Derek James Sloan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Derek James Sloan has a total of 432 co-authors. Here are the top co-authors by number of shared publications:
- Geraint Rhys Davies
University of Liverpool
10 shared publications - Wilber Sabiiti
University of St Andrews
9 shared publications - Matthew T. G. Holden
School of Medicine, University of St Andrews, St Andrews, Scotland, United Kingdom
8 shared publications - David Griffith Lalloo
Affiliation Centre for Snakebite Research and Interventions, Liverpool School of Tropical Medicine, Liverpool, United Kingdom
6 shared publications - Elizabeth Lucy Corbett
London School of Hygiene & Tropical Medicine
6 shared publications - Jamie J. Kirkham
The University of Manchester
6 shared publications
Latest Publications
- Open Access
Time-resolved predictability of end-of-therapy outcome and relapse after cure in Phase 3 tuberculosis trials
Relapse after apparently successful tuberculosis (TB) therapy remains difficult to predict, and how relapse risk evolves throughout treatment remains unclear. Using harmonised clinical data from two Phase 3 trials (2,918 participants), we performed time-resolved prediction of end-of-therapy (EOT) outcomes and post-treatment relapse by training models using tabular data at monthly intervals from baseline to therapy end. Prediction of EOT outcomes improved after month 3 (ROC-AUC up to 0.84), driven by sputum-smear and solid culture. In contrast, relapse prediction among participants with favourable EOT outcomes and completed follow-up improved only modestly through month 3 (ROC-AUC 0.58-0.63) before declining, with age, sex, clinical symptoms and bacterial burden contributing most strongly to prediction. Models trained on large language model-derived embeddings, a more flexible representation of the same variables, matched tabular relapse models in performance throughout therapy, and outperformed tabular EOT outcome models at months 3 and 4 (ΔROC-AUC: 0.12 and 0.14), with longitudinal modelling and sparse variable inclusion only improving relapse prediction at months 4-6 (ΔROC-AUC: 0.09, 0.19 and 0.12), however with reduced interpretability. Models incorporating data after baseline provided incremental improvements in post-treatment relapse risk stratification compared with baseline cavitation and sputum smear alone (4-month relapse-free survival: 94.8%/78.5% for model-derived low/high risk groups, vs. 91.4%/82.9% for baseline easy-/hard-to-treat groups). Overall, these findings suggest that while routine clinical data collected after baseline can improve post-treatment risk stratification, it offers limited predictive value for relapse, underscoring the need for relapse-specific biomarkers.
Open AccessTime-resolved predictability of end-of-therapy outcome and relapse after cure in Phase 3 tuberculosis trials
Relapse after apparently successful tuberculosis (TB) therapy remains difficult to predict, and how relapse risk evolves throughout treatment remains unclear. Using harmonised clinical data from two Phase 3 trials (2,918 participants), we performed time-resolved prediction of end-of-therapy (EOT) outcomes and post-treatment relapse by training models using tabular data at monthly intervals from baseline to therapy end. Prediction of EOT outcomes improved after month 3 (ROC-AUC up to 0.84), driven by sputum-smear and solid culture. In contrast, relapse prediction among participants with favourable EOT outcomes and completed follow-up improved only modestly through month 3 (ROC-AUC 0.58-0.63) before declining, with age, sex, clinical symptoms and bacterial burden contributing most strongly to prediction. Models trained on large language model-derived embeddings, a more flexible representation of the same variables, matched tabular relapse models in performance throughout therapy, and outperformed tabular EOT outcome models at months 3 and 4 (ΔROC-AUC: 0.12 and 0.14), with longitudinal modelling and sparse variable inclusion only improving relapse prediction at months 4-6 (ΔROC-AUC: 0.09, 0.19 and 0.12), however with reduced interpretability. Models incorporating data after baseline provided incremental improvements in post-treatment relapse risk stratification compared with baseline cavitation and sputum smear alone (4-month relapse-free survival: 94.8%/78.5% for model-derived low/high risk groups, vs. 91.4%/82.9% for baseline easy-/hard-to-treat groups). Overall, these findings suggest that while routine clinical data collected after baseline can improve post-treatment risk stratification, it offers limited predictive value for relapse, underscoring the need for relapse-specific biomarkers.
