Ponnuraja Chinnaiyan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Ponnuraja Chinnaiyan has a total of 70 co-authors. Here are the top co-authors by number of shared publications:
- Shaik Fayaz Ahamed
Department of Statistics, ICMR—National Institute for Research in Tuberculosis, Chennai 600 031, India
4 shared publications - Sundarakumar Karuppasamy
Department of Statistics, ICMR—National Institute for Research in Tuberculosis, Chennai 600 031, India
4 shared publications - Vasantha Mahalingam
Department of Statistics, ICMR-National Institute for Research in Tuberculosis, Chennai, Tamil Nadu, India
4 shared publications - Nagaraj Jaganathasamy
Department of Biostatistics, ICMR—National Institute of Immunohaemotology (NIIH), Mumbai 400 012, Maharashtra, India
3 shared publications - Adalarasan Natesan
Department of Pediatrics, Government Kilpauk Medical College, Chennai 600 010, Tamil Nadu, India
2 shared publications Adhin Bhaskar
Department of Statistics, ICMR-National Institute for Research in Tuberculosis, Chennai, Tamil Nadu, India
2 shared publications
Latest Publications
- Open Access
- 26 December 2025
- Published by Elsevier in Results in Engineering
- Vol. 29
A hierarchical ensemble machine learning framework for precision survival prediction in breast cancer using SEER data
- 26 December 2025
- Published by Elsevier in Results in Engineering
- Vol. 29
Open AccessA hierarchical ensemble machine learning framework for precision survival prediction in breast cancer using SEER data
- Open Access
- 10 October 2025
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 20 (10) , e0333992
Generalized estimating equations for modeling cluster randomized trial data on smoking cessation among tuberculosis patients
There is a paucity of studies applying Generalized Estimating Equations (GEE) for longitudinal analysis of smoking cessation outcomes within the framework of a cluster randomized trial, especially among tuberculosis (TB) patients. In this study, a GEE model which accounts for repeated measures and cluster-level effects was implemented to identify factors associated with smoking cessation among TB patients. The data included 375 TB patients who were smokers and given TB treatment during 2013–2016 in Kanchipuram and Villupuram districts under a cluster randomized trial. GEE modeling provided robust, population-averaged estimates while accounting for intra-cluster correlation, confirming the sustained impact of these interventions. The model demonstrated that smoking cessation interventions, when integrated with TB treatment, had an impact on cessation outcomes in these populations.
- 10 October 2025
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 20 (10) , e0333992
Open AccessGeneralized estimating equations for modeling cluster randomized trial data on smoking cessation among tuberculosis patients
There is a paucity of studies applying Generalized Estimating Equations (GEE) for longitudinal analysis of smoking cessation outcomes within the framework of a cluster randomized trial, especially among tuberculosis (TB) patients. In this study, a GEE model which accounts for repeated measures and cluster-level effects was implemented to identify factors associated with smoking cessation among TB patients. The data included 375 TB patients who were smokers and given TB treatment during 2013–2016 in Kanchipuram and Villupuram districts under a cluster randomized trial. GEE modeling provided robust, population-averaged estimates while accounting for intra-cluster correlation, confirming the sustained impact of these interventions. The model demonstrated that smoking cessation interventions, when integrated with TB treatment, had an impact on cessation outcomes in these populations.
