1
|
Krüger W. Diagnostic algorithm allows for a scientifically robust and reliable retrospective diagnosis using textual evidence from mid-19th century Basel, Switzerland. INTERNATIONAL JOURNAL OF PALEOPATHOLOGY 2024; 44:105-111. [PMID: 38218023 DOI: 10.1016/j.ijpp.2024.01.001] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 05/25/2023] [Revised: 12/17/2023] [Accepted: 01/01/2024] [Indexed: 01/15/2024]
Abstract
OBJECTIVE Diagnosing disease from the past using historic textual sources can be controversial as to its accuracy. To overcome these objections, an empirical approach to the historical clinical data was developed. The approach follows a standardised, objective, and systematic evaluation, satisfying the requirements of the philosophy of science. MATERIAL Physician-managed medical records of mid-19th century patients reported to have suffered from tuberculosis. METHOD A diagnostic algorithm, quantifying clinical data into a scoring system, was developed based on criteria recorded in the medical sources. The findings were compared to the autopsy results using the Receiver Operating Characteristics method. RESULTS The generated scoring system correctly predicted the diagnosis of tuberculosis in 86% of patients in the study. 6% false negatives and 8% false positives were predicted. CONCLUSIONS It is possible to retrospectively diagnose in a reliable and scientifically robust manner under certain conditions. It is important to embed the clinical data into the historical context. A general rejection of retrospective diagnosis is unsubstantiated. Well-designed, disease-specific, and source adapted medical scoring systems are new approaches and overcome criticism raised against retrospective diagnosis. SIGNIFICANCE This new approach utilises diverse historic sources and potentially leads to reliable retrospective diagnosis of most common diseases of the past. LIMITATIONS Selection bias of the records allocated. Quality of the historic sources utilized. Restricted statistical assessment potential of historic sources. SUGGESTIONS FOR FURTHER RESEARCH Development of disease- and epoch-specific medical score systems.
Collapse
Affiliation(s)
- Wolfgang Krüger
- Biological Anthropology, Faculty of Medicine, University of Freiburg, Hebelstrasse 29, D-79104 Freiburg im Breisgau, Germany.
| |
Collapse
|
2
|
Sambarey A, Smith K, Chung C, Arora HS, Yang Z, Agarwal PP, Chandrasekaran S. Integrative analysis of multimodal patient data identifies personalized predictors of tuberculosis treatment prognosis. iScience 2024; 27:109025. [PMID: 38357663 PMCID: PMC10865408 DOI: 10.1016/j.isci.2024.109025] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/29/2023] [Revised: 12/08/2023] [Accepted: 01/22/2024] [Indexed: 02/16/2024] Open
Abstract
Tuberculosis (TB) afflicted 10.6 million people in 2021, and its global burden is increasing due to multidrug-resistant TB (MDR-TB) and extensively resistant TB (XDR-TB). Here, we analyze multi-domain information from 5,060 TB patients spanning 10 countries with high burden of MDR-TB from the NIAID TB Portals database to determine predictors of TB treatment outcome. Our analysis revealed significant associations between radiological, microbiological, therapeutic, and demographic data modalities. Our machine learning model, built with 203 features across modalities outperforms models built using each modality alone in predicting treatment outcomes, with an accuracy of 83% and area under the curve of 0.84. Notably, our analysis revealed that the drug regimens Bedaquiline-Clofazimine-Cycloserine-Levofloxacin-Linezolid and Bedaquiline-Clofazimine-Linezolid-Moxifloxacin were associated with treatment success and failure, respectively, for MDR non-XDR-TB. Drug combinations predicted to be synergistic by the INDIGO algorithm performed better than antagonistic combinations. Our prioritized set of features predictive of treatment outcomes can ultimately guide the personalized clinical management of TB.
Collapse
Affiliation(s)
- Awanti Sambarey
- Department of Biomedical Engineering, University of Michigan, Ann Arbor, MI 48109, USA
| | - Kirk Smith
- Department of Biomedical Engineering, University of Michigan, Ann Arbor, MI 48109, USA
| | - Carolina Chung
- Department of Biomedical Engineering, University of Michigan, Ann Arbor, MI 48109, USA
| | - Harkirat Singh Arora
- Department of Biomedical Engineering, University of Michigan, Ann Arbor, MI 48109, USA
| | - Zhenhua Yang
- Department of Epidemiology, School of Public Health, University of Michigan, Ann Arbor, MI 48109, USA
| | - Prachi P. Agarwal
- Department of Radiology, University of Michigan, Ann Arbor, MI 48109, USA
| | - Sriram Chandrasekaran
- Department of Biomedical Engineering, University of Michigan, Ann Arbor, MI 48109, USA
- Program in Chemical Biology, University of Michigan, Ann Arbor, MI 48109, USA
- Center for Bioinformatics and Computational Medicine, Ann Arbor, MI 48109, USA
| |
Collapse
|
3
|
Nijiati M, Guo L, Abulizi A, Fan S, Wubuli A, Tuersun A, Nijiati P, Xia L, Hong K, Zou X. Deep learning and radiomics of longitudinal CT scans for early prediction of tuberculosis treatment outcomes. Eur J Radiol 2023; 169:111180. [PMID: 37949023 DOI: 10.1016/j.ejrad.2023.111180] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/25/2023] [Revised: 10/21/2023] [Accepted: 10/29/2023] [Indexed: 11/12/2023]
Abstract
BACKGROUND To predict tuberculosis (TB) treatment outcomes at an early stage, prevent poor outcomes ofdrug-resistant tuberculosis(DR-TB) and interrupt transmission. METHODS An internal cohort for model development consists of 204 bacteriologically-confirmed TB patients who completed anti-tuberculosis treatment, with one pretreatment and two follow-up CT images (612 scans). Three radiomics feature-based models (RM) with multiple classifiers of Bagging, Random forest and Gradient boosting and two deep-learning-based models (i.e., supervised deep-learning model, SDLM; weakly supervised deep-learning model, WSDLM) are developed independently. Prediction scores of RM and deep-learning models with respectively highest performance are fused to create new fusion models under different fusion strategies. An additional independent validation was conducted on the external cohort comprising 80 patients (160 scans). RESULTS For RM scheme, 16 optimal radiomics features are finally selected using longitudinal scans. The AUCs of RM for Bagging, Random forest and Gradient boosting were 0.789, 0.773 and 0.764 in the internal cohort and 0.840, 0.834 and 0.816 in the external cohort, respectively. For deep learning-based scheme, AUCs of SDLM and WSDLM were 0.767 and 0.661 in the internal cohort, and 0.823 and 0.651 in the external. The fusion model yields AUCs from 0.767 to 0.802 in the internal cohort, and from 0.831 to 0.857 in the external cohort. CONCLUSIONS Fusion of radiomics features and deep-learning model may have the potential to predict early failure outcome of DR-TB, which may be combined to help prevent poor TB treatment outcomes.
