Clinicopathological Profile and Outcome of a Large Cohort of Patients with Nonalcoholic Fatty Liver Disease from South Asia: Interim Results of the Indian Consortium on Nonalcoholic Fatty Liver Disease

Duseja, Ajay; Singh, Shivaram Prasad; Mehta, Manu; Shalimar, S.; Venkataraman, Jayanthi; Mehta, Varun; Devadas, Krishnadas; Kar, Sanjib; Nagral, Aabha; Saigal, Sanjiv; Nijhawan, Sandeep; Praharaj, Dibyalochan; Shukla, Akash; Sharma, Brij; Narayanasamy, Krishnasamy; Kumar, Pramod; Rao, Padaki Nagaraja; Arora, Anil; Mehta, Rajiv; Asati, Pankaj; Ranjan, Piyush; Koshy, Abraham; Alam, Seema; Mukewar, Shrikant; Mukewar, Saurabh; Prasad, V G Mohan; Rastogi, Mukul; Sanyal, Arun J.

doi:10.1089/met.2021.0104

Cited by 20 publications

(11 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…NAFLD/MASLD confers a considerable burden (29.8%) across the globe 23 and in India (38.5%) 24 with 15%–45% of patients 25–27 being affected with significant or advanced fibrosis. Liver biopsy is the only gold standard for diagnosis and staging; however, it is impossible to recommend and perform it in all patients 18 .…”

Section: Discussionmentioning

confidence: 99%

Machine learning improves the prediction of significant fibrosis in Asian patients with metabolic dysfunction‐associated steatotic liver disease – The Gut and Obesity in Asia (GO‐ASIA) Study

Verma,

Duseja,

Mehta

et al. 2024

Aliment Pharmacol Ther

Self Cite

View full text Add to dashboard Cite

SummaryBackgroundThe precise estimation of cases with significant fibrosis (SF) is an unmet goal in non‐alcoholic fatty liver disease (NAFLD/MASLD).AimsWe evaluated the performance of machine learning (ML) and non‐patented scores for ruling out SF among NAFLD/MASLD patients.MethodsTwenty‐one ML models were trained (N = 1153), tested (N = 283), and validated (N = 220) on clinical and biochemical parameters of histologically‐proven NAFLD/MASLD patients (N = 1656) collected across 14 centres in 8 Asian countries. Their performance for detecting histological‐SF (≥F2fibrosis) were evaluated with APRI, FIB4, NFS, BARD, and SAFE (NPV/F1‐score as model‐selection criteria).ResultsPatients aged 47 years (median), 54.6% males, 73.7% with metabolic syndrome, and 32.9% with histological‐SF were included in the study. Patients with SFvs.no‐SF had higher age, aminotransferases, fasting plasma glucose, metabolic syndrome, uncontrolled diabetes, and NAFLD activity score (p < 0.001, each). ML models showed 7%–12% better discrimination than FIB‐4 to detect SF. Optimised random forest (RF) yielded best NPV/F1 in overall set (0.947/0.754), test set (0.798/0.588) and validation set (0.852/0.559), as compared to FIB4 in overall set (0.744/0.499), test set (0.722/0.456), and validation set (0.806/0.507). Compared to FIB‐4, RF could pick 10 times more patients with SF, reduce unnecessary referrals by 28%, and prevent missed referrals by 78%. Age, AST, ALT fasting plasma glucose, and platelet count were top features determining the SF. Sequential use of SAFE < 140 and FIB4 < 1.2 (when SAFE > 140) was next best in ruling out SF (NPV of 0.757, 0.724 and 0.827 in overall, test and validation set).ConclusionsML with clinical, anthropometric data and simple blood investigations perform better than FIB‐4 for ruling out SF in biopsy‐proven Asian NAFLD/MASLD patients.

show abstract

Section: Discussionmentioning

confidence: 99%

Machine learning improves the prediction of significant fibrosis in Asian patients with metabolic dysfunction‐associated steatotic liver disease – The Gut and Obesity in Asia (GO‐ASIA) Study