- Open Access
- 23 July 2025
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 20 (7) , e0328484
Health related quality of life of tuberculosis patients in South India: A longitudinal assessment study
Background: In India, there is no information on health related quality of life (HRQoL) of patients with drug sensitive tuberculosis (TB) using a longitudinal design that includes post- treatment period. This study is the first of its kind in India to assess HRQoL of TB patients from a longitudinal prospective and to identify the factors associated with changes in HRQoL. Methods: The study participants were 180 newly diagnosed drug-sensitive smear-positive pulmonary TB patients who were initiated on treatment under the National TB Elimination Programme (NTEP) in Chennai and Tiruvallur districts of Tamil Nadu, South India. The patients were interviewed at four different time points between 2020 and 2023 using validated questionnaires assessing general health (European Quality of Life-5 Dimensions-5 Level (EQ-5D-5L), Short Form health survey (SF-20)), disease specific (St. George’s Respiratory Questionnaire (SGRQ)) and mental health including depression and anxiety (Patient Health Questionnaire (PHQ-9), Generalized Anxiety Disorder (GAD-7)). The Friedman test was used to identify changes in HRQoL scores over time and generalised estimating equation (GEE) were applied to identify factors associated with HRQoL. Results: HRQoL scores of TB patients, as measured by different scales showed significant improvement from treatment initiation to treatment completion. The GEE analysis showed that the EQ-5D-5L scores over follow-up visits were significantly lower in females (−0.038, p < 0.005) and higher in those who did not skip their main meal in a day (0.077, p < 0.001). The PHQ-9 and GAD-7 scores were significantly higher among females (0.609, p < 0.05; 0.531, p < 0.05). Additionally, PHQ-9 scores were also higher among patients from rural district (0.392, p < 0.05). The SF-20 scores were significantly lower in patients aged >45 years (−1.675, p < 0.05), female (−3.809, p < 0.001) and unemployed (−2.277, p < 0.005). The SGRQ scores were higher in patients aged >45 years (3.043, p < 0.01), females (4.256, p < 0.05) and those from rural district (2.219, p < 0.05). The HRQoL scores were significantly higher in patients who did not skip their main meal and lower in females irrespective of the scales used. Conclusion: The HRQoL of TB patients improved significantly over a period of treatment. Gender, age, skipping main meals, region and employment status were the key factors influencing HRQoL. Focusing on HRQoL assessment in the care of TB patients could help to minimize physical, mental and social challenges and enable them to lead a normal life.
- 23 July 2025
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 20 (7) , e0328484
Open AccessHealth related quality of life of tuberculosis patients in South India: A longitudinal assessment study
Background: In India, there is no information on health related quality of life (HRQoL) of patients with drug sensitive tuberculosis (TB) using a longitudinal design that includes post- treatment period. This study is the first of its kind in India to assess HRQoL of TB patients from a longitudinal prospective and to identify the factors associated with changes in HRQoL. Methods: The study participants were 180 newly diagnosed drug-sensitive smear-positive pulmonary TB patients who were initiated on treatment under the National TB Elimination Programme (NTEP) in Chennai and Tiruvallur districts of Tamil Nadu, South India. The patients were interviewed at four different time points between 2020 and 2023 using validated questionnaires assessing general health (European Quality of Life-5 Dimensions-5 Level (EQ-5D-5L), Short Form health survey (SF-20)), disease specific (St. George’s Respiratory Questionnaire (SGRQ)) and mental health including depression and anxiety (Patient Health Questionnaire (PHQ-9), Generalized Anxiety Disorder (GAD-7)). The Friedman test was used to identify changes in HRQoL scores over time and generalised estimating equation (GEE) were applied to identify factors associated with HRQoL. Results: HRQoL scores of TB patients, as measured by different scales showed significant improvement from treatment initiation to treatment completion. The GEE analysis showed that the EQ-5D-5L scores over follow-up visits were significantly lower in females (−0.038, p < 0.005) and higher in those who did not skip their main meal in a day (0.077, p < 0.001). The PHQ-9 and GAD-7 scores were significantly higher among females (0.609, p < 0.05; 0.531, p < 0.05). Additionally, PHQ-9 scores were also higher among patients from rural district (0.392, p < 0.05). The SF-20 scores were significantly lower in patients aged >45 years (−1.675, p < 0.05), female (−3.809, p < 0.001) and unemployed (−2.277, p < 0.005). The SGRQ scores were higher in patients aged >45 years (3.043, p < 0.01), females (4.256, p < 0.05) and those from rural district (2.219, p < 0.05). The HRQoL scores were significantly higher in patients who did not skip their main meal and lower in females irrespective of the scales used. Conclusion: The HRQoL of TB patients improved significantly over a period of treatment. Gender, age, skipping main meals, region and employment status were the key factors influencing HRQoL. Focusing on HRQoL assessment in the care of TB patients could help to minimize physical, mental and social challenges and enable them to lead a normal life.