Collapse
Affiliation(s)
- Mayidili Nijiati
- Department of Radiology, The First People's Hospital of Kashi (Kashgar) Prefecture, China
| | - Lin Guo
- Shenzhen Zhiying Medical Imaging, Shenzhen, China
| | | | - Shiyu Fan
- Department of Radiology, The First People's Hospital of Kashi (Kashgar) Prefecture, China
| | - Abulikemu Wubuli
- Department of Radiology, Yecheng County People's Hospital, China
| | - Abudouresuli Tuersun
- Department of Radiology, The First People's Hospital of Kashi (Kashgar) Prefecture, China
| | - Pahatijiang Nijiati
- Department of Radiology, The First People's Hospital of Kashi (Kashgar) Prefecture, China
| | - Li Xia
- Shenzhen Zhiying Medical Imaging, Shenzhen, China
| | - Kunlei Hong
- Shenzhen Zhiying Medical Imaging, Shenzhen, China
| | - Xiaoguang Zou
- Clinical Medical Research Center, The First People's Hospital of Kashi (Kashgar) Prefecture, China.
| |
Collapse
|
4
|
Nijiati M, Guo L, Tuersun A, Damola M, Abulizi A, Dong J, Xia L, Hong K, Zou X. Deep learning on longitudinal CT scans: automated prediction of treatment outcomes in hospitalized tuberculosis patients. iScience 2023; 26:108326. [PMID: 37965132 PMCID: PMC10641748 DOI: 10.1016/j.isci.2023.108326] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/14/2023] [Revised: 08/17/2023] [Accepted: 10/20/2023] [Indexed: 11/16/2023] Open
Abstract
Three deep learning (DL)-based prediction models (PMs) using longitudinal CT images were developed to predict tuberculosis (TB) treatment outcomes. The internal dataset consists of 493 bacteriologically confirmed TB patients who completed the anti-tuberculosis treatment with three-time CT scans, including a pretreatment CT scan and two follow-up CT scans. PM1 was trained using only pretreatment CT scans, and PM2 and PM3 were developed by adding follow-up scans. An independent testing was performed on external dataset comprising 86 TB patients. The area under the curve for classifying success and drug-resistant (DR)-TB was improved on both internal (0.609 vs. 0.625 vs. 0.815) and external (0.627 vs. 0.705 vs. 0.735) dataset by adding follow-up scans. The accuracy and F1-score also showed an increasing tendency in the external test. Regular follow-up CT scans can aid in the treatment prediction, and special attention should be given to early intensive phase of treatment to identify high-risk DR-TB patients.
Collapse
Affiliation(s)
- Mayidili Nijiati
- Department of Radiology, The First People’s Hospital of Kashi Prefecture, Kashi, China
| | - Lin Guo
- Shenzhen Zhiying Medical Imaging, Shenzhen, China
| | - Abudouresuli Tuersun
- Department of Radiology, The First People’s Hospital of Kashi Prefecture, Kashi, China
| | - Maihemitijiang Damola
- Department of Radiology, The First People’s Hospital of Kashi Prefecture, Kashi, China
| | | | - Jiake Dong
- Department of Radiology, The First People’s Hospital of Kashi Prefecture, Kashi, China
| | - Li Xia
- Shenzhen Zhiying Medical Imaging, Shenzhen, China
| | - Kunlei Hong
- Shenzhen Zhiying Medical Imaging, Shenzhen, China
| | - Xiaoguang Zou
- Clinical Medical Research Center, The First People’s Hospital of Kashi Prefecture, Kashi, China
| |
Collapse
|
5
|
Sambarey A, Smith K, Chung C, Arora HS, Yang Z, Agarwal P, Chandrasekaran S. Integrative analysis of clinical health records, imaging and pathogen genomics identifies personalized predictors of disease prognosis in tuberculosis. MEDRXIV : THE PREPRINT SERVER FOR HEALTH SCIENCES 2022:2022.07.20.22277862. [PMID: 35898335 PMCID: PMC9327630 DOI: 10.1101/2022.07.20.22277862] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Indexed: 06/15/2023]
Abstract
Tuberculosis (TB) afflicts over 10 million people every year and its global burden is projected to increase dramatically due to multidrug-resistant TB (MDR-TB). The Covid-19 pandemic has resulted in reduced access to TB diagnosis and treatment, reversing decades of progress in disease management globally. It is thus crucial to analyze real-world multi-domain information from patient health records to determine personalized predictors of TB treatment outcome and drug resistance. We conduct a retrospective analysis on electronic health records of 5060 TB patients spanning 10 countries with high burden of MDR-TB including Ukraine, Moldova, Belarus and India available on the NIAID-TB portals database. We analyze over 200 features across multiple host and pathogen modalities representing patient social demographics, disease presentations as seen in cChest X rays and CT scans, and genomic records with drug susceptibility features of the pathogen strain from each patient. Our machine learning model, built with diverse data modalities outperforms models built using each modality alone in predicting treatment outcomes, with an accuracy of 81% and AUC of 0.768. We determine robust predictors across countries that are associated with unsuccessful treatmentclinical outcomes, and validate our predictions on new patient data from TB Portals. Our analysis of drug regimens and drug interactions suggests that synergistic drug combinations and those containing the drugs Bedaquiline, Levofloxacin, Clofazimine and Amoxicillin see more success in treating MDR and XDR TB. Features identified via chest imaging such as percentage of abnormal volume, size of lung cavitation and bronchial obstruction are associated significantly with pathogen genomic attributes of drug resistance. Increased disease severity was also observed in patients with lower BMI and with comorbidities. Our integrated multi-modal analysis thus revealed significant associations between radiological, microbiological, therapeutic, and demographic data modalities, providing a deeper understanding of personalized responses to aid in the clinical management of TB.
