scholarly journals Characterizing Artificial Intelligence Applications in Cancer Research using Latent Dirichlet Allocation (Preprint)

2019 ◽  
Author(s):  
Bach Xuan Tran ◽  
Carl A. Latkin ◽  
Noha Sharafeldin ◽  
Katherina Nguyen ◽  
Giang Thu Vu ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Cancer Research ◽  
Latent Dirichlet Allocation ◽  
Similarity Index ◽  
Cancer Control ◽  
Clinical Practices ◽  
Global Trends ◽  
Patient Reported ◽  
Dirichlet Allocation

BACKGROUND Artificial Intelligence (AI) - based therapeutics, devices and systems are vital innovations in cancer control. OBJECTIVE This study analyzes the global trends, patterns, and development of interdisciplinary landscapes in AI and cancer research. METHODS Exploratory factor analysis was applied to identify research domains emerging from contents of the abstracts. Jaccard’s similarity index was utilized to identify terms most frequently co-occurring with each other. Latent Dirichlet Allocation was used for classifying papers into corresponding topics. RESULTS The number of studies applying AI to cancer during 1991-2018 has been grown with 3,555 papers covering therapeutics, capacities, and factors associated with outcomes. Topics with the highest volumes of publications include 1) Machine learning, 2) Comparative Effectiveness Evaluation of AI-assisted medical therapies, 3) AI-based Prediction. Noticeably, this classification has revealed topics examining the incremental effectiveness of AI applications, the quality of life and functioning of patients receiving these innovations. The growing research productivity and expansion of multidisciplinary approaches, largely driven by machine learning, artificial neutral network, and artificial intelligence in various clinical practices. CONCLUSIONS The research landscapes show that the development of AI in cancer is focused not only on improving prediction in cancer screening and AI-assisted therapeutics, but also other corresponding areas such as Precision and Personalized Medicine and patient-reported outcomes.

scholarly journals Characterizing Artificial Intelligence Applications in Cancer Research: A Latent Dirichlet Allocation Analysis

10.2196/14401 ◽  
2019 ◽  
Vol 7 (4) ◽  
pp. e14401 ◽  
Author(s):  
Bach Xuan Tran ◽  
Carl A Latkin ◽  
Noha Sharafeldin ◽  
Katherina Nguyen ◽  
Giang Thu Vu ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Cancer Research ◽  
Cancer Care ◽  
Latent Dirichlet Allocation ◽  
Similarity Index ◽  
Cancer Control ◽  
Clinical Practices ◽  
Patient Reported ◽  
Dirichlet Allocation

Background Artificial intelligence (AI)–based therapeutics, devices, and systems are vital innovations in cancer control; particularly, they allow for diagnosis, screening, precise estimation of survival, informing therapy selection, and scaling up treatment services in a timely manner. Objective The aim of this study was to analyze the global trends, patterns, and development of interdisciplinary landscapes in AI and cancer research. Methods An exploratory factor analysis was conducted to identify research domains emerging from abstract contents. The Jaccard similarity index was utilized to identify the most frequently co-occurring terms. Latent Dirichlet Allocation was used for classifying papers into corresponding topics. Results From 1991 to 2018, the number of studies examining the application of AI in cancer care has grown to 3555 papers covering therapeutics, capacities, and factors associated with outcomes. Topics with the highest volume of publications include (1) machine learning, (2) comparative effectiveness evaluation of AI-assisted medical therapies, and (3) AI-based prediction. Noticeably, this classification has revealed topics examining the incremental effectiveness of AI applications, the quality of life, and functioning of patients receiving these innovations. The growing research productivity and expansion of multidisciplinary approaches are largely driven by machine learning, artificial neural networks, and AI in various clinical practices. Conclusions The research landscapes show that the development of AI in cancer care is focused on not only improving prediction in cancer screening and AI-assisted therapeutics but also on improving other corresponding areas such as precision and personalized medicine and patient-reported outcomes.

scholarly journals Modeling Research Topics for Artificial Intelligence Applications in Medicine: Latent Dirichlet Allocation Application Study