- Open Access
- 7 July 2025
- Published by MDPI AG in Informatics
- Vol. 12 (3) , 64
Clinical Text Classification for Tuberculosis Diagnosis Using Natural Language Processing and Deep Learning Model with Statistical Feature Selection Technique
Background: In the medical field, various deep learning (DL) algorithms have been effectively used to extract valuable information from unstructured clinical text data, potentially leading to more effective outcomes. This study utilized clinical text data to classify clinical case reports into tuberculosis (TB) and non-tuberculosis (non-TB) groups using natural language processing (NLP), a pre-processing technique, and DL models. Methods: This study used 1743 open-source respiratory disease clinical text data, labeled via fuzzy matching with ICD-10 codes to create a labeled dataset. Two tokenization methods preprocessed the clinical text data, and three models were evaluated: the existing Text-CNN, the proposed Text-CNN with t-test, and Bio_ClinicalBERT. Performance was assessed using multiple metrics and validated on 228 baseline screening clinical case text data collected from ICMR–NIRT to demonstrate effective TB classification. Results: The proposed model achieved the best results in both the test and validation datasets. On the test dataset, it attained a precision of 88.19%, a recall of 90.71%, an F1-score of 89.44%, and an AUC of 0.91. Similarly, on the validation dataset, it achieved 100% precision, 98.85% recall, 99.42% F1-score, and an AUC of 0.982, demonstrating its effectiveness in TB classification. Conclusions: This study highlights the effectiveness of DL models in classifying TB cases from clinical notes. The proposed model outperformed the other two models. The TF-IDF and t-test showed statistically significant feature selection and enhanced model interpretability and efficiency, demonstrating the potential of NLP and DL in automating TB diagnosis in clinical decision settings.
- 7 July 2025
- Published by MDPI AG in Informatics
- Vol. 12 (3) , 64
Open AccessClinical Text Classification for Tuberculosis Diagnosis Using Natural Language Processing and Deep Learning Model with Statistical Feature Selection Technique
Background: In the medical field, various deep learning (DL) algorithms have been effectively used to extract valuable information from unstructured clinical text data, potentially leading to more effective outcomes. This study utilized clinical text data to classify clinical case reports into tuberculosis (TB) and non-tuberculosis (non-TB) groups using natural language processing (NLP), a pre-processing technique, and DL models. Methods: This study used 1743 open-source respiratory disease clinical text data, labeled via fuzzy matching with ICD-10 codes to create a labeled dataset. Two tokenization methods preprocessed the clinical text data, and three models were evaluated: the existing Text-CNN, the proposed Text-CNN with t-test, and Bio_ClinicalBERT. Performance was assessed using multiple metrics and validated on 228 baseline screening clinical case text data collected from ICMR–NIRT to demonstrate effective TB classification. Results: The proposed model achieved the best results in both the test and validation datasets. On the test dataset, it attained a precision of 88.19%, a recall of 90.71%, an F1-score of 89.44%, and an AUC of 0.91. Similarly, on the validation dataset, it achieved 100% precision, 98.85% recall, 99.42% F1-score, and an AUC of 0.982, demonstrating its effectiveness in TB classification. Conclusions: This study highlights the effectiveness of DL models in classifying TB cases from clinical notes. The proposed model outperformed the other two models. The TF-IDF and t-test showed statistically significant feature selection and enhanced model interpretability and efficiency, demonstrating the potential of NLP and DL in automating TB diagnosis in clinical decision settings.
- Open Access
An Application for Spatial Frailty Models: An Exploration with Data on Fungal Sepsis in Neonates
Background: Globally, neonatal fungal sepsis (NFS) is a leading cause of neonatal mortality, particularly among vulnerable populations in neonatal intensive care units (NICU). The use of spatial frailty models with a Bayesian approach to identify hotspots and risk factors for neonatal deaths due to fungal sepsis has not been explored before. Methods: A cohort of 80 neonates admitted to the NICU at a Government Hospital in Tamil Nadu, India and diagnosed with fungal sepsis through blood cultures between 2018–2020 was considered for this study. Bayesian spatial frailty models using parametric distributions, such as Log-logistic, Log-normal, and Weibull proportional hazard (PH) models, were employed to identify associated risk factors for NFS deaths and hotspot areas using the R version 4.1.3 software and QGIS version 3.26 (Quantum Geographic Information System). Results: The spatial parametric frailty models were found to be good models for analyzing NFS data. Abnormal levels of activated thromboplastin carried a significantly higher risk of death in neonates across all PH models (Log-logistic, Hazard Ratio (HR), 95% Credible Interval (CI): 22.12, (5.40, 208.08); Log-normal: 20.87, (5.29, 123.23); Weibull: 18.49, (5.60, 93.41). The presence of hemorrhage also carried a risk of death for the Log-normal (1.65, (1.05, 2.75)) and Weibull models (1.75, (1.07, 3.12)). Villivakkam, Tiruvallur, and Poonamallee blocks were identified as high-risk areas. Conclusions: The spatial parametric frailty models proved their effectiveness in identifying these risk factors and quantifying their association with mortality. The findings from this study underline the importance of the early detection and management of risk factors to improve survival outcomes in neonates with fungal sepsis.
