Dataset Information

A smart tele-cytology point-of-care platform for oral cancer screening.

ABSTRACT: Early detection of oral cancer necessitates a minimally invasive, tissue-specific diagnostic tool that facilitates screening/surveillance. Brush biopsy, though minimally invasive, demands skilled cyto-pathologist expertise. In this study, we explored the clinical utility/efficacy of a tele-cytology system in combination with Artificial Neural Network (ANN) based risk-stratification model for early detection of oral potentially malignant (OPML)/malignant lesion. A portable, automated tablet-based tele-cytology platform capable of digitization of cytology slides was evaluated for its efficacy in the detection of OPML/malignant lesions (n = 82) in comparison with conventional cytology and histology. Then, an image pre-processing algorithm was established to segregate cells, ANN was trained with images (n = 11,981) and a risk-stratification model developed. The specificity, sensitivity and accuracy of platform/ stratification model were computed, and agreement was examined using Kappa statistics. The tele-cytology platform, Cellscope, showed an overall accuracy of 84-86% with no difference between tele-cytology and conventional cytology in detection of oral lesions (kappa, 0.67-0.72). However, OPML could be detected with low sensitivity (18%) in accordance with the limitations of conventional cytology. The integration of image processing and development of an ANN-based risk stratification model improved the detection sensitivity of malignant lesions (93%) and high grade OPML (73%), thereby increasing the overall accuracy by 30%. Tele-cytology integrated with the risk stratification model, a novel strategy established in this study, can be an invaluable Point-of-Care (PoC) tool for early detection/screening in oral cancer. This study hence establishes the applicability of tele-cytology for accurate, remote diagnosis and use of automated ANN-based analysis in improving its efficacy.

SUBMITTER: Sunny S

PROVIDER: S-EPMC6857853 | biostudies-literature | 2019

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

A smart tele-cytology point-of-care platform for oral cancer screening.

Sunny Sumsum S Baby Arun A James Bonney Lee BL Balaji Dev D N V Aparna A Rana Maitreya H MH Gurpur Praveen P Skandarajah Arunan A D'Ambrosio Michael M Ramanjinappa Ravindra Doddathimmasandra RD Mohan Sunil Paramel SP Raghavan Nisheena N Kandasarma Uma U N Sangeetha S Raghavan Subhasini S Hedne Naveen N Koch Felix F Fletcher Daniel A DA Selvam Sumithra S Kollegal Manohar M N Praveen Birur PB Ladic Lance L Suresh Amritha A Pandya Hardik J HJ Kuriakose Moni Abraham MA

PloS one 20191115 11

Early detection of oral cancer necessitates a minimally invasive, tissue-specific diagnostic tool that facilitates screening/surveillance. Brush biopsy, though minimally invasive, demands skilled cyto-pathologist expertise. In this study, we explored the clinical utility/efficacy of a tele-cytology system in combination with Artificial Neural Network (ANN) based risk-stratification model for early detection of oral potentially malignant (OPML)/malignant lesion. A portable, automated tablet-based ...[more]

PMID: 31730638

Similar Datasets

Project description:Recently, illicit drug use has become more widespread and is linked to problems with crime and public health. These drugs disrupt consciousness, affecting perceptions and feelings. Combining stimulants and depressants to suppress the effect of drugs has become the most common reason for drug overdose deaths. On-site platforms for illicit-drug detection have gained an important role in dealing, without any excess equipment, long process, and training, with drug abuse and drug trafficking. Consequently, the development of rapid, sensitive, noninvasive, and reliable multiplex drug-detecting platforms has become a major necessity. In this study, a multiplex laser-scribed graphene (LSG) sensing platform with one counter, one reference, and three working electrodes was developed for rapid and sensitive electrochemical detection of amphetamine (AMP), cocaine (COC), and benzodiazepine (BZD) simultaneously in saliva samples. The multidetection sensing system was combined with a custom-made potentiostat to achieve a complete point-of-care (POC) platform. Smartphone integration was achieved by a customized application to operate, display, and send data. To the best of our knowledge, this is the first multiplex LSG-based electrochemical platform designed for illicit-drug detection with a custom-made potentiostat device to build a complete POC platform. Each working electrode was optimized with standard solutions of AMP, COC, and BZD in the concentration range of 1.0 pg/mL-500 ng/mL. The detection limit of each illicit drug was calculated as 4.3 ng/mL for AMP, 9.7 ng/mL for BZD, and 9.0 ng/mL for COC. Healthy and MET (methamphetamine) patient saliva samples were used for the clinical study. The multiplex LSG sensor was able to detect target analytes in real saliva samples successfully. This multiplex detection device serves the role of a practical and affordable alternative to conventional drug-detection methods by combining multiple drug detections in one portable platform.