- Open Access
- 19 March 2026
- Published by European Respiratory Society (ERS) in European Respiratory Journal
- Vol. 67 (5) , 2501531
Rising bedaquiline resistance: exploring potential causes and next steps
Although the estimated incidence of multidrug-resistant (MDR)/rifampicin-resistant (RR) tuberculosis (TB) has been relatively stable in recent years, MDR/RR-TB still represents a significant public health threat, with an estimated number of 400 000 new cases in 2023 [1]. The US Food and Drug Administration granted bedaquiline (BDQ) accelerated approval in 2012, and although the label does not include recommendations for the treatment of RR-TB, BDQ is being incorporated into all guideline-recommended standard regimens for MDR/RR-TB worldwide [1, 2].
- 19 March 2026
- Published by European Respiratory Society (ERS) in European Respiratory Journal
- Vol. 67 (5) , 2501531
Open AccessRising bedaquiline resistance: exploring potential causes and next steps
Although the estimated incidence of multidrug-resistant (MDR)/rifampicin-resistant (RR) tuberculosis (TB) has been relatively stable in recent years, MDR/RR-TB still represents a significant public health threat, with an estimated number of 400 000 new cases in 2023 [1]. The US Food and Drug Administration granted bedaquiline (BDQ) accelerated approval in 2012, and although the label does not include recommendations for the treatment of RR-TB, BDQ is being incorporated into all guideline-recommended standard regimens for MDR/RR-TB worldwide [1, 2].
- Open Access
- 1 January 2026
- Published by Microbiology Society in Access Microbiology
- Vol. 8 (1)
Draft genome sequence of a non-tuberculous Mycobacterium strain isolated from a clinical urine sample
Here, we report the draft sequence of a rapid-growing nontuberculous Mycobacterium isolated from a urine sample at the Scottish Mycobacteria Reference Laboratory, Royal Infirmary of Edinburgh, UK. The reported genome has a length of 6,749,454 bp, a G+C content of 67.2 mol% and 6,336 protein CDSs. Average nucleotide identity (ANI) analysis identified Mycobacterium vanbaalenii PYR-1 as the closest relative (83.32% ANI), indicating that this isolate likely represents a novel species within the genus. Notably, phenotypic characterization revealed a distinct antimicrobial resistance (AMR) profile. This assembly provides a valuable resource for studying the evolution of AMR mechanisms in nontuberculous mycobacteria and offers insight into resistance phenotypes observed in clinical isolates.
- 1 January 2026
- Published by Microbiology Society in Access Microbiology
- Vol. 8 (1)
Open AccessDraft genome sequence of a non-tuberculous Mycobacterium strain isolated from a clinical urine sample
Here, we report the draft sequence of a rapid-growing nontuberculous Mycobacterium isolated from a urine sample at the Scottish Mycobacteria Reference Laboratory, Royal Infirmary of Edinburgh, UK. The reported genome has a length of 6,749,454 bp, a G+C content of 67.2 mol% and 6,336 protein CDSs. Average nucleotide identity (ANI) analysis identified Mycobacterium vanbaalenii PYR-1 as the closest relative (83.32% ANI), indicating that this isolate likely represents a novel species within the genus. Notably, phenotypic characterization revealed a distinct antimicrobial resistance (AMR) profile. This assembly provides a valuable resource for studying the evolution of AMR mechanisms in nontuberculous mycobacteria and offers insight into resistance phenotypes observed in clinical isolates.
- Open Access
- 22 December 2025
- Published by Microbiology Society
- p. 001110.v2
Draft Genome Sequence of a non-tuberculous Mycobacterium Strain Isolated from a Clinical Urine Sample.
Here we report the draft sequence of a rapid-growing nontuberculous Mycobacterium isolated from a urine sample at the Scottish Mycobacteria Reference Laboratory (SMRL), Royal Infirmary of Edinburgh, UK. The reported genome has a length of 6,749,454 bp, a GC content of 67.2%, and 6,336 protein-coding sequences. Average nucleotide identity (ANI) analysis identified Mycobacterium vanbaalenii PYR-1 as the closest relative (83.32% ANI), indicating that this isolate likely represents a novel species within the genus. Notably, phenotypic characterisation revealed a distinct antimicrobial resistance (AMR) profile. This assembly provides a valuable resource for studying the evolution of antimicrobial resistance mechanisms in nontuberculous mycobacteria and offers insight into resistance phenotypes observed in clinical isolates.