Open AccessAn Application for Spatial Frailty Models: An Exploration with Data on Fungal Sepsis in Neonates
Background: Globally, neonatal fungal sepsis (NFS) is a leading cause of neonatal mortality, particularly among vulnerable populations in neonatal intensive care units (NICU). The use of spatial frailty models with a Bayesian approach to identify hotspots and risk factors for neonatal deaths due to fungal sepsis has not been explored before. Methods: A cohort of 80 neonates admitted to the NICU at a Government Hospital in Tamil Nadu, India and diagnosed with fungal sepsis through blood cultures between 2018–2020 was considered for this study. Bayesian spatial frailty models using parametric distributions, such as Log-logistic, Log-normal, and Weibull proportional hazard (PH) models, were employed to identify associated risk factors for NFS deaths and hotspot areas using the R version 4.1.3 software and QGIS version 3.26 (Quantum Geographic Information System). Results: The spatial parametric frailty models were found to be good models for analyzing NFS data. Abnormal levels of activated thromboplastin carried a significantly higher risk of death in neonates across all PH models (Log-logistic, Hazard Ratio (HR), 95% Credible Interval (CI): 22.12, (5.40, 208.08); Log-normal: 20.87, (5.29, 123.23); Weibull: 18.49, (5.60, 93.41). The presence of hemorrhage also carried a risk of death for the Log-normal (1.65, (1.05, 2.75)) and Weibull models (1.75, (1.07, 3.12)). Villivakkam, Tiruvallur, and Poonamallee blocks were identified as high-risk areas. Conclusions: The spatial parametric frailty models proved their effectiveness in identifying these risk factors and quantifying their association with mortality. The findings from this study underline the importance of the early detection and management of risk factors to improve survival outcomes in neonates with fungal sepsis.
- Open Access
- 23 January 2025
- Published by MDPI AG in Preprints.org
An Application of Spatial Frailty Model: Exploration with Data of Fungal Sepsis in Neonates
Background: Globally, Neonatal fungal sepsis (NFS) is a leading cause of neonatal mortality, particularly among vulnerable populations in neonatal intensive care units (NICU). The use of spatial frailty models with a Bayesian approach to identify hotspots and risk factors for neonatal deaths due to fungal sepsis has not been explored before. Methods: A cohort of 80 neonates admitted to the NICU and diagnosed with fungal sepsis through blood culture at a Government Hospital in Tamil Nadu, India, during 2018-2020 was considered for this study. The Bayesian spatial frailty models using parametric distributions, including Log-logistic, Log-normal, and Weibull proportional hazard (PH) models were employed to identify associated risk factors for deaths of NFS and hotspot areas using R software. Results: The spatial parametric frailty models were found to be good models for ana-lysing NFS data. Abnormal levels of activated thromboplastin had a significantly higher risk of death across all PH models (Log-logistic, Hazard Ratio (HR), 95% Credible In-terval (CI): 22.12, (5.40,208.08); Log-normal: 20.87, (5.29,123.23); Weibull: 18.49, (5.60,93.41). Haemorrhage had a higher risk of death for the Log-normal (1.65, (1.05,2.75)) and Weibull models (1.75, (1.07,3.12)). Villivakkam, Tiruvallur, and Poo-namallee blocks were identified as high-risk areas. Conclusions: The spatial parametric frailty models proved effective in identifying these risk factors and quantifying their association with mortality. The findings from this study underline the importance of early detection and management of risk factors to improve survival outcomes in neonates with fungal sepsis.