Collapse
Affiliation(s)
| | - Kirk Smith
- Chemical BIology, University of Michigan
| | | | | | | | | | | |
Collapse
|
6
|
Gopalan N, Srinivasalu VA, Chinnayan P, Velayutham B, Bhaskar A, Santhanakrishnan R, Senguttuvan T, Rathinam S, Ayyamperumal M, Satagopan K, Rajendran D, Manoharan T, Lakshmanan S, Paramasivam P, Angamuthu D, Ganesan M, Easudoss Arockia JW, Venkatesan RB, Lakshmipathy V, Shanmugham S, Subramanyam B, Shankar S, Mohideen Shaheed J, Dhanaraj B, Paranji Ramiyengar N, Swaminathan S, Chandrasekaran P. Predictors of unfavorable responses to therapy in rifampicin-sensitive pulmonary tuberculosis using an integrated approach of radiological presentation and sputum mycobacterial burden. PLoS One 2021; 16:e0257647. [PMID: 34543329 PMCID: PMC8452066 DOI: 10.1371/journal.pone.0257647] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/02/2021] [Accepted: 09/06/2021] [Indexed: 11/18/2022] Open
Abstract
INTRODUCTION Despite the exalted status of sputum mycobacterial load for gauging pulmonary tuberculosis treatment and progress, Chest X-rays supplement valuable information for taking instantaneous therapeutic decisions, especially during the COVID-19 pandemic. Even though literature on individual parameters is overwhelming, few studies have explored the interaction between radiographic parameters denoting severity with mycobacterial burden signifying infectivity. By using a sophisticated approach of integrating Chest X-ray parameters with sputum mycobacterial characteristics, evaluated at all the three crucial time points of TB treatment namely pre-treatment, end of intensive phase and completion of treatment, utilizing the interactive Cox Proportional Hazards model, we aimed to precisely deduce predictors of unfavorable response to TB treatment. MATERIALS AND METHOD We extracted de-identified data from well characterized clinical trial cohorts that recruited rifampicin-sensitive Pulmonary TB patients without any comorbidities, taking their first spell of anti-tuberculosis therapy under supervision and meticulous follow up for 24 months post treatment completion, to accurately predict TB outcomes. Radiographic data independently obtained, interpreted by two experienced pulmonologists was collated with demographic details and, sputum smear and culture grades of participants by an independent statistician and analyzed using the Cox Proportional Hazards model, to not only adjust for confounding factors including treatment effect, but also explore the interaction between radiological and bacteriological parameters for better therapeutic application. RESULTS Of 667 TB patients with data available, cavitation, extent of involvement, lower zone involvement, smear and culture grade at baseline were significant parameters predisposing to an unfavorable TB treatment outcome in the univariate analysis. Reduction in radiological lesions in Chest X-ray by at least 50% at 2 months and 75% at the end of treatment helped in averting unfavorable responses. Smear and Culture conversion at the end of 2 months was highly significant as a predictor (p<0.001). In the multivariate analysis, the adjusted hazards ratios (HR) for an unfavorable response to TB therapy for extent of involvement, baseline cavitation and persistence (post treatment) were 1.21 (95% CI: 1.01-1.44), 1.73 (95% CI: 1.05-2.84) and 2.68 (95% CI: 1.4-5.12) respectively. A 3+ smear had an HR of 1.94 (95% CI: 0.81-4.64). Further probing into the interaction, among patients with 3+ and 2+ smears, HRs for cavitation were 3.26 (95% CI: 1.33-8.00) and 1.92 (95% CI: 0.80-4.60) while for >2 zones, were 3.05 (95% CI: 1.12-8.23) and 1.92 (95% CI: 0.72-5.08) respectively. Patients without cavitation, zonal involvement <2, and a smear grade less than 2+ had a better prognosis and constituted minimal disease. CONCLUSION Baseline Cavitation, Opacities occupying >2 zones and 3+ smear grade individually and independently forecasted a poorer TB outcome. The interaction model revealed that Zonal involvement confined to 2 zones, without a cavity and smear grade up to 2+, constituting "minimal disease", had a better prognosis. Radiological clearance >50% along with smear conversion at the end of intensive phase of treatment, observed to be a reasonable alternative to culture conversion in predicting a successful outcome. These parameters may potentially take up key positions as stratification factors for future trials contemplating on shorter TB regimens.
Collapse
Affiliation(s)
- Narendran Gopalan
- Department of Clinical Research, National Institute for Research in Tuberculosis (formerly Tuberculosis Research Centre), Indian Council of Medical Research, Chennai, Tamil Nadu, India
- * E-mail:
| | - Vignes Anand Srinivasalu
- Department of Clinical Research, National Institute for Research in Tuberculosis (formerly Tuberculosis Research Centre), Indian Council of Medical Research, Chennai, Tamil Nadu, India
| | - Ponnuraja Chinnayan
- Department of Clinical Research, National Institute for Research in Tuberculosis (formerly Tuberculosis Research Centre), Indian Council of Medical Research, Chennai, Tamil Nadu, India
| | - Banurekha Velayutham
- Department of Clinical Research, National Institute for Research in Tuberculosis (formerly Tuberculosis Research Centre), Indian Council of Medical Research, Chennai, Tamil Nadu, India
| | - Adhin Bhaskar
- Department of Clinical Research, National Institute for Research in Tuberculosis (formerly Tuberculosis Research Centre), Indian Council of Medical Research, Chennai, Tamil Nadu, India
| | - Ramesh Santhanakrishnan
- Department of Clinical Research, National Institute for Research in Tuberculosis (formerly Tuberculosis Research Centre), Indian Council of Medical Research, Chennai, Tamil Nadu, India
| | - Thirumaran Senguttuvan
- Department of Clinical Research, National Institute for Research in Tuberculosis (formerly Tuberculosis Research Centre), Indian Council of Medical Research, Chennai, Tamil Nadu, India
| | - Sridhar Rathinam
- Department of Thoracic Medicine, Government Hospital of Thoracic Medicine Tambaram, Chennai, Tamil Nadu, India
| | - Mahilmaran Ayyamperumal
- Department of Thoracic Medicine, Institute of Thoracic Medicine, Madras Medical College, Chennai, Tamil Nadu, India
| | - Kumar Satagopan
- Department of Thoracic Medicine, Government Hospital of Thoracic Medicine Tambaram, Chennai, Tamil Nadu, India
| | - Dhanalakshmi Rajendran
- Department of Clinical Research, National Institute for Research in Tuberculosis (formerly Tuberculosis Research Centre), Indian Council of Medical Research, Chennai, Tamil Nadu, India
| | - Tamizhselvan Manoharan
- Department of Clinical Research, National Institute for Research in Tuberculosis (formerly Tuberculosis Research Centre), Indian Council of Medical Research, Chennai, Tamil Nadu, India
| | - Sekar Lakshmanan
- Department of Clinical Research, National Institute for Research in Tuberculosis (formerly Tuberculosis Research Centre), Indian Council of Medical Research, Chennai, Tamil Nadu, India
| | - Paulkumaran Paramasivam
- Department of Clinical Research, National Institute for Research in Tuberculosis (formerly Tuberculosis Research Centre), Indian Council of Medical Research, Chennai, Tamil Nadu, India
| | - Dhanalakshmi Angamuthu
- Department of Clinical Research, National Institute for Research in Tuberculosis (formerly Tuberculosis Research Centre), Indian Council of Medical Research, Chennai, Tamil Nadu, India
| | - Mangalambal Ganesan
- Department of Clinical Research, National Institute for Research in Tuberculosis (formerly Tuberculosis Research Centre), Indian Council of Medical Research, Chennai, Tamil Nadu, India
| | - John Washington Easudoss Arockia
- Department of Clinical Research, National Institute for Research in Tuberculosis (formerly Tuberculosis Research Centre), Indian Council of Medical Research, Chennai, Tamil Nadu, India
| | - Ramesh Babu Venkatesan