- 22 December 2025
- Published by Microbiology Society
- p. 001110.v2
Open AccessDraft Genome Sequence of a non-tuberculous Mycobacterium Strain Isolated from a Clinical Urine Sample.
Here we report the draft sequence of a rapid-growing nontuberculous Mycobacterium isolated from a urine sample at the Scottish Mycobacteria Reference Laboratory (SMRL), Royal Infirmary of Edinburgh, UK. The reported genome has a length of 6,749,454 bp, a GC content of 67.2%, and 6,336 protein-coding sequences. Average nucleotide identity (ANI) analysis identified Mycobacterium vanbaalenii PYR-1 as the closest relative (83.32% ANI), indicating that this isolate likely represents a novel species within the genus. Notably, phenotypic characterisation revealed a distinct antimicrobial resistance (AMR) profile. This assembly provides a valuable resource for studying the evolution of antimicrobial resistance mechanisms in nontuberculous mycobacteria and offers insight into resistance phenotypes observed in clinical isolates.
- Open Access
- 3 September 2025
- Published by Microbiology Society
- p. 001110.v1
Draft Genome Sequence of a non-tuberculous Mycobacterium Strain Isolated from a Clinical Urine Sample.
Here we report the draft sequence of a rapid-growing nontuberculous Mycobacterium isolated from a urine sample at the Scottish Mycobacteria Reference Laboratory (SMRL), Royal Infirmary of Edinburgh, UK. The reported Mycobacterium genome has a length of 6,749,454 bp, a GC content of 67.2%, and 6,336 protein coding sequences. An average nucleotide identity (ANI) analysis found that the closest relative was Mycobacterium vanbaalenii PYR-1, with 83.32% ANI.
- 3 September 2025
- Published by Microbiology Society
- p. 001110.v1
Open AccessDraft Genome Sequence of a non-tuberculous Mycobacterium Strain Isolated from a Clinical Urine Sample.
Here we report the draft sequence of a rapid-growing nontuberculous Mycobacterium isolated from a urine sample at the Scottish Mycobacteria Reference Laboratory (SMRL), Royal Infirmary of Edinburgh, UK. The reported Mycobacterium genome has a length of 6,749,454 bp, a GC content of 67.2%, and 6,336 protein coding sequences. An average nucleotide identity (ANI) analysis found that the closest relative was Mycobacterium vanbaalenii PYR-1, with 83.32% ANI.
- Open Access
- 28 May 2025
- Published by F1000 Research Ltd in Wellcome Open Research
- Vol. 10, 282
Multimorbidity in tuberculosis (TB) and its impact on patient care (MITICare): a cross-sectional study nested within a prospective cohort study protocol.
Multimorbidity, defined as two or more co-existing long-term health conditions, is increasing in low- and middle-income countries, overlapping with ongoing high tuberculosis (TB) incidence. It is known that there is a high prevalence of multimorbidity in patients with TB in South Africa, but our understanding of how common TB-multimorbidity is in other African countries, and its effect on the trajectories of TB care, is limited. This cross-sectional study nested within a prospective cohort (co-designed between the Infectious Diseases Institute, Uganda and the University of St Andrews, United Kingdom) aims to describe the burden and evaluate the consequences of multimorbidity among patients with TB disease in Kampala, Uganda. The primary objective is to describe the prevalence of multimorbidity at the start of treatment for TB. The secondary objectives are to determine the effect of multimorbidity on clinical characteristics at the start of treatment, progress through TB care, and end of TB treatment outcomes. 254 adults commencing treatment for TB shall be recruited. Multimorbidity shall be assessed using structured questionnaires, simple examination and blood analysis. Th clinical characteristics of TB shall be determined using health and quality of life scores and, in patients with pulmonary TB, the degree of chest X-ray abnormalities and sputum bacillary burden. Patients shall be followed-up at two and six months and their response to treatment determined. The analysis of the prevalence of multimorbidity at baseline shall be reported using a proportion and 95% confidence interval. For the secondary objectives, regression models adjusting for confounders identified through directed acyclic graphs will be used. This study has been developed in close collaboration with a core patient and public involvement group, who will also be actively involved in the dissemination of study results. Ugandan and St Andrews University ethical approval has been prospectively granted (IDI-REC-2023-82, MD17720 and HS3888ES).