- 23 January 2025
- Published by MDPI AG in Preprints.org
Open AccessAn Application of Spatial Frailty Model: Exploration with Data of Fungal Sepsis in Neonates
Background: Globally, Neonatal fungal sepsis (NFS) is a leading cause of neonatal mortality, particularly among vulnerable populations in neonatal intensive care units (NICU). The use of spatial frailty models with a Bayesian approach to identify hotspots and risk factors for neonatal deaths due to fungal sepsis has not been explored before. Methods: A cohort of 80 neonates admitted to the NICU and diagnosed with fungal sepsis through blood culture at a Government Hospital in Tamil Nadu, India, during 2018-2020 was considered for this study. The Bayesian spatial frailty models using parametric distributions, including Log-logistic, Log-normal, and Weibull proportional hazard (PH) models were employed to identify associated risk factors for deaths of NFS and hotspot areas using R software. Results: The spatial parametric frailty models were found to be good models for ana-lysing NFS data. Abnormal levels of activated thromboplastin had a significantly higher risk of death across all PH models (Log-logistic, Hazard Ratio (HR), 95% Credible In-terval (CI): 22.12, (5.40,208.08); Log-normal: 20.87, (5.29,123.23); Weibull: 18.49, (5.60,93.41). Haemorrhage had a higher risk of death for the Log-normal (1.65, (1.05,2.75)) and Weibull models (1.75, (1.07,3.12)). Villivakkam, Tiruvallur, and Poo-namallee blocks were identified as high-risk areas. Conclusions: The spatial parametric frailty models proved effective in identifying these risk factors and quantifying their association with mortality. The findings from this study underline the importance of early detection and management of risk factors to improve survival outcomes in neonates with fungal sepsis.
- 21 November 2024
- Published by Springer Nature in Metabolic Brain Disease
- Vol. 40 (1) , 1-18
Accelerated cognitive aging in chronically infected HIV-1 positive individuals despite effective long-term antiretroviral therapy
People living with HIV (PLHIV) are known to be at a higher risk of developing an array of aging-related diseases despite well-adhered combined antiretroviral therapy (cART). The present study aimed to investigate the impact of chronic HIV infection on neurocognitive function in virally suppressed PLHIV. We enrolled HIV-positive individuals randomly from an ART Center in Chennai, South India. A similar number of HIV-uninfected individuals matched for age and gender with the HIV-infected individuals served as controls. All individuals provided a detailed clinical history and underwent neuropsychological assessment using the International HIV Dementia Scale (IHDS). Plasma proteome analysis was performed using the Proximity extension assay (PEA) with the Olink® neuroexploratory panel, and untargeted metabolomics was performed using Ultra-High-Performance Liquid Chromatography/Mass Spectrometry/Mass Spectrometry. Despite a median duration of 9 years on first-line cART and suppressed viremia, a significant proportion of PLHIV registered significant levels of asymptomatic neurocognitive impairment, with 71% of these individuals scoring ≤ 10 in the IHDS test. We also observed significant alterations in a number of proteins and metabolites that are known to be associated with neuroinflammation, neurodegeneration, cognitive impairment, and gastrointestinal cancers, in the PLHIV group. Thus the study provides clinical as well as laboratory evidence to substantiate the presence of asymptomatic neurocognitive impairment in a large proportion of PLHIV, despite adequate cART and undetectable viremia, thereby supporting the view that HIV infection potentiates the risk for accelerated and accentuated neurological aging. This observation highlights the need to devise and implement appropriate intervention strategies for better long term management of HIV-infected persons.
