scholarly journals Application of Machine Learning for Diagnosis of Head and Neck Cancer in Primary Healthcare Organisation

2020 ◽  
Vol 5 (4) ◽  
pp. 489-493
Author(s):  
Olatunbosun Olabode ◽  
Adebayo O. Adetunmbi ◽  
Folake Akinbohun ◽  
Ambrose Akinbohun
Keyword(s):  
Machine Learning ◽  
Head And Neck Cancer ◽  
Decision Tree ◽  
Head And Neck ◽  
Neck Cancer ◽  
Learning Algorithm ◽  
Late Presentation ◽  
Healthcare Organisation ◽  
K Nearest Neighbors ◽  
Supervised Learning Algorithms

Head and neck cancers (HNC) are indicated when cells grow abnormally.  The disturbing rate of morbidity and mortality of patients with HNC due to late presentation is on the increase especially in Africa (developing countries). There is need to diagnose head and neck cancer early if patients present so that prompt referral could be facilitated.  The collected data consists of 1473 instances with 18 features. The dataset was divided into training and test data.  Two supervised learning algorithms were deployed for the study namely: Decision Tree (C4.5) and k-Nearest Neighbors (KNN). It showed that Decision Tree outperformed with accuracy of 91.40% while KNN had accuracy of 88.24%. Hence, machine learning algorithm like Decision Tree can be used for diagnosis of HNC in healthcare organisations.

scholarly journals CLASSIFICATION OF HEAD AND NECK CANCER TYPES USING MACHINE LEARNING ALGORITHM

2020 ◽  
pp. 198-205
Author(s):  
Prof O. Olabode ◽  
Prof A. O. Adetunmbi ◽  
Folake Akinbohun ◽  
Dr Ambrose Akinbohun
Keyword(s):  
Machine Learning ◽  
Head And Neck Cancer ◽  
Head And Neck ◽  
Neck Cancer ◽  
Naive Bayes ◽  
Information Gain ◽  
Learning Algorithm ◽  
Naïve Bayes ◽  
Machine Learning Algorithms ◽  
Chi Square

The worldwide incidence of head and neck cancer exceeds half a million cases annually. The morbidity and mortality of head and neck cancers considering thyroid, nasopharyngeal, sinonasal and laryngeal were reported high. The degree of facial disfigurement is unrivalled. Information Gain and Chi Square, Decision and Naïve Bayes were deployed for the study. The dataset was divided into training and test data. The results showed that the performance of Naïve Bayes outperformed Decision Trees. With the application of machine learning algorithms, head and neck cancer can be classified. KEYWORDS: Head and Neck, thyroid, Chi Square, Information Gain

scholarly journals Establishing a head and neck unit in a developing country

2012 ◽  
Vol 126 (6) ◽  
pp. 552-555 ◽  
Author(s):  
J Aswani ◽  
K Baidoo ◽  
J Otiti
Keyword(s):  
Head And Neck Cancer ◽  
Head And Neck ◽  
Neck Cancer ◽  
Late Presentation ◽  
Care Staff ◽  
Health Care Staff ◽  
Cancer Awareness ◽  
African Countries ◽  
Sub Saharan ◽  
University Of Cape Town

AbstractHead and neck cancers pose an especially serious problem in developing countries due to late presentation requiring complex surgical intervention. These countries are faced with many challenges, ranging from insufficient health care staff to problems with peri-operative requirements, diagnostic facilities, chemoradiation services and research funding.These challenges can be addressed through the training of head and neck surgeons and support personnel, the improvement of cancer awareness in local communities, and the establishment of dedicated head and neck institutes which focus on the special needs of head and neck cancer patients.All these changes can best be achieved through collaborative efforts with external partners. The Karl Storz Fellowship in Advanced Head and Neck Cancer, enabling training at the University of Cape Town, South Africa, has served as a springboard towards establishing head and neck services in developing sub-Saharan African countries.

scholarly journals Machine Learning–Guided Adjuvant Treatment of Head and Neck Cancer

2020 ◽  
Vol 3 (11) ◽  
pp. e2025881
Author(s):  
Frederick Matthew Howard ◽  
Sara Kochanny ◽  
Matthew Koshy ◽  
Michael Spiotto ◽  
Alexander T. Pearson
Keyword(s):  
Machine Learning ◽  
Head And Neck Cancer ◽  
Head And Neck ◽  
Neck Cancer ◽  
Adjuvant Treatment

scholarly journals Machine Learning for Head and Neck Cancer: A Safe Bet?—A Clinically Oriented Systematic Review for the Radiation Oncologist

2021 ◽  
Vol 11 ◽  
Author(s):  
Stefania Volpe ◽  
Matteo Pepa ◽  
Mattia Zaffaroni ◽  
Federica Bellerba ◽  
Riccardo Santamaria ◽  
...  
Keyword(s):  
Machine Learning ◽  
Systematic Review ◽  
Head And Neck Cancer ◽  
Head And Neck ◽  
Treatment Planning ◽  
Neck Cancer ◽  
Radiation Oncology ◽  
Imaging Modality ◽  
Oncological Outcome ◽  
Image Features

Background and PurposeMachine learning (ML) is emerging as a feasible approach to optimize patients’ care path in Radiation Oncology. Applications include autosegmentation, treatment planning optimization, and prediction of oncological and toxicity outcomes. The purpose of this clinically oriented systematic review is to illustrate the potential and limitations of the most commonly used ML models in solving everyday clinical issues in head and neck cancer (HNC) radiotherapy (RT).Materials and MethodsElectronic databases were screened up to May 2021. Studies dealing with ML and radiomics were considered eligible. The quality of the included studies was rated by an adapted version of the qualitative checklist originally developed by Luo et al. All statistical analyses were performed using R version 3.6.1.ResultsForty-eight studies (21 on autosegmentation, four on treatment planning, 12 on oncological outcome prediction, 10 on toxicity prediction, and one on determinants of postoperative RT) were included in the analysis. The most common imaging modality was computed tomography (CT) (40%) followed by magnetic resonance (MR) (10%). Quantitative image features were considered in nine studies (19%). No significant differences were identified in global and methodological scores when works were stratified per their task (i.e., autosegmentation).Discussion and ConclusionThe range of possible applications of ML in the field of HN Radiation Oncology is wide, albeit this area of research is relatively young. Overall, if not safe yet, ML is most probably a bet worth making.

Sign in / Sign up

Export Citation Format

Share Document