Verma,

Duseja,

Mehta

et al. 2024

Aliment Pharmacol Ther

Self Cite

View full text Add to dashboard Cite

show abstract

“…A population screening study from Hong Kong showed that 3.7% of patients with NAFLD had an LSM ≥ 9.6 kPa suggestive of advanced fibrosis 87. A higher percentage was reported in a multicenter study from India that around 30% and 10% of patients with NAFLD had LSM ≥ 8 and ≥13 kPa, respectively 92…”

Section: Burden Of Nafld In Asiamentioning

confidence: 99%

“…[87] A higher percentage was reported in a multicenter study from India that around 30% and 10% of patients with NAFLD had LSM ≥ 8 and ≥ 13 kPa, respectively. [92] Disease severity assessed by liver biopsy…”

Section: Disease Severity Assessed By Noninvasive Testsmentioning

confidence: 99%

Geographical similarity and differences in the burden and genetic predisposition of NAFLD

et al. 2022

View full text Add to dashboard Cite

NAFLD has become a major public health problem for more than 2 decades with a growing prevalence in parallel with the epidemic of obesity and type 2 diabetes (T2D). The disease burden of NAFLD differs across geographical regions and ethnicities. Variations in prevalence of metabolic diseases, extent of urban–rural divide, dietary habits, lifestyles, and the prevalence of NAFLD risk and protective alleles can contribute to such differences. The rise in NAFLD has led to a remarkable increase in the number of cases of cirrhosis, hepatocellular carcinoma, hepatic decompensation, and liver‐related mortality related to NAFLD. Moreover, NAFLD is associated with multiple extrahepatic manifestations. Most of them are risk factors for the progression of liver fibrosis and thus worsen the prognosis of NAFLD. All these comorbidities and complications affect the quality of life in subjects with NAFLD. Given the huge and growing size of the population with NAFLD, it is expected that patients, healthcare systems, and the economy will suffer from the ongoing burden related to NAFLD. In this review, we examine the disease burden of NAFLD across geographical areas and ethnicities, together with the distribution of some well‐known genetic variants for NAFLD. We also describe some special populations including patients with T2D, lean patients, the pediatric population, and patients with concomitant liver diseases. We discuss extrahepatic outcomes, patient‐reported outcomes, and economic burden related to NAFLD.

show abstract

“…At least in India, our real-life data on NAFLD suggested reluctance for liver biopsy both among patients and physicians. 7 In conclusion, the editorial underlines legitimate concerns of generalizability, yet it is essential to consider it as a 'health artefact' that needs nuanced interpretation and understand the constraints under which these ML models are developed and the strides taken to alleviate these challenges. As we navigate the evolving landscape of AI in healthcare, it is incumbent upon us to ensure that these innovations enhance, not undermine, the equity and integrity of patient care.…”

Section: The Disparity In Patient Representation From Indonesia Andmentioning

confidence: 99%

Editorial: Using machine learning to predict significant fibrosis in metabolic dysfunction‐associated steatotic liver disease—authors' reply

Verma,

De,

Duseja

2024

Aliment Pharmacol Ther

Self Cite

View full text Add to dashboard Cite

show abstract

Clinicopathological Profile and Outcome of a Large Cohort of Patients with Nonalcoholic Fatty Liver Disease from South Asia: Interim Results of the Indian Consortium on Nonalcoholic Fatty Liver Disease

Cited by 20 publications

References 39 publications

Machine learning improves the prediction of significant fibrosis in Asian patients with metabolic dysfunction‐associated steatotic liver disease – The Gut and Obesity in Asia (GO‐ASIA) Study

Machine learning improves the prediction of significant fibrosis in Asian patients with metabolic dysfunction‐associated steatotic liver disease – The Gut and Obesity in Asia (GO‐ASIA) Study

Geographical similarity and differences in the burden and genetic predisposition of NAFLD

Editorial: Using machine learning to predict significant fibrosis in metabolic dysfunction‐associated steatotic liver disease—authors' reply

Contact Info

Product

Resources

About