- Department of Clinical Research, National Institute for Research in Tuberculosis (formerly Tuberculosis Research Centre), Indian Council of Medical Research, Chennai, Tamil Nadu, India
| | - Venkatesan Lakshmipathy
- Department of Clinical Research, National Institute for Research in Tuberculosis (formerly Tuberculosis Research Centre), Indian Council of Medical Research, Chennai, Tamil Nadu, India
| | - Shivakumar Shanmugham
- Department of Clinical Research, National Institute for Research in Tuberculosis (formerly Tuberculosis Research Centre), Indian Council of Medical Research, Chennai, Tamil Nadu, India
| | - Balaji Subramanyam
- Department of Clinical Research, National Institute for Research in Tuberculosis (formerly Tuberculosis Research Centre), Indian Council of Medical Research, Chennai, Tamil Nadu, India
| | - Shakila Shankar
- Department of Clinical Research, National Institute for Research in Tuberculosis (formerly Tuberculosis Research Centre), Indian Council of Medical Research, Chennai, Tamil Nadu, India
| | - Jawahar Mohideen Shaheed
- Department of Clinical Research, National Institute for Research in Tuberculosis (formerly Tuberculosis Research Centre), Indian Council of Medical Research, Chennai, Tamil Nadu, India
| | - Baskaran Dhanaraj
- Department of Clinical Research, National Institute for Research in Tuberculosis (formerly Tuberculosis Research Centre), Indian Council of Medical Research, Chennai, Tamil Nadu, India
| | - Narayanan Paranji Ramiyengar
- Department of Clinical Research, National Institute for Research in Tuberculosis (formerly Tuberculosis Research Centre), Indian Council of Medical Research, Chennai, Tamil Nadu, India
| | | | - Padmapriyadarsini Chandrasekaran
- Department of Clinical Research, National Institute for Research in Tuberculosis (formerly Tuberculosis Research Centre), Indian Council of Medical Research, Chennai, Tamil Nadu, India
| |
Collapse
|
7
|
Cheng N, Wu S, Luo X, Xu C, Lou Q, Zhu J, You L, Li B. A Comparative Study of Chest Computed Tomography Findings: 1030 Cases of Drug-Sensitive Tuberculosis versus 516 Cases of Drug-Resistant Tuberculosis. Infect Drug Resist 2021; 14:1115-1128. [PMID: 33776457 PMCID: PMC7987723 DOI: 10.2147/idr.s300754] [Citation(s) in RCA: 11] [Impact Index Per Article: 3.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/12/2021] [Accepted: 03/04/2021] [Indexed: 01/15/2023] Open
Abstract
Purpose To investigate the CT features of drug-resistant pulmonary tuberculosis (DR-PTB) and the diagnostic value of CT in DR-PTB diagnosis to provide imaging evidence for the timely detection of drug-resistant Mycobacterium tuberculosis. Materials and Methods A total of 1546 cases of pulmonary tuberculosis (PTB) with complete clinical data, chest CT images and defined drug sensitivity testing results were consecutively enrolled; 516 cases of DR-PTB were included in the drug-resistant group, and 1030 cases of drug-sensitive pulmonary tuberculosis (DS-PTB) were included in the drug-sensitivity group. Comparative analyses of clinical symptoms and imaging findings were conducted. Univariate and logistic regression analyses were performed, a regression equation model was developed, and the receiver operating characteristic (ROC) curve was constructed. Results In the univariate analysis, some features, including whole-lung involvement, multiple cavities, thick-walled cavities, collapsed lung, disseminated lesions along the bronchi, bronchiectasis, emphysema, atelectasis, calcification, proliferative lesions, encapsulated effusion, etc., were observed more frequently in the DR-PTB group than in the DS-PTB group, and the differences were statistically significant (p<0.05). Exudative lesions and pneumoconiosis were observed more frequently in the drug-sensitivity group than in the drug-resistant group (p<0.05). Logistic regression analysis indicated that whole-lung involvement, multiple cavities, thick-walled cavities, disseminated lesions along the bronchi, bronchiectasis, and emphysema were independent risk factors for DR-PTB, and exudative diseases were protective factors. The total prediction accuracy of the regression model was 80.6%, and the area under the ROC curve (AUC) was 82.6%. Conclusion Chest CT manifestations of DR-PTB had certain characteristics that significantly indicated the possibility of drug resistance in tuberculosis patients, specifically when multifarious imaging findings, including multiple cavities, thick-walled cavities, disseminated lesions along the bronchi, whole-lung involvement, etc., coexisted simultaneously. These results may provide imaging evidence for timely drug resistance detection in suspected drug-resistant cases and contribute to the early diagnosis of DR-PTB.
Collapse
Affiliation(s)
- Nianlan Cheng
- Department of Radiology, Affiliated Hospital of Zunyi Medical University, Zunyi, Guizhou Province, People's Republic of China
| | - Shuo Wu
- Department of Radiology, Affiliated Hospital of Zunyi Medical University, Zunyi, Guizhou Province, People's Republic of China
| | - Xianli Luo
- Department of Radiology, Affiliated Hospital of Zunyi Medical University, Zunyi, Guizhou Province, People's Republic of China
| | - Chunyan Xu
- Department of Radiology, Affiliated Hospital of Zunyi Medical University, Zunyi, Guizhou Province, People's Republic of China
| | - Qin Lou
- Department of Radiology, Affiliated Hospital of Zunyi Medical University, Zunyi, Guizhou Province, People's Republic of China
| | - Jin Zhu
- Department of Radiology, Affiliated Hospital of Zunyi Medical University, Zunyi, Guizhou Province, People's Republic of China
| | - Lu You
- Department of Radiology, Affiliated Hospital of Zunyi Medical University, Zunyi, Guizhou Province, People's Republic of China
| | - Bangguo Li
- Department of Radiology, Affiliated Hospital of Zunyi Medical University, Zunyi, Guizhou Province, People's Republic of China
| |
Collapse
|
8
|
Wang HR, Han C, Wang JL, Zhang YA, Wang MS. Risk Factor for Retreatment Episode on Admission Among TB Patients With Schizophrenia. Front Psychiatry 2021; 12:793470. [PMID: 34955934 PMCID: PMC8695840 DOI: 10.3389/fpsyt.2021.793470] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 10/12/2021] [Accepted: 11/09/2021] [Indexed: 11/13/2022] Open
Abstract
Background: The clinical characteristics of patients with tuberculosis (TB) and schizophrenia remain largely unknown. Furthermore, TB retreatment is associated with a poor outcome. Hence, we aimed to address the risk factors of TB retreatment in schizophrenia patients in this retrospective cohort. Methods: Between March 2005 and August 2020, patients diagnosed with schizophrenia and TB were included in the study. Patient characteristics, such as demographics, medical history, underlying diseases, symptoms, outcome, and lab examinations, were collected from medical records using a structured questionnaire. TB retreatment was defined as treatment failures and relapses. Subsequently, multivariate logistic regression was performed using variables selected based on prior findings as well as factors found to be associated with a retreatment episode in univariate analyses (p < 0.1). Results: A total of 113 TB patients with schizophrenia were included. Of them, 94 (83.2%) patients were classified as initial treatment group, and 19 (16.8%) were classified as retreatment group. The mean age was 53.0 ± 23.2 years, and males accounted for 61.9% of all cases. Multivariate analysis revealed that continuous antipsychotics treatment (OR = 0.226, 95% CI: 0.074, 0.693; p = 0.009) and extra-pulmonary TB (OR = 0.249, 95% CI: 0.080, 0.783; p = 0.017) were associated with the retreatment in TB patients with schizophrenia. Conclusion: Retreatment is a significant concern for TB patients with schizophrenia. To improve the current dilemma, continuous antipsychotics treatment is required, and increasing awareness of schizophrenia would reduce the disease burden.