10.2196/15511 ◽  
2019 ◽  
Vol 21 (11) ◽  
pp. e15511 ◽  
Author(s):  
Bach Xuan Tran ◽  
Son Nghiem ◽  
Oz Sahin ◽  
Tuan Manh Vu ◽  
Giang Hai Ha ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Health Care ◽  
Precision Medicine ◽  
Data Science ◽  
Latent Dirichlet Allocation ◽  
Developed Countries ◽  
Theory And Practice ◽  
Clinical Practices ◽  
Research Topics ◽  
Dirichlet Allocation

Background Artificial intelligence (AI)–based technologies develop rapidly and have myriad applications in medicine and health care. However, there is a lack of comprehensive reporting on the productivity, workflow, topics, and research landscape of AI in this field. Objective This study aimed to evaluate the global development of scientific publications and constructed interdisciplinary research topics on the theory and practice of AI in medicine from 1977 to 2018. Methods We obtained bibliographic data and abstract contents of publications published between 1977 and 2018 from the Web of Science database. A total of 27,451 eligible articles were analyzed. Research topics were classified by latent Dirichlet allocation, and principal component analysis was used to identify the construct of the research landscape. Results The applications of AI have mainly impacted clinical settings (enhanced prognosis and diagnosis, robot-assisted surgery, and rehabilitation), data science and precision medicine (collecting individual data for precision medicine), and policy making (raising ethical and legal issues, especially regarding privacy and confidentiality of data). However, AI applications have not been commonly used in resource-poor settings due to the limit in infrastructure and human resources. Conclusions The application of AI in medicine has grown rapidly and focuses on three leading platforms: clinical practices, clinical material, and policies. AI might be one of the methods to narrow down the inequality in health care and medicine between developing and developed countries. Technology transfer and support from developed countries are essential measures for the advancement of AI application in health care in developing countries.

AI-Enabled Support System for Melanoma Detection and Classification

2021 ◽  
Vol 10 (4) ◽  
pp. 58-75
Author(s):  
Vivek Sen Saxena ◽  
Prashant Johri ◽  
Avneesh Kumar
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Skin Lesion ◽  
Performance Metrics ◽  
Similarity Index ◽  
Skin Lesions ◽  
Machine Learning Algorithms ◽  
Lesion Area ◽  
Melanoma Detection ◽  
Grabcut Algorithm

Skin lesion melanoma is the deadliest type of cancer. Artificial intelligence provides the power to classify skin lesions as melanoma and non-melanoma. The proposed system for melanoma detection and classification involves four steps: pre-processing, resizing all the images, removing noise and hair from dermoscopic images; image segmentation, identifying the lesion area; feature extraction, extracting features from segmented lesion and classification; and categorizing lesion as malignant (melanoma) and benign (non-melanoma). Modified GrabCut algorithm is employed to generate skin lesion. Segmented lesions are classified using machine learning algorithms such as SVM, k-NN, ANN, and logistic regression and evaluated on performance metrics like accuracy, sensitivity, and specificity. Results are compared with existing systems and achieved higher similarity index and accuracy.

scholarly journals A Latent Dirichlet Allocation and Fuzzy Clustering Based Machine Learning Model for Text Thesaurus

2020 ◽  
Vol 15 (2) ◽  
Author(s):  
Jia Luo ◽  
Dongwen Yu ◽  
Zong Dai
Keyword(s):  
Machine Learning ◽  
Fuzzy Clustering ◽  
Latent Dirichlet Allocation ◽  
Learning Model ◽  
Machine Learning Algorithms ◽  
Text Data ◽  
Huge Data ◽  
Machine Learning Model ◽  
N Gram ◽  
Dirichlet Allocation

It is not quite possible to use manual methods to process the huge amount of structured and semi-structured data. This study aims to solve the problem of processing huge data through machine learning algorithms. We collected the text data of the company’s public opinion through crawlers, and use Latent Dirichlet Allocation (LDA) algorithm to extract the keywords of the text, and uses fuzzy clustering to cluster the keywords to form different topics. The topic keywords will be used as a seed dictionary for new word discovery. In order to verify the efficiency of machine learning in new word discovery, algorithms based on association rules, N-Gram, PMI, andWord2vec were used for comparative testing of new word discovery. The experimental results show that the Word2vec algorithm based on machine learning model has the highest accuracy, recall and F-value indicators.