- 21 November 2024
- Published by Springer Nature in Metabolic Brain Disease
- Vol. 40 (1) , 1-18
Accelerated cognitive aging in chronically infected HIV-1 positive individuals despite effective long-term antiretroviral therapy
People living with HIV (PLHIV) are known to be at a higher risk of developing an array of aging-related diseases despite well-adhered combined antiretroviral therapy (cART). The present study aimed to investigate the impact of chronic HIV infection on neurocognitive function in virally suppressed PLHIV. We enrolled HIV-positive individuals randomly from an ART Center in Chennai, South India. A similar number of HIV-uninfected individuals matched for age and gender with the HIV-infected individuals served as controls. All individuals provided a detailed clinical history and underwent neuropsychological assessment using the International HIV Dementia Scale (IHDS). Plasma proteome analysis was performed using the Proximity extension assay (PEA) with the Olink® neuroexploratory panel, and untargeted metabolomics was performed using Ultra-High-Performance Liquid Chromatography/Mass Spectrometry/Mass Spectrometry. Despite a median duration of 9 years on first-line cART and suppressed viremia, a significant proportion of PLHIV registered significant levels of asymptomatic neurocognitive impairment, with 71% of these individuals scoring ≤ 10 in the IHDS test. We also observed significant alterations in a number of proteins and metabolites that are known to be associated with neuroinflammation, neurodegeneration, cognitive impairment, and gastrointestinal cancers, in the PLHIV group. Thus the study provides clinical as well as laboratory evidence to substantiate the presence of asymptomatic neurocognitive impairment in a large proportion of PLHIV, despite adequate cART and undetectable viremia, thereby supporting the view that HIV infection potentiates the risk for accelerated and accentuated neurological aging. This observation highlights the need to devise and implement appropriate intervention strategies for better long term management of HIV-infected persons.
- Open Access
- 16 October 2024
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 19 (10) , e0309151
Machine learning algorithms to predict treatment success for patients with pulmonary tuberculosis
Despite advancements in detection and treatment, tuberculosis (TB), an infectious illness caused by the Mycobacterium TB bacteria, continues to pose a serious threat to world health. The TB diagnosis phase includes a patient’s medical history, physical examination, chest X-rays, and laboratory procedures, such as molecular testing and sputum culture. In artificial intelligence (AI), machine learning (ML) is an advanced study of statistical algorithms that can learn from historical data and generalize the results to unseen data. There are not many studies done on the ML algorithm that enables the prediction of treatment success for patients with pulmonary TB (PTB). The objective of this study is to identify an effective and predictive ML algorithm to evaluate the detection of treatment success in PTB patients and to compare the predictive performance of the ML models. In this retrospective study, a total of 1236 PTB patients who were given treatment under a randomized controlled clinical trial at the ICMR-National Institute for Research in Tuberculosis, Chennai, India were considered for data analysis. The multiple ML models were developed and tested to identify the best algorithm to predict the sputum culture conversion of TB patients during the treatment period. In this study, decision tree (DT), random forest (RF), support vector machine (SVM) and naïve bayes (NB) models were validated with high performance by achieving an area under the curve (AUC) of receiver operating characteristic (ROC) greater than 80%. The salient finding of the study is that the DT model was produced as a better algorithm with the highest accuracy (92.72%), an AUC (0.909), precision (95.90%), recall (95.60%) and F1-score (95.75%) among the ML models. This methodology may be used to study the precise ML model classification for predicting the treatment success of TB patients during the treatment period.
- 16 October 2024
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 19 (10) , e0309151
Open AccessMachine learning algorithms to predict treatment success for patients with pulmonary tuberculosis
Despite advancements in detection and treatment, tuberculosis (TB), an infectious illness caused by the Mycobacterium TB bacteria, continues to pose a serious threat to world health. The TB diagnosis phase includes a patient’s medical history, physical examination, chest X-rays, and laboratory procedures, such as molecular testing and sputum culture. In artificial intelligence (AI), machine learning (ML) is an advanced study of statistical algorithms that can learn from historical data and generalize the results to unseen data. There are not many studies done on the ML algorithm that enables the prediction of treatment success for patients with pulmonary TB (PTB). The objective of this study is to identify an effective and predictive ML algorithm to evaluate the detection of treatment success in PTB patients and to compare the predictive performance of the ML models. In this retrospective study, a total of 1236 PTB patients who were given treatment under a randomized controlled clinical trial at the ICMR-National Institute for Research in Tuberculosis, Chennai, India were considered for data analysis. The multiple ML models were developed and tested to identify the best algorithm to predict the sputum culture conversion of TB patients during the treatment period. In this study, decision tree (DT), random forest (RF), support vector machine (SVM) and naïve bayes (NB) models were validated with high performance by achieving an area under the curve (AUC) of receiver operating characteristic (ROC) greater than 80%. The salient finding of the study is that the DT model was produced as a better algorithm with the highest accuracy (92.72%), an AUC (0.909), precision (95.90%), recall (95.60%) and F1-score (95.75%) among the ML models. This methodology may be used to study the precise ML model classification for predicting the treatment success of TB patients during the treatment period.