Collapse
Affiliation(s)
- Hai-Rong Wang
- Department of Outpatient, Shandong Mental Health Center, Jinan, China
| | - Chao Han
- Department of Outpatient, Shandong Mental Health Center, Jinan, China
| | - Jun-Li Wang
- Department of Lab Medicine, The Affiliated Hospital of Youjiang Medical University for Nationalities, Baise, China
| | - Yan-An Zhang
- Department of Cardiovascular Surgery, Shandong Public Health Clinical Center, Cheeloo College of Medicine, Shandong University, Jinan, China.,Shandong Key Laboratory of Infectious Respiratory Disease, Jinan, China
| | - Mao-Shui Wang
- Shandong Key Laboratory of Infectious Respiratory Disease, Jinan, China.,Department of Lab Medicine, Shandong Provincial Chest Hospital, Cheeloo College of Medicine, Shandong University, Jinan, China.,Department of Lab Medicine, Shandong Public Health Clinical Center, Cheeloo College of Medicine, Shandong University, Jinan, China
| |
Collapse
|
9
|
Anaam MS, Alrasheedy AA, Alsahali S, Alfadly SO, Aldhubhani AH. Rate and risk factors of recurrent tuberculosis in Yemen: a 5-year prospective study. Infect Dis (Lond) 2019; 52:161-169. [DOI: 10.1080/23744235.2019.1690162] [Citation(s) in RCA: 6] [Impact Index Per Article: 1.2] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 02/07/2023] Open
Affiliation(s)
- Mohammed Saif Anaam
- Department of Pharmacy Practice, Unaizah College of Pharmacy, Qassim University, Unaizah, Saudi Arabia
| | - Alian A. Alrasheedy
- Department of Pharmacy Practice, Unaizah College of Pharmacy, Qassim University, Unaizah, Saudi Arabia
| | - Saud Alsahali
- Department of Pharmacy Practice, Unaizah College of Pharmacy, Qassim University, Unaizah, Saudi Arabia
| | - Saeed O. Alfadly
- Department of Pharmacy Practice, Unaizah College of Pharmacy, Qassim University, Unaizah, Saudi Arabia
- Pharmacy Department, College of Medicine and Health Sciences, Hadramout University, Hadramout, Yemen
| | | |
Collapse
|
10
|
Getnet F, Demissie M, Worku A, Gobena T, Tschopp R, Girmachew M, Assefa G, Seyoum B. Delay in diagnosis of pulmonary tuberculosis increases the risk of pulmonary cavitation in pastoralist setting of Ethiopia. BMC Pulm Med 2019; 19:201. [PMID: 31694601 PMCID: PMC6836413 DOI: 10.1186/s12890-019-0971-y] [Citation(s) in RCA: 11] [Impact Index Per Article: 2.2] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/21/2019] [Accepted: 10/21/2019] [Indexed: 11/23/2022] Open
Abstract
BACKGROUND Delay in diagnosis and treatment of pulmonary tuberculosis (PTB) leads to severe disease, adverse outcomes and increased transmission. Assessing the extent of delay and its effect on disease progression in TB affected settings has clinical and programmatic importance. Hence, the aim of this study was to investigate the possible effect of delay on infectiousness (cavitation and smear positivity) of patients at diagnosis in Somali pastoralist area, Ethiopia. METHODS A cross-sectional study was conducted between December 2017 and October 2018, and 434 newly coming and confirmed PTB patients aged ≥15 years were recruited in five facilities. Data were collected using interview, record-review, anthropometry, Acid-fast bacilli and chest radiography techniques. Log-binomial regression models were used to reveal the association of delay and other factors associated with cavitation and smear positivity, and ROC Curve was used to determine discriminative ability and threshold delays. RESULTS Median age of patients was 30 years. Of all, 62.9% were males, and 46.5% were pastoralists. Median diagnosis delay was 49 days (IQR = 33-70). Cavitation was significantly associated with diagnosis delay [P < 0.001]; 22.2% among patients diagnosed within 30 days of illness and 51.7% if delay was over 30 days. The threshold delay that optimizes cavitation was 43 days [AUC (95% CI) = 0.67(0.62-0.72)]. Smear positivity was significantly increased in patients delayed over 49 days [p = 0.02]. Other factors associated with cavitation were age ≤ 35 years [APR (95% CI) =1.3(1.01-1.6)], chronic diseases [APR (95% CI) = 1.8(1.2-2.6)] and low MUAC*female [APR (95% CI) = 1.8(1.2-2.8)]. Smear positivity was also associated with age ≤ 35 years [APR (95% CI) =1.4(1.1-1.8)], low BMI [APR (95% CI) =1.3(1.01-1.7)] and low MUAC [APR (95% CI) =1.5(1.2-1.9)]. CONCLUSION This study highlights delay in diagnosis of pulmonary TB remained high and increased infectiousness of patients in pastoral settings of Ethiopia. Hence, delay should be targeted to improve patient outcomes and reduce transmission in such settings.
