28
views
0
recommends
+1 Recommend
0 collections
    0
    shares
      • Record: found
      • Abstract: found
      • Article: found
      Is Open Access

      Machine Learning-Based Differentiation of Nontuberculous Mycobacteria Lung Disease and Pulmonary Tuberculosis Using CT Images

      research-article

      Read this article at

      Bookmark
          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

          Abstract

          An increasing number of patients infected with nontuberculous mycobacteria (NTM) are observed worldwide. However, it is challenging to identify NTM lung diseases from pulmonary tuberculosis (PTB) due to considerable overlap in classic manifestations and clinical and radiographic characteristics. This study quantifies both cavitary and bronchiectasis regions in CT images and explores a machine learning approach for the differentiation of NTM lung diseases and PTB. It involves 116 patients and 103 quantitative features. After the selection of informative features, a linear support vector machine performs disease classification, and simultaneously, discriminative features are recognized. Experimental results indicate that bronchiectasis is relatively more informative, and two features are figured out due to promising prediction performance (area under the curve, 0.84 ± 0.06; accuracy, 0.85 ± 0.06; sensitivity, 0.88 ± 0.07; and specificity, 0.80 ± 0.12). This study provides insight into machine learning-based identification of NTM lung diseases from PTB, and more importantly, it makes early and quick diagnosis of NTM lung diseases possible that can facilitate lung disease management and treatment planning.

          Related collections

          Most cited references31

          • Record: found
          • Abstract: found
          • Article: not found

          Treatment of nontuberculous mycobacterial pulmonary disease: an official ATS/ERS/ESCMID/IDSA clinical practice guideline

          Nontuberculous mycobacteria (NTM) represent over 190 species and subspecies, some of which can produce disease in humans of all ages and can affect both pulmonary and extrapulmonary sites. This guideline focuses on pulmonary disease in adults (without cystic fibrosis or human immunodeficiency virus infection) caused by the most common NTM pathogens such as Mycobacterium avium complex, Mycobacterium kansasii , and Mycobacterium xenopi among the slowly growing NTM and Mycobacterium abscessus among the rapidly growing NTM. A panel of experts was carefully selected by leading international respiratory medicine and infectious diseases societies (ATS, ERS, ESCMID, IDSA) and included specialists in pulmonary medicine, infectious diseases and clinical microbiology, laboratory medicine, and patient advocacy. Systematic reviews were conducted around each of 22 PICO (Population, Intervention, Comparator, Outcome) questions and the recommendations were formulated, written, and graded using the GRADE (Grading of Recommendations Assessment, Development, and Evaluation) approach. Thirty-one evidence-based recommendations about treatment of NTM pulmonary disease are provided. This guideline is intended for use by healthcare professionals who care for patients with NTM pulmonary disease, including specialists in infectious diseases and pulmonary diseases.
            Bookmark
            • Record: found
            • Abstract: found
            • Article: found
            Is Open Access

            Of tuberculosis and non-tuberculous mycobacterial infections – a comparative analysis of epidemiology, diagnosis and treatment

            Pulmonary diseases due to mycobacteria cause significant morbidity and mortality to human health. In addition to tuberculosis (TB), caused by Mycobacterium tuberculosis (Mtb), recent epidemiological studies have shown the emergence of non-tuberculous mycobacteria (NTM) species in causing lung diseases in humans. Although more than 170 NTM species are present in various environmental niches, only a handful, primarily Mycobacterium avium complex and M. abscessus, have been implicated in pulmonary disease. While TB is transmitted through inhalation of aerosol droplets containing Mtb, generated by patients with symptomatic disease, NTM disease is mostly disseminated through aerosols originated from the environment. However, following inhalation, both Mtb and NTM are phagocytosed by alveolar macrophages in the lungs. Subsequently, various immune cells are recruited from the circulation to the site of infection, which leads to granuloma formation. Although the pathophysiology of TB and NTM diseases share several fundamental cellular and molecular events, the host-susceptibility to Mtb and NTM infections are different. Striking differences also exist in the disease presentation between TB and NTM cases. While NTM disease is primarily associated with bronchiectasis, this condition is rarely a predisposing factor for TB. Similarly, in Human Immunodeficiency Virus (HIV)-infected individuals, NTM disease presents as disseminated, extrapulmonary form rather than as a miliary, pulmonary disease, which is seen in Mtb infection. The diagnostic modalities for TB, including molecular diagnosis and drug-susceptibility testing (DST), are more advanced and possess a higher rate of sensitivity and specificity, compared to the tools available for NTM infections. In general, drug-sensitive TB is effectively treated with a standard multi-drug regimen containing well-defined first- and second-line antibiotics. However, the treatment of drug-resistant TB requires the additional, newer class of antibiotics in combination with or without the first and second-line drugs. In contrast, the NTM species display significant heterogeneity in their susceptibility to standard anti-TB drugs. Thus, the treatment for NTM diseases usually involves the use of macrolides and injectable aminoglycosides. Although well-established international guidelines are available, treatment of NTM disease is mostly empirical and not entirely successful. In general, the treatment duration is much longer for NTM diseases, compared to TB, and resection surgery of affected organ(s) is part of treatment for patients with NTM diseases that do not respond to the antibiotics treatment. Here, we discuss the epidemiology, diagnosis, and treatment modalities available for TB and NTM diseases of humans.
              Bookmark
              • Record: found
              • Abstract: found
              • Article: found
              Is Open Access