- Open Access
- 7 October 2024
- Published by Sechenov University in The BRICS Health Journal
- Vol. 1 (1) , 35-58
Current challenges and future development of India’s healthcare system’ towards tuberculosis free India – research evidence and programmatic initiatives
Tuberculosis (TB), the single most infectious killer deserves special attention in a focussed manner, to reduce morbidity and mortality. We describe the challenges in the four pillars of TB control: detect or diagnosis, treat, prevent, build and elaborate the success stories, listing out newer and advanced tools like artificial intelligence, whole genome sequencing, clustered regularly interspaced short palindromic repeats based technologies, one health approach and cost effectiveness strategies for an all- round reduction in TB control. Special problems posed by paediatric and extra-pulmonary TB are dealt with. Post TB lung sequalae, reverse zoonosis and behavioural modification that can influence catastrophic costs are explored. Use of molecular and genomic methods of TB detection has revolutionized TB care with increased sensitivity of diagnosis, and timely detection of drug resistance, saving many a precious lives. Undoubtedly, the need of the hour would be shortening TB treatment duration and comprehensive preventive strategies that simultaneously decrease both the incidence and prevalence of TB. The various schemes and initiatives undertaken by the Government of India including the Pradhan Mantri TB Mukt Bharat Abhiyaan – “TB free India” stand as a unique solution in the wake of eliminating TB. India has been extending its success stories to other countries as well, by creating platforms for multilateral research and multinational implementation. This manuscript gives a concise and comprehensive outlook of process involved in TB elimination, amalgamating the research evidences with the programmatic initiatives, enlisting the existing challenges, envisaging the current achievements, providing a road map for TB elimination.
- 7 October 2024
- Published by Sechenov University in The BRICS Health Journal
- Vol. 1 (1) , 35-58
Open AccessCurrent challenges and future development of India’s healthcare system’ towards tuberculosis free India – research evidence and programmatic initiatives
Tuberculosis (TB), the single most infectious killer deserves special attention in a focussed manner, to reduce morbidity and mortality. We describe the challenges in the four pillars of TB control: detect or diagnosis, treat, prevent, build and elaborate the success stories, listing out newer and advanced tools like artificial intelligence, whole genome sequencing, clustered regularly interspaced short palindromic repeats based technologies, one health approach and cost effectiveness strategies for an all- round reduction in TB control. Special problems posed by paediatric and extra-pulmonary TB are dealt with. Post TB lung sequalae, reverse zoonosis and behavioural modification that can influence catastrophic costs are explored. Use of molecular and genomic methods of TB detection has revolutionized TB care with increased sensitivity of diagnosis, and timely detection of drug resistance, saving many a precious lives. Undoubtedly, the need of the hour would be shortening TB treatment duration and comprehensive preventive strategies that simultaneously decrease both the incidence and prevalence of TB. The various schemes and initiatives undertaken by the Government of India including the Pradhan Mantri TB Mukt Bharat Abhiyaan – “TB free India” stand as a unique solution in the wake of eliminating TB. India has been extending its success stories to other countries as well, by creating platforms for multilateral research and multinational implementation. This manuscript gives a concise and comprehensive outlook of process involved in TB elimination, amalgamating the research evidences with the programmatic initiatives, enlisting the existing challenges, envisaging the current achievements, providing a road map for TB elimination.
- 14 August 2024
- Published by Elsevier in Indian Journal of Medical Microbiology
- Vol. 51, 100701
Trends of drug resistance in M. tuberculosis in a reference laboratory in Central India: Forging ahead towards TB elimination
- 14 August 2024
- Published by Elsevier in Indian Journal of Medical Microbiology
- Vol. 51, 100701
Trends of drug resistance in M. tuberculosis in a reference laboratory in Central India: Forging ahead towards TB elimination