Collapse
Affiliation(s)
- Fentabil Getnet
- College of Medicine and Health Sciences, Jigjiga University, Jijiga, Ethiopia
- School of Public Health, Haramaya University, Dire Dawa, Ethiopia
| | - Meaza Demissie
- Addis Continental Institute of Public Health, Addis Ababa, Ethiopia
| | - Alemayehu Worku
- Addis Continental Institute of Public Health, Addis Ababa, Ethiopia
- School of Public Health, Addis Ababa University, Addis Ababa, Ethiopia
| | - Tesfaye Gobena
- School of Public Health, Haramaya University, Dire Dawa, Ethiopia
| | - Rea Tschopp
- Armauer Hansen Research Institute, Addis Ababa, Ethiopia
- Swiss Tropical and Public Health Institute, Basel, Switzerland
- University of Basel, Basel, Switzerland
| | | | | | - Berhanu Seyoum
- Armauer Hansen Research Institute, Addis Ababa, Ethiopia
| |
Collapse
|
11
|
Flores-Treviño S, Rodríguez-Noriega E, Garza-González E, González-Díaz E, Esparza-Ahumada S, Escobedo-Sánchez R, Pérez-Gómez HR, León-Garnica G, Morfín-Otero R. Clinical predictors of drug-resistant tuberculosis in Mexico. PLoS One 2019; 14:e0220946. [PMID: 31415616 PMCID: PMC6695153 DOI: 10.1371/journal.pone.0220946] [Citation(s) in RCA: 8] [Impact Index Per Article: 1.6] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/29/2018] [Accepted: 07/26/2019] [Indexed: 12/02/2022] Open
Abstract
Drug-resistant tuberculosis (DR-TB) remains a major global health problem. Early treatment of TB is critical; in the absence of rapid- susceptibility testing, the empiric selection of drugs should be guided by clinical data. This study aimed to determine the clinical predictors of DR-TB. From September 2010 to August 2017, sociodemographic and clinical characteristics were collected from 144 patients with tuberculosis at the Hospital Civil de Guadalajara, Mexico. Isolates were subjected to drug-susceptibility testing. Clinical predictors of DR-TB were determined using univariate and multivariate analysis. Any drug, isoniazid, and rifampin resistance rates were 47.7, 23.0, and 11.6%, respectively. The visualization of cavities and nodules through either chest radiography or computed tomography were independent predictors of DR-TB. In conclusion, early detection of DR-TB in this population could be based on multiple cavities being observed using chest imaging. This study’s results can be applied to future patients with TB in our community to optimize the DR-TB diagnostic process.
Collapse
Affiliation(s)
- Samantha Flores-Treviño
- Servicio de Gastroenterología, Hospital Universitario Dr. José Eleuterio González, Universidad Autónoma de Nuevo León, Monterrey, Nuevo León, México
| | - Eduardo Rodríguez-Noriega
- Hospital Civil de Guadalajara, Fray Antonio Alcalde, Instituto de Patología Infecciosa y Experimental, Centro Universitario de Ciencias de la Salud, Universidad de Guadalajara, Guadalajara, Jalisco, México
| | - Elvira Garza-González
- Servicio de Gastroenterología, Hospital Universitario Dr. José Eleuterio González, Universidad Autónoma de Nuevo León, Monterrey, Nuevo León, México
| | - Esteban González-Díaz
- Hospital Civil de Guadalajara, Fray Antonio Alcalde, Instituto de Patología Infecciosa y Experimental, Centro Universitario de Ciencias de la Salud, Universidad de Guadalajara, Guadalajara, Jalisco, México
| | - Sergio Esparza-Ahumada
- Hospital Civil de Guadalajara, Fray Antonio Alcalde, Instituto de Patología Infecciosa y Experimental, Centro Universitario de Ciencias de la Salud, Universidad de Guadalajara, Guadalajara, Jalisco, México
| | - Rodrigo Escobedo-Sánchez
- Hospital Civil de Guadalajara, Fray Antonio Alcalde, Instituto de Patología Infecciosa y Experimental, Centro Universitario de Ciencias de la Salud, Universidad de Guadalajara, Guadalajara, Jalisco, México
| | - Héctor R. Pérez-Gómez
- Hospital Civil de Guadalajara, Fray Antonio Alcalde, Instituto de Patología Infecciosa y Experimental, Centro Universitario de Ciencias de la Salud, Universidad de Guadalajara, Guadalajara, Jalisco, México
| | - Gerardo León-Garnica
- Hospital Civil de Guadalajara, Fray Antonio Alcalde, Instituto de Patología Infecciosa y Experimental, Centro Universitario de Ciencias de la Salud, Universidad de Guadalajara, Guadalajara, Jalisco, México
| | - Rayo Morfín-Otero
- Hospital Civil de Guadalajara, Fray Antonio Alcalde, Instituto de Patología Infecciosa y Experimental, Centro Universitario de Ciencias de la Salud, Universidad de Guadalajara, Guadalajara, Jalisco, México
- * E-mail:
| |
Collapse
|
12
|
Bouton TC, Forson A, Kudzawu S, Zigah F, Jenkins H, Bamfo TD, Carter J, Jacobson K, Kwara A. High mortality during tuberculosis retreatment at a Ghanaian tertiary center: a retrospective cohort study. Pan Afr Med J 2019; 33:111. [PMID: 31489089 PMCID: PMC6711700 DOI: 10.11604/pamj.2019.33.111.18574] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/01/2019] [Accepted: 05/15/2019] [Indexed: 11/16/2022] Open
Abstract
INTRODUCTION High mortality among individuals receiving retreatment for tuberculosis (RT-TB) persists, although reasons for these poor outcomes remain unclear. METHODS We retrospectively reviewed 394 RT-TB patients diagnosed between January 2010 and June 2016 in Accra, Ghana. RESULTS Of RT-TB patients, 161 (40.9%) were treated empirically (negative/absent smear, culture or Xpert), of whom 30.4% (49/161) had only extrapulmonary TB signs or symptoms. Mortality during treatment was 19.4%; 15-day mortality was 10.8%. In multivariable proportional hazards regression, living with HIV (aHR=2.69 [95 CI: 1.51, 4.80], p<0.01) and previous loss-to-follow up (aHR=8.27 (95 CI: 1.10, 62.25), p=0.04) were associated with mortality, while drug susceptibility testing (DST, aHR=0.36 (95 CI: 0.13, 1.01), p=0.052) was protective. Isoniazid resistance was observed in 40% (23/58 tested) and rifampin resistance in 19.1% (12/63 tested). CONCLUSION High rates of extrapulmonary TB and smear/culture negative disease highlight the barriers to achieving DST-driven RT-TB regimens and the need for improved diagnostics. Our finding of poly-drug resistance in rifampin-susceptible cases supports access to comprehensive first line DST. Additionally, interventions to reduce mortality, especially in HIV co-infected RT-TB patients, are urgently needed.