Project description:ImportanceCervical cancer is highly preventable but remains a common and deadly cancer in areas without screening programs. The creation of a diagnostic system to digitize Papanicolaou test samples and analyze them using a cloud-based deep learning system (DLS) may provide needed cervical cancer screening to resource-limited areas.ObjectiveTo determine whether artificial intelligence-supported digital microscopy diagnostics can be implemented in a resource-limited setting and used for analysis of Papanicolaou tests.Design, setting, and participantsIn this diagnostic study, cervical smears from 740 HIV-positive women aged between 18 and 64 years were collected between September 1, 2018, and September 30, 2019. The smears were digitized with a portable slide scanner, uploaded to a cloud server using mobile networks, and used to train and validate a DLS for the detection of atypical cervical cells. This single-center study was conducted at a local health care center in rural Kenya.ExposuresDetection of squamous cell atypia in the digital samples by analysis with the DLS.Main outcomes and measuresThe accuracy of the DLS in the detection of low- and high-grade squamous intraepithelial lesions in Papanicolaou test whole-slide images.ResultsPapanicolaou test results from 740 HIV-positive women (mean [SD] age, 41.8 [10.3] years) were collected. The DLS was trained using 350 whole-slide images and validated on 361 whole-slide images (average size, 100 387 × 47 560 pixels). For detection of cervical cellular atypia, sensitivities were 95.7% (95% CI, 85.5%-99.5%) and 100% (95% CI, 82.4%-100%), and specificities were 84.7% (95% CI, 80.2%-88.5%) and 78.4% (95% CI, 73.6%-82.4%), compared with the pathologist assessment of digital and physical slides, respectively. Areas under the receiver operating characteristic curve were 0.94 and 0.96, respectively. Negative predictive values were high (99%-100%), and accuracy was high, particularly for the detection of high-grade lesions. Interrater agreement was substantial compared with the pathologist assessment of digital slides (κ = 0.72) and fair compared with the assessment of glass slides (κ = 0.36). No samples that were classified as high grade by manual sample analysis had false-negative assessments by the DLS.Conclusions and relevanceIn this study, digital microscopy with artificial intelligence was implemented at a rural clinic and used to detect atypical cervical smears with a high sensitivity compared with visual sample analysis.

Project description:BackgroundSepsis is a clinical syndrome characterized by organ dysfunction due to presumed or proven infection. Severe cases can have case fatality ratio 25% or higher in low-middle income countries, but early diagnosis and timely treatment have a proven benefit. The Smart Triage program in Jinja Regional Referral Hospital in Uganda will provide expedited sepsis treatment in children through a data-driven electronic patient triage system. To complement the ongoing Smart Triage interventional trial, we propose methods for a concurrent cost-effectiveness analysis of the Smart Triage platform.MethodsWe will use a decision-analytic model taking a societal perspective, combining government and out-of-pocket costs, as patients bear a sizeable portion of healthcare costs in Uganda due to the lack of universal health coverage. Previously published secondary data will be used to link healthcare utilization with costs and intermediate outcomes with mortality. We will model uncertainty via probabilistic sensitivity analysis and present findings at various willingness-to-pay thresholds using a cost-effectiveness acceptability curve.DiscussionOur proposed analysis represents a first step in evaluating the cost-effectiveness of an innovative digital triage platform designed to improve clinical outcomes in pediatric sepsis through expediting care in low-resource settings. Our use of a decision analytic model to link secondary costing data, incorporate post-discharge healthcare utilization, and model clinical endpoints is also novel in the pediatric sepsis triage literature for low-middle income countries. Our analysis, together with subsequent analyses modelling budget impact and scale up, will inform future modifications to the Smart Triage platform, as well as motivate scale-up to the district and national levels.Trial registrationTrial registration of parent clinical trial: NCT04304235, https://clinicaltrials.gov/ct2/show/NCT04304235. Registered 11 March 2020.

Project description:BackgroundAs outpatient chemotherapy treatment increases, cancer patients receiving chemotherapy spend more time at home. In addition, since the types of chemotherapy are gradually expanding, it will be essential to prepare patient self-management strategies for various chemotherapy-related side effects. This study aimed to develop a platform (called Smart Cancer Care) to implement a chemotherapy side effect management program and to evaluate its feasibility.MethodsSmart Cancer Care comprises an application for patients and a dashboard for medical staff. Thirty-two symptoms to be managed using Smart Cancer Care were summarized through a literature review and Delphi. Management guidelines were developed based on the severity of each symptom (3 stages), and installed in Smart Cancer Care according to the Common Terminology Criteria for Adverse Events (CTCAE) v5.0 guidelines. To evaluate the feasibility of the developed application and medical dashboard, cancer patients and cancer treatment medical staff used Smart Cancer Care for 2 to 3 weeks and subsequently reported the experience of using them.ResultsThe patient application provided a list of symptoms according to the cancer type and anticancer drug enabling presence and severity of each symptom to be evaluated. Patients received management guidelines for symptoms based on the symptom evaluation results. On the medical staff dashboard, administrators and authorized medical personnel could access and assess information regarding side effects and symptom severity submitted by the patient. The feasibility and usefulness of Smart Cancer Care were confirmed through a pilot test targeting 30 patients and 24 chemotherapy-related medical staff. For patients, the evaluation score for the "The program will be helpful when seeing medical staff" item was the highest. For medical staff, the score for the "By checking the patient's symptoms using the program, it helps to take appropriate measures for the patient" item was the highest. Although minor corrections were raised, most patients and medical staff expected that Smart Cancer Care would help their treatment.ConclusionsThe configuration of the application and dashboard of Smart Cancer Care detailed in this study could be used for the development of a widely accepted platform to implement a chemotherapy side effect management program.

Dataset Information

A smart tele-cytology point-of-care platform for oral cancer screening.

Publications

A smart tele-cytology point-of-care platform for oral cancer screening.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets