http://ojs.ais.cn/jaims <p>The <em><strong>Journal of Artificial Intelligence for Medical Sciences </strong></em>(<strong>JAIMS,</strong> <strong>Online ISSN 2666-1470</strong>) is an international peer reviewed journal that covers all aspects of theoretical, methodological and applied artificial intelligence (AI) for medical sciences, healthcare and life sciences.</p> <p>The Editors welcome original research articles, comprehensive reviews, correspondences and perspectives that provide novel insights into diagnostics, drug development, care processes, treatment personalization with the support of machine/deep learning, data science, natural language processing (NLP), etc.</p> <p>Research areas covered in the journal include, but are not limited to, the following:</p> <ul> <li>Precision medicine</li> <li>Semantic technology for medicine</li> <li>Medical knowledge graphs and ontologies</li> <li>Machine learning and deep learning for medicine</li> <li>AI in bio-informatics</li> <li>AI for mental health</li> <li>NLP for medical data processing</li> <li>Medical data mining</li> <li>Ontology/knowledge engineering for medicine</li> <li>AI for patient data processing and management</li> <li>Epidemic outbreak prediction</li> <li>(Bio-)medical knowledge acquisition and management</li> <li>Computerized clinical practice / clinical guidelines (CPGs) and protocols</li> <li>Biomedical imaging and signal processing</li> <li>Visual analytics in biomedicine</li> <li>Clinical decision support systems (CDSS)</li> <li>Drug discovery</li> <li>Case prioritization</li> <li>Chatbots in medical science</li> <li>AI in gene editing</li> </ul> <h2> </h2> <h2 id="open-access-and-publication-fees">Open Access</h2> <p>This is an <strong>open access</strong> journal, i.e. all articles are immediately and permanently free to read, download, copy &amp; distribute. The journal is published under the <a href="https://creativecommons.org/licenses/by-nc/4.0/" target="_blank" rel="noopener"><strong>CC BY-NC 4.0</strong></a> user license which defines the permitted 3rd-party reuse of its articles. Publication in this journal is <strong>free of charge</strong> for Authors. All open access publication fees are subsidized by Guangdong AiScholar Institute of Academic Exchange (GDAIAE) . Note that this is a <em>promotional offer</em> which applies to all papers submitted before <strong>31 December 2022</strong>.</p> <h2> </h2> <h2 id="indexation">Indexation</h2> <p>The <em>Journal of Artificial Intelligence for Medical Sciences</em> is currently indexed in <strong>Ulrich's Periodicals Directory</strong> (Ulrichsweb), <strong>Google Scholar</strong>, the <strong>China National Knowledge Infrastructure</strong> (CNKI) and <strong>Wanfang Data</strong>.</p> en-US <p>This is an open access article distributed under the CC BY-NC 4.0 license (<a class="ext-link" href="http://creativecommons.org/licenses/by-nc/4.0/">http://creativecommons.org/licenses/by-nc/4.0/</a>).</p> ping.du@ais.cn (Ping DU) gongwenshi@ais.cn (Wenshi Gong) Wed, 28 Dec 2022 00:00:00 +0800 OJS 3.3.0.8 http://blogs.law.harvard.edu/tech/rss 60 http://ojs.ais.cn/jaims/article/view/80 In recent years the skin microbiome has taken center stage as drug target and as disease biomarker. Computational analyses of microbiome sequencing data from patients with skin diseases, for example seborrheic dermatitis, can be performed to identify discriminative biomarkers in the microbiome profile. The aim of the present study was twofold, namely to employ machine learning to predict disease from the microbiome dataset, and to identify discriminative biomarkers in the microbiome of patients with seborrheic dermatitis versus healthy controls using machine learning techniques. The population consisted of 97 patients with seborrheic dermatitis and 763 healthy controls. Skin swabs were taken from naso-labial fold (lesional skin: n = 22; non-lesional skin: n = 75, controls: n = 763). Using an extra trees machine learning model, differences between the skin microbiome of patients with seborrheic dermatitis versus healthy controls were characterized. Subsequently, the most important microorganisms for discrimination were determined by feature analysis and SHapley Additive exPlanations (SHAP) values. The accuracy of the prediction models to discriminate between skin affected by seborrheic dermatitis and facial skin from healthy subjects was 77% and