Collapse
Affiliation(s)
- Tara Catherine Bouton
- Division of Infectious Diseases, Warren Alpert Medical School, Brown University, Providence, Rhode Island
| | - Audrey Forson
- University of Ghana School of Medicine and Dentistry, Accra, Ghana
| | | | | | - Helen Jenkins
- Department of Biostatistics, Boston University School of Public Health, Boston, Massachusetts
| | | | - Jane Carter
- Division of Pulmonary, Critical Care and Sleep Medicine, Warren Alpert School of Medicine, Brown University, Providence, Rhode Island
| | - Karen Jacobson
- Section of Infectious Diseases, Boston University School of Medicine, Boston, Massachusetts
| | - Awewura Kwara
- Division of Infectious Diseases & Global Medicine, University of Florida College of Medicine, Gainesville, Florida
| |
Collapse
|
13
|
Strydom N, Gupta SV, Fox WS, Via LE, Bang H, Lee M, Eum S, Shim T, Barry CE, Zimmerman M, Dartois V, Savic RM. Tuberculosis drugs' distribution and emergence of resistance in patient's lung lesions: A mechanistic model and tool for regimen and dose optimization. PLoS Med 2019; 16:e1002773. [PMID: 30939136 PMCID: PMC6445413 DOI: 10.1371/journal.pmed.1002773] [Citation(s) in RCA: 124] [Impact Index Per Article: 24.8] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 08/10/2018] [Accepted: 02/28/2019] [Indexed: 11/18/2022] Open
Abstract
BACKGROUND The sites of mycobacterial infection in the lungs of tuberculosis (TB) patients have complex structures and poor vascularization, which obstructs drug distribution to these hard-to-reach and hard-to-treat disease sites, further leading to suboptimal drug concentrations, resulting in compromised TB treatment response and resistance development. Quantifying lesion-specific drug uptake and pharmacokinetics (PKs) in TB patients is necessary to optimize treatment regimens at all infection sites, to identify patients at risk, to improve existing regimens, and to advance development of novel regimens. Using drug-level data in plasma and from 9 distinct pulmonary lesion types (vascular, avascular, and mixed) obtained from 15 hard-to-treat TB patients who failed TB treatments and therefore underwent lung resection surgery, we quantified the distribution and the penetration of 7 major TB drugs at these sites, and we provide novel tools for treatment optimization. METHODS AND FINDINGS A total of 329 plasma- and 1,362 tissue-specific drug concentrations from 9 distinct lung lesion types were obtained according to optimal PK sampling schema from 15 patients (10 men, 5 women, aged 23 to 58) undergoing lung resection surgery (clinical study NCT00816426 performed in South Korea between 9 June 2010 and 24 June 2014). Seven major TB drugs (rifampin [RIF], isoniazid [INH], linezolid [LZD], moxifloxacin [MFX], clofazimine [CFZ], pyrazinamide [PZA], and kanamycin [KAN]) were quantified. We developed and evaluated a site-of-action mechanistic PK model using nonlinear mixed effects methodology. We quantified population- and patient-specific lesion/plasma ratios (RPLs), dynamics, and variability of drug uptake into each lesion for each drug. CFZ and MFX had higher drug exposures in lesions compared to plasma (median RPL 2.37, range across lesions 1.26-22.03); RIF, PZA, and LZD showed moderate yet suboptimal lesion penetration (median RPL 0.61, range 0.21-2.4), while INH and KAN showed poor tissue penetration (median RPL 0.4, range 0.03-0.73). Stochastic PK/pharmacodynamic (PD) simulations were carried out to evaluate current regimen combinations and dosing guidelines in distinct patient strata. Patients receiving standard doses of RIF and INH, who are of the lower range of exposure distribution, spent substantial periods (>12 h/d) below effective concentrations in hard-to-treat lesions, such as caseous lesions and cavities. Standard doses of INH (300 mg) and KAN (1,000 mg) did not reach therapeutic thresholds in most lesions for a majority of the population. Drugs and doses that did reach target exposure in most subjects include 400 mg MFX and 100 mg CFZ. Patients with cavitary lesions, irrespective of drug choice, have an increased likelihood of subtherapeutic concentrations, leading to a higher risk of resistance acquisition while on treatment. A limitation of this study was the small sample size of 15 patients, performed in a unique study population of TB patients who failed treatment and underwent lung resection surgery. These results still need further exploration and validation in larger and more diverse cohorts. CONCLUSIONS Our results suggest that the ability to reach and maintain therapeutic concentrations is both lesion and drug specific, indicating that stratifying patients based on disease extent, lesion types, and individual drug-susceptibility profiles may eventually be useful for guiding the selection of patient-tailored drug regimens and may lead to improved TB treatment outcomes. We provide a web-based tool to further explore this model and results at http://saviclab.org/tb-lesion/.
Collapse
Affiliation(s)
- Natasha Strydom
- Department of Bioengineering and Therapeutic Sciences, University of California, San Francisco, San Francisco, California, United States of America
| | - Sneha V. Gupta
- Department of Bioengineering and Therapeutic Sciences, University of California, San Francisco, San Francisco, California, United States of America
| | - William S. Fox
- Department of Bioengineering and Therapeutic Sciences, University of California, San Francisco, San Francisco, California, United States of America
| | - Laura E. Via
- Tuberculosis Research Section, Laboratory of Clinical Immunology and Microbiology, NIAID, NIH, Bethesda, Maryland, United States of America
| | - Hyeeun Bang
- Tuberculosis Research Section, Laboratory of Clinical Immunology and Microbiology, NIAID, NIH, Bethesda, Maryland, United States of America
| | - Myungsun Lee
- International Tuberculosis Research Center, Changwon, Republic of Korea
| | - Seokyong Eum
- International Tuberculosis Research Center, Changwon, Republic of Korea
| | - TaeSun Shim
- Asan Medical Center, Seoul, Republic of Korea
| | - Clifton E. Barry
- Tuberculosis Research Section, Laboratory of Clinical Immunology and Microbiology, NIAID, NIH, Bethesda, Maryland, United States of America
| | - Matthew Zimmerman
- Public Health Research Institute and New Jersey Medical School, Rutgers, The State University of New Jersey, Newark, New Jersey, United States of America
| | - Véronique Dartois
- Public Health Research Institute and New Jersey Medical School, Rutgers, The State University of New Jersey, Newark, New Jersey, United States of America
| | - Radojka M. Savic
- Department of Bioengineering and Therapeutic Sciences, University of California, San Francisco, San Francisco, California, United States of America
- * E-mail:
| |
Collapse
|
14
|
Sauer CM, Sasson D, Paik KE, McCague N, Celi LA, Sánchez Fernández I, Illigens BMW. Feature selection and prediction of treatment failure in tuberculosis. PLoS One 2018; 13:e0207491. [PMID: 30458029 PMCID: PMC6245785 DOI: 10.1371/journal.pone.0207491] [Citation(s) in RCA: 27] [Impact Index Per Article: 4.5] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/25/2018] [Accepted: 10/28/2018] [Indexed: 12/16/2022] Open
Abstract
Background Tuberculosis is a major cause of morbidity and mortality in the developing world. Drug resistance, which is predicted to rise in many countries worldwide, threatens tuberculosis treatment and control. Objective To identify features associated with treatment failure and to predict which patients are at highest risk of treatment failure. Methods On a multi-country dataset managed by the National Institute of Allergy and Infectious Diseases we applied various machine learning techniques to identify factors statistically associated with treatment failure and to predict treatment failure based on baseline demographic and clinical characteristics alone. Results The complete-case analysis database consisted of 587 patients (68% males) with a median (p25-p75) age of 40 (30–51) years. Treatment failure occurred in approximately one fourth of the patients. The features most associated with treatment failure were patterns of drug sensitivity, imaging findings, findings in the microscopy Ziehl-Nielsen stain, education status, and employment status. The most predictive model was forward stepwise selection (AUC: 0.74), although most models performed at or above AUC 0.7. A sensitivity analysis using the 643 original patients filling the missing values with multiple imputation showed similar predictive features and generally increased predictive performance. Conclusion Machine learning can help to identify patients at higher risk of treatment failure. Closer monitoring of these patients may decrease treatment failure rates and prevent emergence of antibiotic resistance. The use of inexpensive basic demographic and clinical features makes this approach attractive in low and middle-income countries.