scholarly journals Modern Probabilistic Model: Filtering Massive Data in E-learning

2021 ◽  
pp. 52-58
Author(s):  
Hachem Harouni Alaoui ◽  
Elkaber Hachem ◽  
Cherif Ziti
Keyword(s):  
Machine Learning ◽  
Probabilistic Model ◽  
Latent Dirichlet Allocation ◽  
Web Pages ◽  
Massive Data ◽  
Learning Session ◽  
Learning Procedure ◽  
E Learning ◽  
Dirichlet Allocation

So muchinformation keeps on being digitized and stored in several forms, web pages, scientific articles, books, etc. so the mission of discovering information has become more and more challenging. The requirement for new IT devices to retrieve and arrange these vastamounts of informationaregrowing step by step. Furthermore, platforms of e-learning are developing to meet the intended needsof students.The aim of this article is to utilize machine learning to determine the appropriate actions that support the learning procedure and the Latent Dirichlet Allocation (LDA) so as to find the topics contained in the connections proposed in a learning session. Ourpurpose is also to introduce a course which moves toward the student's attempts and which reduces the unimportant recommendations (Which aren’t proper to the need of the student grown-up) through the modeling algorithms of the subjects.

scholarly journals Applying Text Mining, Clustering Analysis, and Latent Dirichlet Allocation Techniques for Topic Classification of Environmental Education Journals

2021 ◽  
Vol 13 (19) ◽  
pp. 10856
Author(s):  
I-Cheng Chang ◽  
Tai-Kuei Yu ◽  
Yu-Jie Chang ◽  
Tai-Yi Yu
Keyword(s):  
Artificial Intelligence ◽  
Cluster Analysis ◽  
Text Mining ◽  
Environmental Education ◽  
Hierarchical Clustering ◽  
Language Processing ◽  
Latent Dirichlet Allocation ◽  
Word Analysis ◽  
Dirichlet Allocation

Facing the big data wave, this study applied artificial intelligence to cite knowledge and find a feasible process to play a crucial role in supplying innovative value in environmental education. Intelligence agents of artificial intelligence and natural language processing (NLP) are two key areas leading the trend in artificial intelligence; this research adopted NLP to analyze the research topics of environmental education research journals in the Web of Science (WoS) database during 2011–2020 and interpret the categories and characteristics of abstracts for environmental education papers. The corpus data were selected from abstracts and keywords of research journal papers, which were analyzed with text mining, cluster analysis, latent Dirichlet allocation (LDA), and co-word analysis methods. The decisions regarding the classification of feature words were determined and reviewed by domain experts, and the associated TF-IDF weights were calculated for the following cluster analysis, which involved a combination of hierarchical clustering and K-means analysis. The hierarchical clustering and LDA decided the number of required categories as seven, and the K-means cluster analysis classified the overall documents into seven categories. This study utilized co-word analysis to check the suitability of the K-means classification, analyzed the terms with high TF-IDF wights for distinct K-means groups, and examined the terms for different topics with the LDA technique. A comparison of the results demonstrated that most categories that were recognized with K-means and LDA methods were the same and shared similar words; however, two categories had slight differences. The involvement of field experts assisted with the consistency and correctness of the classified topics and documents.

scholarly journals The Current Research Landscape on the Artificial Intelligence Application in the Management of Depressive Disorders: A Bibliometric Analysis

2019 ◽  
Vol 16 (12) ◽  
pp. 2150 ◽  
Author(s):  
Bach Xuan Tran ◽  
Roger S. McIntyre ◽  
Carl A. Latkin ◽  
Hai Thanh Phan ◽  
Giang Thu Vu ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Factor Analysis ◽  
Bibliometric Analysis ◽  
Exploratory Factor Analysis ◽  
Depressive Disorders ◽  
Latent Dirichlet Allocation ◽  
Rapid Development ◽  
The United States ◽  
Research Network ◽  
Dirichlet Allocation