- 28 May 2025
- Published by F1000 Research Ltd in Wellcome Open Research
- Vol. 10, 282
Open AccessMultimorbidity in tuberculosis (TB) and its impact on patient care (MITICare): a cross-sectional study nested within a prospective cohort study protocol.
Multimorbidity, defined as two or more co-existing long-term health conditions, is increasing in low- and middle-income countries, overlapping with ongoing high tuberculosis (TB) incidence. It is known that there is a high prevalence of multimorbidity in patients with TB in South Africa, but our understanding of how common TB-multimorbidity is in other African countries, and its effect on the trajectories of TB care, is limited. This cross-sectional study nested within a prospective cohort (co-designed between the Infectious Diseases Institute, Uganda and the University of St Andrews, United Kingdom) aims to describe the burden and evaluate the consequences of multimorbidity among patients with TB disease in Kampala, Uganda. The primary objective is to describe the prevalence of multimorbidity at the start of treatment for TB. The secondary objectives are to determine the effect of multimorbidity on clinical characteristics at the start of treatment, progress through TB care, and end of TB treatment outcomes. 254 adults commencing treatment for TB shall be recruited. Multimorbidity shall be assessed using structured questionnaires, simple examination and blood analysis. Th clinical characteristics of TB shall be determined using health and quality of life scores and, in patients with pulmonary TB, the degree of chest X-ray abnormalities and sputum bacillary burden. Patients shall be followed-up at two and six months and their response to treatment determined. The analysis of the prevalence of multimorbidity at baseline shall be reported using a proportion and 95% confidence interval. For the secondary objectives, regression models adjusting for confounders identified through directed acyclic graphs will be used. This study has been developed in close collaboration with a core patient and public involvement group, who will also be actively involved in the dissemination of study results. Ugandan and St Andrews University ethical approval has been prospectively granted (IDI-REC-2023-82, MD17720 and HS3888ES).
- Open Access
Triage test for all-oral drug-resistant tuberculosis (DR-TB) regimen: a phase IV study to assess effectiveness, feasibility, acceptability and cost-effectiveness of the Xpert MTB/XDR assay for rapid triage and treatment of DR-TB
Introduction: The TriAD study will assess the Xpert MTB/XDR (Xpert XDR; Cepheid) assay to detect tuberculosis (TB) drug resistance in sputum testing positive for TB to rapidly triage and treat patients with a short all-oral treatment regimen. Methods and analysis: In this study, approximately 4800 Xpert MTB/RIF or Ultra MTB-positive patients (irrespective of rifampicin (RIF) resistance (RR) status) from several clinical sites across South Africa, Nigeria and Ethiopia will be enrolled over 18–24 months and followed-up for approximately 6 months post-TB treatment completion. Participants will be enrolled into one of two cohorts based on Xpert MTB/RIF and Xpert XDR results: Mycobacterium tuberculosis ( M.tb ) positive participants with RR in Cohort 1 (n=880) and M.tb positive RIF susceptible TB patients with isoniazid mono-resistance irrespective of presence of resistance to fluoroquinolones, second-line injectable drugs or ethionamide in Cohort 2 (n=400). Cohort 1 will be compared with historical cohorts from each implementing sites. The primary study outcomes include time to initiation of an appropriate treatment regimen by resistance profile and the proportion of patients with favourable treatment outcomes compared with historical cohorts from each of the implementing sites. Secondary outcomes include feasibility, acceptability and cost-effectiveness of this approach to inform policies and guidelines for programmatic implementation of this triage and treat model for drug-resistant tuberculosis management. Utility of the tuberculosis molecular bacterial load assay (TB-MBLA) for real-time treatment response assessment will also be evaluated. Ethics and dissemination: The University of KwaZulu-Natal Biomedical Research Ethics Committee (BREC) and local research committees have provided ethical review and approval (BREC/00002654/2021, HREC 210805, NHREC/01/01/2007 and EPHI-IRB-459–2022). The South African Health Products Regulatory Authority (SAHPRA) have granted regulatory approval for the TRiAD Study (SAHPRA MD20211001). Trial results will be disseminated through conference presentations, peer-reviewed publications and the clinical trial registry. Trial registration number: Clinicaltrials.gov; Trial registration number: NCT05175794 ; South African National Clinical Trials Register (SANCTR DOH-27-012022-4720)
Open AccessTriage test for all-oral drug-resistant tuberculosis (DR-TB) regimen: a phase IV study to assess effectiveness, feasibility, acceptability and cost-effectiveness of the Xpert MTB/XDR assay for rapid triage and treatment of DR-TB
