SNScarlet Nazarian

Scarlet Nazarian

*This is an algorithmically generated author record based on publicly available information.

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


Scarlet Nazarian has a total of 45 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Real-time classification of tumour and non-tumour tissue in colorectal cancer using diffuse reflectance spectroscopy and neural networks to aid margin assessment

    by Scarlet Mbbs Nazarian, Ioannis Gkouzionis, Jamie Murphy, Ara Darzi, Nisha Patel, Christopher J. Peters, Daniel S. Elson

    Background: Colorectal cancer is the third most commonly diagnosed malignancy and the second leading cause of mortality worldwide. A positive resection margin following surgery for colorectal cancer is linked with higher rates of local recurrence and poorer survival. We investigated diffuse reflectance spectroscopy (DRS) to distinguish tumour and non-tumour tissue in ex vivo colorectal specimens, to aid margin assessment and provide augmented visual maps to the surgeon in real-time. Methods: Patients undergoing elective colorectal cancer resection surgery at a London-based hospital were prospectively recruited. A hand-held DRS probe was used on the surface of freshly resected ex vivo colorectal tissue. Spectral data was acquired for tumour and non-tumour tissue. Binary classification was achieved using conventional machine learning classifiers and a convolutional neural network (CNN), which were evaluated in terms of sensitivity, specificity, accuracy and the area under the curve. Results: A total of 7692 mean spectra were obtained for tumour and non-tumour colorectal tissue. The CNN-based classifier was the best performing machine learning algorithm, when compared to contrastive approaches, for differentiating tumour and non-tumour colorectal tissue, with an overall diagnostic accuracy of 90.8% and area under the curve of 96.8%. Live on-screen classification of tissue type was achieved using a graduated colourmap. Conclusion: A high diagnostic accuracy for a DRS probe and tracking system to differentiate ex vivo tumour and non-tumour colorectal tissue in real-time with on-screen visual feedback was highlighted by this study. Further in vivo studies are needed to ensure integration into a surgical workflow.


  • Open Access

    Development and validation of machine learning models to predict the need for haemostatic therapy in acute upper gastrointestinal bleeding

    by Scarlet Nazarian, Frank Po Wen Lo, Jianing Qiu, Nisha Patel, Benny Lo, Lakshmana Ayaru

    Background: Acute upper gastrointestinal bleeding (AUGIB) is a major cause of morbidity and mortality. This presentation however is not universally high risk as only 20–30% of bleeds require urgent haemostatic therapy. Nevertheless, the current standard of care is for all patients admitted to an inpatient bed to undergo endoscopy within 24 h for risk stratification which is invasive, costly and difficult to achieve in routine clinical practice. Objectives: To develop novel non-endoscopic machine learning models for AUGIB to predict the need for haemostatic therapy by endoscopic, radiological or surgical intervention. Design: A retrospective cohort study Method: We analysed data from patients admitted with AUGIB to hospitals from 2015 to 2020 ( n = 970). Machine learning models were internally validated to predict the need for haemostatic therapy. The performance of the models was compared to the Glasgow-Blatchford score (GBS) using the area under receiver operating characteristic (AUROC) curves. Results: The random forest classifier [AUROC 0.84 (0.80–0.87)] had the best performance and was superior to the GBS [AUROC 0.75 (0.72–0.78), p < 0.001] in predicting the need for haemostatic therapy in patients with AUGIB. A GBS cut-off of ⩾12 was associated with an accuracy, sensitivity, specificity, positive predictive value (PPV) and negative predictive value (NPV) of 0.74, 0.49, 0.81, 0.41 and 0.85, respectively. The Random Forrest model performed better with an accuracy, sensitivity, specificity, PPV and NPV of 0.82, 0.54, 0.90, 0.60 and 0.88, respectively. Conclusion: We developed and validated a machine learning algorithm with high accuracy and specificity in predicting the need for haemostatic therapy in AUGIB. This could be used to risk stratify high-risk patients to urgent endoscopy.


