍:
Cancer survivorship is a worldwide concern. The aim of this multidisciplinary journal is to provide a global forum for new knowledge related to cancer survivorship. The journal publishes peer-reviewed papers relevant to improving the understanding, prevention, and management of the multiple areas related to cancer survivorship that can affect quality of care, access to care, longevity, and quality of life. It is a forum for research on humans (both laboratory and clinical), clinical studies, systematic and meta-analytic literature reviews, policy studies, and in rare situations case studies as long as they provide a new observation that should be followed up on to improve outcomes related to cancer survivors. Published articles represent a broad range of fields including oncology, primary care, physical medicine and rehabilitation, many other medical and nursing specialties, nursing, health services research, physical and occupational therapy, public health, behavioral medicine, psychology, social work, evidence-based policy, health economics, biobehavioral mechanisms, and qualitative analyses. The journal focuses exclusively on adult cancer survivors, young adult cancer survivors, and childhood cancer survivors who are young adults. Submissions must target those diagnosed with and treated for cancer.