Artificial intelligence (AI)-based techniques have been widely applied in depression research and treatment. Nonetheless, there is currently no systematic review or bibliometric analysis in the medical literature about the applications of AI in depression. We performed a bibliometric analysis of the current research landscape, which objectively evaluates the productivity of global researchers or institutions in this field, along with exploratory factor analysis (EFA) and latent dirichlet allocation (LDA). From 2010 onwards, the total number of papers and citations on using AI to manage depressive disorder have risen considerably. In terms of global AI research network, researchers from the United States were the major contributors to this field. Exploratory factor analysis showed that the most well-studied application of AI was the utilization of machine learning to identify clinical characteristics in depression, which accounted for more than 60% of all publications. Latent dirichlet allocation identified specific research themes, which include diagnosis accuracy, structural imaging techniques, gene testing, drug development, pattern recognition, and electroencephalography (EEG)-based diagnosis. Although the rapid development and widespread use of AI provide various benefits for both health providers and patients, interventions to enhance privacy and confidentiality issues are still limited and require further research.

Global trends of COVID-19 research in cancer: A scientometric study.

2021 ◽  
Vol 39 (15_suppl) ◽  
pp. e13549-e13549
Author(s):  
Noha Sharafeldin ◽  
Hai Quang Pham ◽  
Long Hoang Nguyen ◽  
Giang Thu Vu ◽  
Trang Huyen ◽  
...  
Keyword(s):  
Cancer Patients ◽  
Latent Dirichlet Allocation ◽  
Citation Rate ◽  
Treatment Options ◽  
Descriptive Analysis ◽  
Similarity Index ◽  
Individual Risk ◽  
Middle Income ◽  
Global Trends ◽  
Individual Risk Factors

e13549 Background: The scientific literature experienced an unprecedented growth in archived pre-prints and peer-reviewed COVID-19 related publications with regional variations making the task of synthesizing the information burdensome. This study aims to characterize global patterns and domains of COVID-19 research in cancer. Methods: We used the NIH COVID-19 portfolio and Web of Science (WOS) curated databases to extract abstracts using standard search terms for COVID-19 and cancer between Nov 1 2019 and Dec 31 2020. A total of 21,325 publications matched the study search criteria (NIH: 18,029 records; WOS: 3512 records; 204 records overlapped). We performed a descriptive analysis to calculate country citations and intercountry collaboration networks. The Jaccard similarity index was utilized to identify the most frequently co-occurring terms. Latent Dirichlet Allocation (LDA) was used for classifying publications into corresponding research topics. Results: The most productive period was May 2020 with 3,181 published articles, mean citation rate per paper was highest in Jan 2020 (1,620.5) followed by Feb 2020 (236.7), highest mean use rate in the last 12 months was March 2020. Top productive countries are classified as High and Upper Middle-income countries, 17% of research contributed by USA, 12% by China PR, and 11.4% by Italy. Linkage between top 30 productive countries show USA, Italy, and England with the highest inter-country co-ordination. Analysis of keywords co-occurring at least 5 times resulted in 12 major clusters including: 1) cancer treatment and mortality; 2) inflammation and immunology; 3) chronic diseases and co-morbidities; and 4) mental health and social psychology. Ranked topics with the highest volume of publications include 1) effect of COVID-19 on treatment outcomes; 2) individual risk factors of COVID-19 severity and mortality, and 3) novel treatment options relevant to cancer patients [Table]. Growth of articles peaked between Mar and Apr 2020 with a steady decline across all topics in Sept 2020. Conclusions: Global cancer –related research productivity peaked following the declaration of the pandemic and first wave in Mar- Apr 2020. Systematic synthesis of a large volume of COVID-19 literature revealed the global research landscape highlighting focus on the study of outcomes in cancer patients.[Table: see text]

Sign in / Sign up

Export Citation Format

Share Document