Collapse
Affiliation(s)
- Christopher Martin Sauer
- Department of Epidemiology, Harvard T.H. Chan School of Public Health, Boston, MA, United States of America
- Institute for Medical Engineering and Science, Massachusetts Institute of Technology, Cambridge, MA, United States of America
- * E-mail:
| | - David Sasson
- Department of Biostatistics, Harvard T.H. Chan School of Public Health, Boston, MA, United States of America
| | - Kenneth E. Paik
- Institute for Medical Engineering and Science, Massachusetts Institute of Technology, Cambridge, MA, United States of America
| | - Ned McCague
- Institute for Medical Engineering and Science, Massachusetts Institute of Technology, Cambridge, MA, United States of America
| | - Leo Anthony Celi
- Institute for Medical Engineering and Science, Massachusetts Institute of Technology, Cambridge, MA, United States of America
| | - Iván Sánchez Fernández
- Division of Epilepsy and Clinical Neurophysiology, Department of Neurology, Boston Children’s Hospital, Harvard Medical School, Boston, MA, United States of America
| | - Ben M. W. Illigens
- Department of Neurology, Beth Israel Deaconess Medical Center, Harvard Medical School, Boston, MA, United States of America
| |
Collapse
|
15
|
Wáng YXJ, Chung MJ, Skrahin A, Rosenthal A, Gabrielian A, Tartakovsky M. Radiological signs associated with pulmonary multi-drug resistant tuberculosis: an analysis of published evidences. Quant Imaging Med Surg 2018; 8:161-173. [PMID: 29675357 DOI: 10.21037/qims.2018.03.06] [Citation(s) in RCA: 33] [Impact Index Per Article: 5.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/15/2023]
Abstract
Background Despite that confirmative diagnosis of pulmonary drug-sensitive tuberculosis (DS-TB) and multidrug resistant tuberculosis (MDR-TB) is determined by microbiological testing, early suspicions of MDR-TB by chest imaging are highly desirable in order to guide diagnostic process. We aim to perform an analysis of currently available literatures on radiological signs associated with pulmonary MDR-TB. Methods A literature search was performed using PubMed on January 29, 2018. The search words combination was "((extensive* drug resistant tuberculosis) OR (multidrug-resistant tuberculosis)) AND (CT or radiograph or imaging or X-ray or computed tomography)". We analyzed English language articles reported sufficient information of radiological signs of DS-TB vs. MDR-TB. Results Seventeen articles were found to be sufficiently relevant and included for analysis. The reported pulmonary MDR-TB cases were grouped into four categories: (I) previously treated (or 'secondary', or 'acquired') MDR-TB in HIV negative (-) adults; (II) new (or 'primary') MDR-TB in HIV(-) adults; (III) MDR-TB in HIV positive (+) adults; and (IV) MDR-TB in child patients. The common radiological findings of pulmonary MDR-TB included centrilobular small nodules, branching linear and nodular opacities (tree-in-bud sign), patchy or lobular areas of consolidation, cavitation, and bronchiectasis. While overall MDR-TB cases tended to have more extensive disease, more likely to be bilateral, to have pleural involvement, to have bronchiectasis, and to have lung volume loss; these signs alone were not sufficient for differential diagnosis of MDR-TB. Current literatures suggest that the radiological sign which may offer good specificity for pulmonary MDR-TB diagnosis, though maybe at the cost of low sensitivity, would be thick-walled multiple cavities, particularly if the cavity number is ≥3. For adult HIV(-) patients, new MDR-TB appear to show similar prevalence of cavity lesion, which was estimated to be around 70%, compared with previously treated MDR-TB. Conclusions Thick-walled multiple cavity lesions present the most promising radiological sign for MDR-TB diagnosis. For future studies cavity lesion characteristics should be quantified in details.
Collapse
Affiliation(s)
- Yì Xiáng J Wáng
- Department of Imaging and Interventional Radiology, Faculty of Medicine, The Chinese University of Hong Kong, Shatin, New Territories, Hong Kong, China
| | - Myung Jin Chung
- Department of Radiology and Center for Imaging Science; Samsung Medical Center, Sungkyunkwan University School of Medicine, Seoul, Korea
| | - Aliaksandr Skrahin
- Republican Scientific and Practical Centre of Pulmonology and Tuberculosis, Ministry of Health, Minsk, Belarus.,Belarus State Medical University, Minsk, Belarus
| | - Alex Rosenthal
- Office of Cyber Infrastructure and Computational Biology, National Institute of Allergy and Infectious Diseases, National Institutes of Health, Department of Health and Human Services, Bethesda, Maryland, USA
| | - Andrei Gabrielian
- Office of Cyber Infrastructure and Computational Biology, National Institute of Allergy and Infectious Diseases, National Institutes of Health, Department of Health and Human Services, Bethesda, Maryland, USA
| | - Michael Tartakovsky
- Office of Cyber Infrastructure and Computational Biology, National Institute of Allergy and Infectious Diseases, National Institutes of Health, Department of Health and Human Services, Bethesda, Maryland, USA
| |
Collapse
|