              Identification of the core bacteria in rectums of diarrheic and non-diarrheic piglets

              Porcine diarrhea is a global problem that leads to large economic losses of the porcine industry. There are numerous factors related to piglet diarrhea, and compelling evidence suggests that gut microbiota is vital to host health. However, the key bacterial differences between non-diarrheic and diarrheic piglets are not well understood. In the present study, a total of 85 commercial piglets at three pig farms in Sichuan Province and Chongqing Municipality, China were investigated. To accomplish this, anal swab samples were collected from piglets during the lactation (0–19 days old in this study), weaning (20–21 days old), and post-weaning periods (22–40 days), and fecal microbiota were assessed by 16S rRNA gene V4 region sequencing using the Illumina Miseq platform. We found age-related biomarker microbes in the fecal microbiota of diarrheic piglets. Specifically, the family Enterobacteriaceae was a biomarker of diarrheic piglets during lactation (cluster A, 7–12 days old), whereas the Bacteroidales family S24–7 group was found to be a biomarker of diarrheic pigs during weaning (cluster B, 20–21 days old). Co-correlation network analysis revealed that the genus Escherichia-Shigella was the core component of diarrheic microbiota, while the genus Prevotellacea UCG-003 was the key bacterium in non-diarrheic microbiota of piglets in Southwest China. Furthermore, changes in bacterial metabolic function between diarrheic piglets and non-diarrheic piglets were estimated by PICRUSt analysis, which revealed that the dominant functions of fecal microbes were membrane transport, carbohydrate metabolism, amino acid metabolism, and energy metabolism. Remarkably, genes related to transporters, DNA repair and recombination proteins, purine metabolism, ribosome, secretion systems, transcription factors, and pyrimidine metabolism were decreased in diarrheic piglets, but no significant biomarkers were found between groups using LEfSe analysis.
                Bookmark

                Author and article information

                Contributors
                Journal
                Biomed Res Int
                Biomed Res Int
                BMRI
                BioMed Research International
                Hindawi
                2314-6133
                2314-6141
                2020
                29 September 2020
                : 2020
                : 6287545
                Affiliations
                1Tianjin Medical University Cancer Institute and Hospital, National Clinical Research Center for Cancer, Key Laboratory of Cancer Prevention and Therapy, Tianjin, Tianjin's Clinical Research Center for Cancer, Tianjin, China
                2Haihe Hospital, Tianjin University, Tianjin Institute of Respiratory Diseases, Tianjin, China
                Author notes

                Academic Editor: Zhiguo Zhou

                Author information
                https://orcid.org/0000-0003-3157-8393
                Article
                10.1155/2020/6287545
                7545409
                33062689
                b24e171a-4365-4399-b033-9cf811e0284b
                Copyright © 2020 Zhiheng Xing et al.

                This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

                History
                : 6 August 2020
                : 11 September 2020
                : 22 September 2020
                Funding
                Funded by: Tianjin Municipal Health Science and Technology Project From Tianjin Municipal Health and Health Committee
                Award ID: 2020xkm03
                Categories
                Research Article

                Comments

                Comment on this article

                scite_
                27
                0
                16
                0
                Smart Citations
                27
                0
                16
                0
                Citing PublicationsSupportingMentioningContrasting
                View Citations

                See how this article has been cited at scite.ai

                scite shows how a scientific paper has been cited by providing the context of the citation, a classification describing whether it supports, mentions, or contrasts the cited claim, and a label indicating in which section the citation was made.

                Similar content768

                Cited by11

                Most referenced authors3,396