the ROC-AUC was 83%. Next to Cutibacterium and Staphylococcus, the most important organisms for discrimination had a relatively low occurrence. Our study showed that machine learning can be utilized to identify discriminating biomarkers in the microbiome skin. This indicates that machine learning can be of major importance in basic skin research, and in the discovery and development of new individualized therapies, involving the microbiome. H.E.C. van der Wall, R.J. Doll, G.J.P. van Westen, T. Niemeyer-van der Kolk, G. Feiss, H. Pinckaers, M.B.A. van Doorn, T. Nijsten, M.G.H. Sanders, A.F. Cohen, J. Burggraaf, R. Rissmann, L.M. Pardo Copyright (c) 2022 H.E.C. van der Wall, R.J. Doll, G.J.P. van Westen, T. Niemeyer-van der Kolk, G. Feiss, H. Pinckaers, M.B.A. van Doorn, T. Nijsten, M.G.H. Sanders, A.F. Cohen, J. Burggraaf, R. Rissmann, L.M. Pardo http://creativecommons.org/licenses/by-nc/4.0/ http://ojs.ais.cn/jaims/article/view/80 Tue, 06 Sep 2022 00:00:00 +0800 http://ojs.ais.cn/jaims/article/view/82 Electronic medical records (EMR) of Traditional Chinese Medicine (TCM) contain rich contents such as chief complaints, subcutaneous symptoms, history of present illness, and past medical history, which are important reference bases for TCM diagnosis. However, there are a lot of terminology and expression irregularities since this information is frequently conveyed in natural language. In this paper, we propose a method to normalize the textual information of EMR of TCM and select the text of medical history with a strong narrative such as the history of present illness and past medical history, as well as the text of symptoms such as chief complaints and subcutaneous symptoms as the main research object. The text is then processed separately according to the type of text. For symptom texts such as chief complaints and subcutaneous symptoms, named entity recognition technology is directly applied to extract symptom entities directly; for medical history texts such as the history of present illness and past medical history, event extraction is performed first to divide the treatment events, and then named entity recognition technology is applied to extract various entities, and finally, the various entities are stored in a database. Using this method, experiments are conducted on the EMR of the orthopedic injury department of a hospital, in which the recognition rate of the symptom entity in the symptom text reaches 92.28%, and the recognition rate of entities such as symptoms and diseases in the medical history text reaches 89.86%. The validity of this method is verified. This method normalizes the natural language writing part of the EMR and stores it in a structured way, which is convenient for the subsequent data analysis and mining, and lays a solid foundation for the intellectualization of TCM. Can Li, Dan Xie Copyright (c) 2022 Can Li, Dan Xie https://creativecommons.org/licenses/by-nc/4.0/ http://ojs.ais.cn/jaims/article/view/82 Tue, 15 Nov 2022 00:00:00 +0800 http://ojs.ais.cn/jaims/article/view/83 We analyzed tumor mutations of 7 uterine and 2 cervical cancers with the goal of developing a Deep Learning (DL) software tool that can automatically classify tumors based on their somatic mutations. The data were obtained from the AACR Genie Project, that has a collection of more than 120,000 tumor samples for more than 750 cancer types. We performed a thorough analysis of the mutational data of tumors of the uterus and uterine cervix, selecting tumors with 3 or more mutations and cancer types with more than 15 cases. For each cancer type we then selected the top 12 most mutated genes among their neoplasms. In the introduction section we summarize our analysis of these nine diseases and in the methods section we present a convolutional neural network (CNN) that yields an overall classification accuracy of 94.3% and 89.2% on the train and test datasets, respectively. We hope this tool can be added to the existing arsenal of histological and immunohistochemical techniques in cases when a precise diagnosis cannot be clearly determined. Each cancer type has a unique somatic mutational profile that can be used to disambiguate two candidate malignancies with similar histologic features. Paul Gomez Copyright (c) 2022 Paul Gomez https://creativecommons.org/licenses/by-nc/4.0/ http://ojs.ais.cn/jaims/article/view/83 Fri, 23 Dec 2022 00:00:00 +0800