  • Open Access

    Clinical Validation Benchmark Dataset and Expert Performance Baseline for Colorectal Polyp Localization Methods

    by Luisa F. Sánchez-Peralta, Ben Glover, Cristina L. Saratxaga, Juan Francisco Ortega-Morán, Scarlet Nazarian, Artzai Picón, J. Blas Pagador, Francisco M. Sánchez-Margallo

    Colorectal cancer is one of the leading death causes worldwide, but, fortunately, early detection highly increases survival rates, with the adenoma detection rate being one surrogate marker for colonoscopy quality. Artificial intelligence and deep learning methods have been applied with great success to improve polyp detection and localization and, therefore, the adenoma detection rate. In this regard, a comparison with clinical experts is required to prove the added value of the systems. Nevertheless, there is no standardized comparison in a laboratory setting before their clinical validation. The ClinExpPICCOLO comprises 65 unedited endoscopic images that represent the clinical setting. They include white light imaging and narrow band imaging, with one third of the images containing a lesion but, differently to another public datasets, the lesion does not appear well-centered in the image. Together with the dataset, an expert clinical performance baseline has been established with the performance of 146 gastroenterologists, who were required to locate the lesions in the selected images. Results shows statistically significant differences between experience groups. Expert gastroenterologists’ accuracy was 77.74, while sensitivity and specificity were 86.47 and 74.33, respectively. These values can be established as minimum values for a DL method before performing a clinical trial in the hospital setting.


  • Using Diffuse Reflectance Spectroscopy to Classify Tumor Tissue in Upper Gastrointestinal Cancers—Reply

    by Scarlet Nazarian, Ioannis Gkouzionis, Christopher J. Peters

    In Reply We would like to thank Liu and Yang for their interest in our article1 and for taking the time to express their points for discussion. We appreciate the opportunity to respond. Liu and Yang inquire as to whether the specimens in patients who had undergone neoadjuvant treatment were significantly different in their optical properties to those who had not. At this stage, we have not yet explored the wavelength characteristics when using diffuse reflectance spectroscopy (DRS) on treatment-naive specimens vs those having undergone neoadjuvant treatment. The use of neoadjuvant therapy leads to the formation of scar tissue over healthy areas surrounding the tumor,2,3 and therefore further evaluation of these patients in future studies will aid in classifying fibrosed tissue and improve the accuracy of margin assessment.

  • Open Access

    The future of endoscopy – what are the thoughts on artificial intelligence?

    by S. Nazarian, H.F Koo, E. Carrington, A. Darzi, N. Patel

    There is an emerging role of artificial intelligence (AI) in endoscopy with studies on early systems showing promising results. However, various limitations inhibit widespread use. The aim of this study was to ascertain the sentiments of endoscopists and understand the benefits and barriers towards adoption of AI systems into healthcare. An anonymous online 18-question survey was disseminated to gastroenterology and surgical departments across UK. A total of 75 endoscopists completed the questionnaire. The majority felt that AI would increase adenoma detection rate (ADR) (72.8%) and aid lesion characterisation (78.6%). However, only a quarter of respondents were either moderately or very familiar with AI, and there was no consensus on necessity of AI in endoscopy. The key barriers identified were cost, accessibility and lack of guidelines. Endoscopists believe AI systems will have a positive impact on endoscopy; however, these systems must provide quality assurance through large clinical trials before adoption.


  • Open Access

    Real-time Tracking and Classification of Tumor and Nontumor Tissue in Upper Gastrointestinal Cancers Using Diffuse Reflectance Spectroscopy for Resection Margin Assessment

    by Scarlet Nazarian, Ioannis Gkouzionis, Michal Kawka, Marta Jamroziak, Josephine Lloyd, Ara Darzi, Nisha Patel, Daniel S. Elson, Christopher J. Peters

    Esophageal and gastric cancers are associated with poor prognosis, with 5-year overall survival of patients estimated to be between 15% and 25%.1,2 This is despite an improvement in survival over the last half century, owing to advances in modern neoadjuvant therapies and the implementation of new surgical approaches.3-10


  • Open Access

    Does computer-aided diagnostic endoscopy improve the detection of commonly missed polyps? A meta-analysis

    by Arun Sivananthan, Scarlet Nazarian, Lakshmana Ayaru, Kinesh Patel, Hutan Ashrafian, Ara Darzi, Nisha Patel