Introduction: The TriAD study will assess the Xpert MTB/XDR (Xpert XDR; Cepheid) assay to detect tuberculosis (TB) drug resistance in sputum testing positive for TB to rapidly triage and treat patients with a short all-oral treatment regimen. Methods and analysis: In this study, approximately 4800 Xpert MTB/RIF or Ultra MTB-positive patients (irrespective of rifampicin (RIF) resistance (RR) status) from several clinical sites across South Africa, Nigeria and Ethiopia will be enrolled over 18–24 months and followed-up for approximately 6 months post-TB treatment completion. Participants will be enrolled into one of two cohorts based on Xpert MTB/RIF and Xpert XDR results: Mycobacterium tuberculosis ( M.tb ) positive participants with RR in Cohort 1 (n=880) and M.tb positive RIF susceptible TB patients with isoniazid mono-resistance irrespective of presence of resistance to fluoroquinolones, second-line injectable drugs or ethionamide in Cohort 2 (n=400). Cohort 1 will be compared with historical cohorts from each implementing sites. The primary study outcomes include time to initiation of an appropriate treatment regimen by resistance profile and the proportion of patients with favourable treatment outcomes compared with historical cohorts from each of the implementing sites. Secondary outcomes include feasibility, acceptability and cost-effectiveness of this approach to inform policies and guidelines for programmatic implementation of this triage and treat model for drug-resistant tuberculosis management. Utility of the tuberculosis molecular bacterial load assay (TB-MBLA) for real-time treatment response assessment will also be evaluated. Ethics and dissemination: The University of KwaZulu-Natal Biomedical Research Ethics Committee (BREC) and local research committees have provided ethical review and approval (BREC/00002654/2021, HREC 210805, NHREC/01/01/2007 and EPHI-IRB-459–2022). The South African Health Products Regulatory Authority (SAHPRA) have granted regulatory approval for the TRiAD Study (SAHPRA MD20211001). Trial results will be disseminated through conference presentations, peer-reviewed publications and the clinical trial registry. Trial registration number: Clinicaltrials.gov; Trial registration number: NCT05175794 ; South African National Clinical Trials Register (SANCTR DOH-27-012022-4720)
- Open Access
Analysis of time-to-positivity data in tuberculosis treatment studies: Identifying a new limit of quantification
The BACTEC Mycobacteria Growth Indicator Tube (MGIT) machine is the standard globally for detecting viable mycobacteria in patients’ sputum. Samples are observed for no longer than 42 days, at which point the sample is declared “negative” for tuberculosis (TB). This time to detection of bacterial growth, referred to as time-to-positivity (TTP), is increasingly of interest not solely as a diagnostic tool, but as a continuous biomarker wherein change in TTP over time can be used for comparing the bactericidal activity of different TB treatments. However, as a continuous measure, there are oddities in the distribution of TTP values observed, particularly at higher values. We explored whether there is evidence to suggest setting an upper limit of quantification (ULOQ M ) lower than the diagnostic limit of detection (LOD) using data from several TB-PACTS randomized clinical trials and PanACEA MAMS-TB. Across all trials, less than 7.1% of all weekly samples returned TTP measurements between 25 and 42 days. Further, the relative absolute prediction error (%) was highest in this range. When modeling with ULOQ M s of 25 and 30 days, the precision in estimation improved for 23 of 25 regimen-level slopes as compared to models using the diagnostic LOD while also improving the discrimination between regimens based on Bayesian posteriors. While TTP measurements between 25 days and the diagnostic LOD may be important for diagnostic purposes, TTP values in this range may not contribute meaningfully to its use as a quantitative measure, particularly when assessing treatment response, and may lead to under-powered clinical trials. Highlights: The BACTEC Mycobacteria Growth Indicator Tube (MGIT) machine is the STAND, PaMZard globally for the detection and diagnosis of tuberculosis. As MGIT machine use becomes more ubiquitous, its time-to-positivity (TTP) measures are increasingly of interest as a continuous biomarker for evaluating bactericidal activity of TB treatment regimens. Using data from seven previously published trials, this work highlights the evidence for setting a limit of quantification for quantitative analyses that is below the diagnostic limit of detection. TTP values near the upper limit of detection appear to be noisier and sparser, with precision improving for estimation of 23 of 25 regimen-specific rates of change in TTP when analyzed with a lower limit of quantification. While TTP measurements between 25 days and the diagnostic LOD may be important for diagnostic purposes, TTP values in this range may not contribute meaningfully to its use as a quantitative measure, particularly when assessing early treatment response.
