Krishma Adatia

Krishma Adatia

Auto-generated profile, based on publicly available information

Krishma Adatia

University of Cambridge and Cambridge University Hospitals NHS Foundation Trust Cambridge UK

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 June 2020 in The Lancet Digital Health
Verified
Journal Article
Open access
MMMiguel Pessoa Monteiro
Miguel Pessoa Monteiro
VNVirginia F J Newcombe
Virginia F J Newcombe
FMFrancois Mathieu
Francois Mathieu
KAKrishma Adatia
Krishma Adatia
KKKonstantinos Kamnitsas
Konstantinos Kamnitsas
BGBen Glocker
Ben Glocker
CT is the most common imaging modality in traumatic brain injury (TBI). However, its conventional use requires expert clinical interpretation and does not provide detailed quantitative outputs, which may have prognostic importance. We aimed to use deep learning to reliably and efficiently quantify and detect different lesion types. Patients were recruited between Dec 9, 2014, and Dec 17, 2017, in 60 centres across Europe. We trained and validated an initial convolutional neural network (CNN) on expert manual segmentations (dataset 1). This CNN was used to automatically segment a new dataset of scans, which we then corrected manually (dataset 2). From this dataset, we used a subset of scans to train a final CNN for multiclass, voxel-wise segmentation of lesion types. The performance of this CNN was evaluated on a test subset. Performance was measured for lesion volume quantification, lesion progression, and lesion detection and lesion volume classification. For lesion detection, external validation was done on an independent set of 500 patients from India. 98 scans from one centre were included in dataset 1. Dataset 2 comprised 839 scans from 38 centres: 184 scans were used in the training subset and 655 in the test subset. Compared with manual reference, CNN-derived lesion volumes showed a mean difference of 0·86 mL (95% CI -5·23 to 6·94) for intraparenchymal haemorrhage, 1·83 mL (-12·01 to 15·66) for extra-axial haemorrhage, 2·09 mL (-9·38 to 13·56) for perilesional oedema, and 0·07 mL (-1·00 to 1·13) for intraventricular haemorrhage. We show the ability of a CNN to separately segment, quantify, and detect multiclass haemorrhagic lesions and perilesional oedema. These volumetric lesion estimates allow clinically relevant quantification of lesion burden and progression, with potential applications for personalised treatment strategies and clinical research in TBI. European Union 7th Framework Programme, Hannelore Kohl Stiftung, OneMind, NeuroTrauma Sciences, Integra Neurosciences, European Research Council Horizon 2020.

27 May 2020 in Neurocritical Care
Verified
Journal Article
Open access
PDF file
KAKrishma Adatia
Krishma Adatia
VNVirginia F. J. Newcombe
Virginia F. J. Newcombe
DMDavid K. Menon
David K. Menon
Secondary injuries remain an important cause of the morbidity and mortality associated with traumatic brain injury (TBI). Progression of cerebral contusions occurs in up to 75% of patients with TBI, and this contributes to subsequent clinical deterioration and requirement for surgical intervention. Despite this, the role of early clinical and radiological factors in predicting contusion progression remains relatively poorly defined due to studies investigating progression of all types of hemorrhagic injuries as a combined cohort. In this review, we summarize data from recent studies on factors which predict contusion progression, and the effect of contusion progression on clinical outcomes.

7 November 2017 in ACS Chemical Neuroscience
Verified
Journal Article
Closed access
AVArun Venkatesan
Arun Venkatesan
KAKrishma Adatia
Krishma Adatia

1 April 2021 in American Heart Journal
Verified
Journal Article
Closed access
YGYing Gue
Ying Gue
KAKrishma Adatia
Krishma Adatia
RKRahim Kanji
Rahim Kanji
TPTatjana Potpara
Tatjana Potpara
GLGregory Y.H. Lip
Gregory Y.H. Lip
DGDiana Gorog
Diana Gorog

1 November 2020 in The American Journal of Medicine
Verified
Journal Article
Closed access
YGYing Gue
Ying Gue
MSMax Sayers
Max Sayers
BWBenjamin T. Whitby
Benjamin T. Whitby
RKRahim Kanji
Rahim Kanji
KAKrishma Adatia
Krishma Adatia
DGDiana Gorog
Diana Gorog

22 August 2019 in Thrombosis and Haemostasis
Verified
Journal Article
Closed access
PDF file
KAKrishma Adatia
Krishma Adatia
MFMohamed F. Farag
Mohamed F. Farag
YGYing X. Gue
Ying X. Gue
MSManivannan Srinivasan
Manivannan Srinivasan
DGDiana Gorog
Diana Gorog
Background Patients with ST-elevation myocardial infarction (STEMI) exhibit pro-thrombotic and pro-inflammatory states. Markers of enhanced platelet reactivity and inflammation are predictive of adverse outcome. However, the relationship between these biomarkers, and their combined usefulness for risk stratification, is not clear. Methods In a prospective study of 541 patients presenting with STEMI, blood samples were taken on arrival to measure high-sensitivity C-reactive protein (hs-CRP), neutrophil/lymphocyte ratio (NLR) and platelet reactivity using the point-of-care Global Thrombosis Test. These biomarkers, alone and in combination, were related to the occurrence of major adverse cardiovascular events (MACE, defined as composite of cardiovascular death, myocardial infarction and cerebrovascular accident) at 30 days and 12 months. Results Platelet reactivity and hs-CRP, but not NLR, were weakly predictive of MACE at 30 days and 12 months. The combination of enhanced platelet reactivity and raised hs-CRP was strongly predictive of MACE at 30 days (hazard ratio [HR] 3.46 [95% confidence interval [CI] 1.81–6.62], p < 0.001) and 12 months (HR 3.46 [95% CI 1.81–6.63], p < 0.001). Combination of all three biomarkers (NLR, hs-CRP and platelet reactivity) provided the best prediction of MACE at 30 days (HR 3.73 [95% CI 1.69–8.27], p < 0.001) and 12 months (HR 3.85 [95% CI 1.72–8.60], p < 0.001), and improved the prediction of MACE when added to Thrombolysis In Myocardial Infarction score (net reclassification index 0.296, p < 0.001). Conclusion A combination of three easy to measure biomarkers on arrival, namely hs-CRP, NLR and platelet reactivity, can help identify STEMI patients at high risk of recurrent adverse events over the subsequent year. * These authors contributed equally to the manuscript.