    Background/Aims: Colonoscopy is the gold standard diagnostic method for colorectal neoplasia, allowing detection and resection of adenomatous polyps; however, significant proportions of adenomas are missed. Computer-aided detection (CADe) systems in endoscopy are currently available to help identify lesions. Diminutive (≤5 mm) and nonpedunculated polyps are most commonly missed. This meta-analysis aimed to assess whether CADe systems can improve the real-time detection of these commonly missed lesions.Methods: A comprehensive literature search was performed. Randomized controlled trials evaluating CADe systems categorized by morphology and lesion size were included. The mean number of polyps and adenomas per patient was derived. Independent proportions and their differences were calculated using DerSimonian and Laird random-effects modeling.Results: Seven studies, including 2,595 CADe-assisted colonoscopies and 2,622 conventional colonoscopies, were analyzed. CADe-assisted colonoscopy demonstrated an 80% increase in the mean number of diminutive adenomas detected per patient compared with conventional colonoscopy (0.31 vs. 0.17; effect size, 0.13; 95% confidence interval [CI], 0.09–0.18); it also demonstrated a 91.7% increase in the mean number of nonpedunculated adenomas detected per patient (0.32 vs. 0.19; effect size, 0.05; 95% CI, 0.02–0.07).Conclusions: CADe-assisted endoscopy significantly improved the detection of most commonly missed adenomas. Although this method is a potentially exciting technology, limitations still apply to current data, prompting the need for further real-time studies.


  • Open Access

    Patient perspectives on surgeon-specific outcome reports in bariatric surgery

    by Kyle Lam, Scarlet Nazarian, Nishita Gadi, Sherif Hakky, Krishna Moorthy, Christos Tsironis, Ahmed Ahmed, James M. Kinross, Sanjay Purkayastha


  • Open Access

    Real-time tracking of a diffuse reflectance spectroscopy probe used to aid histological validation of margin assessment in upper gastrointestinal cancer resection surgery

    by Ioannis Gkouzionis, Scarlet Nazarian, Michal Kawka, Ara W. Darzi, Nisha Patel, Christopher J. Peters, Daniel S. Elson

    Cancers of the gastrointestinal (GI) tract remain a major contributor to the global cancer risk, with ∼4.8 million new cases of GI cancer worldwide in 2018.1 These malignancies continue to pose a major threat to public health. The aim of surgery is for complete resection of tumor with clear margins, while preserving as much surrounding healthy tissue as possible.2 A positive circumferential resection margin (CRM) is associated with local recurrence of the tumor and poorer long-term survival.3,4 The five-year survival of patients with esophageal cancer with positive margins has been reported as 13.8% compared to 46.3% for those with negative margins.5 In patients with stomach cancer, local recurrence has been shown to be 16% after a positive margin following surgery.6 For this reason, it is paramount to establish tissue margins accurately.7


  • Open Access

    Diagnostic Accuracy of Smartwatches for the Detection of Cardiac Arrhythmia: Systematic Review and Meta-analysis

    by Scarlet Nazarian, Kyle Lam, Ara Darzi, Hutan Ashrafian

    Background: Significant morbidity, mortality, and financial burden are associated with cardiac rhythm abnormalities. Conventional investigative tools are often unsuccessful in detecting cardiac arrhythmias because of their episodic nature. Smartwatches have gained popularity in recent years as a health tool for the detection of cardiac rhythms. Objective: This study aims to systematically review and meta-analyze the diagnostic accuracy of smartwatches in the detection of cardiac arrhythmias. Methods: A systematic literature search of the Embase, MEDLINE, and Cochrane Library databases was performed in accordance with the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines to identify studies reporting the use of a smartwatch for the detection of cardiac arrhythmia. Summary estimates of sensitivity, specificity, and area under the curve were attempted using a bivariate model for the diagnostic meta-analysis. Studies were examined for quality using the Quality Assessment of Diagnostic Accuracy Studies 2 tool. Results: A total of 18 studies examining atrial fibrillation detection, bradyarrhythmias and tachyarrhythmias, and premature contractions were analyzed, measuring diagnostic accuracy in 424,371 subjects in total. The signals analyzed by smartwatches were based on photoplethysmography. The overall sensitivity, specificity, and accuracy of smartwatches for detecting cardiac arrhythmias were 100% (95% CI 0.99-1.00), 95% (95% CI 0.93-0.97), and 97% (95% CI 0.96-0.99), respectively. The pooled positive predictive value and negative predictive value for detecting cardiac arrhythmias were 85% (95% CI 0.79-0.90) and 100% (95% CI 1.0-1.0), respectively. Conclusions: This review demonstrates the evolving field of digital disease detection. The current diagnostic accuracy of smartwatch technology for the detection of cardiac arrhythmias is high. Although the innovative drive of digital devices in health care will continue to gain momentum toward screening, the process of accurate evidence accrual and regulatory standards ready to accept their introduction is strongly needed. Trial Registration: PROSPERO International Prospective Register of Systematic Reviews CRD42020213237; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=213237.