Open AccessAnalysis of time-to-positivity data in tuberculosis treatment studies: Identifying a new limit of quantification
The BACTEC Mycobacteria Growth Indicator Tube (MGIT) machine is the standard globally for detecting viable mycobacteria in patients’ sputum. Samples are observed for no longer than 42 days, at which point the sample is declared “negative” for tuberculosis (TB). This time to detection of bacterial growth, referred to as time-to-positivity (TTP), is increasingly of interest not solely as a diagnostic tool, but as a continuous biomarker wherein change in TTP over time can be used for comparing the bactericidal activity of different TB treatments. However, as a continuous measure, there are oddities in the distribution of TTP values observed, particularly at higher values. We explored whether there is evidence to suggest setting an upper limit of quantification (ULOQ M ) lower than the diagnostic limit of detection (LOD) using data from several TB-PACTS randomized clinical trials and PanACEA MAMS-TB. Across all trials, less than 7.1% of all weekly samples returned TTP measurements between 25 and 42 days. Further, the relative absolute prediction error (%) was highest in this range. When modeling with ULOQ M s of 25 and 30 days, the precision in estimation improved for 23 of 25 regimen-level slopes as compared to models using the diagnostic LOD while also improving the discrimination between regimens based on Bayesian posteriors. While TTP measurements between 25 days and the diagnostic LOD may be important for diagnostic purposes, TTP values in this range may not contribute meaningfully to its use as a quantitative measure, particularly when assessing treatment response, and may lead to under-powered clinical trials. Highlights: The BACTEC Mycobacteria Growth Indicator Tube (MGIT) machine is the STAND, PaMZard globally for the detection and diagnosis of tuberculosis. As MGIT machine use becomes more ubiquitous, its time-to-positivity (TTP) measures are increasingly of interest as a continuous biomarker for evaluating bactericidal activity of TB treatment regimens. Using data from seven previously published trials, this work highlights the evidence for setting a limit of quantification for quantitative analyses that is below the diagnostic limit of detection. TTP values near the upper limit of detection appear to be noisier and sparser, with precision improving for estimation of 23 of 25 regimen-specific rates of change in TTP when analyzed with a lower limit of quantification. While TTP measurements between 25 days and the diagnostic LOD may be important for diagnostic purposes, TTP values in this range may not contribute meaningfully to its use as a quantitative measure, particularly when assessing early treatment response.
- Open Access
- 19 January 2024
- Published by International Society of Global Health in Journal of Global Health
- Vol. 14, 05007
Treatment seeking and antibiotic use for urinary tract infection symptoms in the time of COVID-19 in Tanzania and Uganda
Antimicrobial resistance (AMR) is a global public health issue which makes infections more costly to treat and common health care interventions such as surgeries potentially life-threatening [1–3]. The burden of drug-resistant infections is estimated to be highest in low- and middle-income regions, particularly Africa [4], where infectious disease accounts for a higher share of morbidity […]
- 19 January 2024
- Published by International Society of Global Health in Journal of Global Health
- Vol. 14, 05007
Open AccessTreatment seeking and antibiotic use for urinary tract infection symptoms in the time of COVID-19 in Tanzania and Uganda
Antimicrobial resistance (AMR) is a global public health issue which makes infections more costly to treat and common health care interventions such as surgeries potentially life-threatening [1–3]. The burden of drug-resistant infections is estimated to be highest in low- and middle-income regions, particularly Africa [4], where infectious disease accounts for a higher share of morbidity […]
- Open Access
- 13 October 2023
- Published by Elsevier in Computers in Biology and Medicine
- Vol. 167, 107573
Localization and phenotyping of tuberculosis bacteria using a combination of deep learning and SVMs
- 13 October 2023
- Published by Elsevier in Computers in Biology and Medicine
- Vol. 167, 107573
Open AccessLocalization and phenotyping of tuberculosis bacteria using a combination of deep learning and SVMs