Objective To evaluate the existing evidence of a machine learning-based classification system that stratifies patients with stroke. Methods The authors carried out a systematic review following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) recommendations for a review article. PubMed, MEDLINE, Web of Science, and CINAHL Plus Full Text were searched from January 2015 to February 2021. Results There are twelve studies included in this systematic review. Fifteen algorithms were used in the included studies. The most common forms of machine learning (ML) used to classify stroke patients were the support vector machine (SVM) (n = 8 studies), followed by random forest (RF) (n = 7 studies), decision tree (DT) (n = 4 studies), gradient boosting (GB) (n = 4 studies), neural networks (NNs) (n = 3 studies), deep learning (n = 2 studies), and k-nearest neighbor (k-NN) (n = 2 studies), respectively. Forty-four features of inputs were used in the included studies, and age and gender are the most common features in the ML model. Discussion There is no single algorithm that performed better or worse than all others at classifying patients with stroke, in part because different input data require different algorithms to achieve optimal outcomes.
Objective: This study aimed to correlate the modified fluorescence stain method and conventional ZN method with routine cytology findings on lymph node aspirates for the detection of AFB in suspected cases of tuberculous lymphadenitis. Material and Methods: After adequate fine needle aspiration, aspirates were examined for cytology diagnosis, studied with Ziehl-Neelsen and Auramine-rhodamine Fluorescent stain. Cytological findings, ZN stain observations and grading were compared with fluorescent stain grading. Result: In the present study, 36 cases were reported positive by fluorescent staining method for M. tuberculosis. Out of 43 granulomatous lymphadenitis cases diagnosed by FNAC, 29 cases were reported positive for acid fast bacilli by Z-N staining. 11 cases were found as false negative (22%). Sensitivity and specificity of Z-N method was found to be 70.27% and 76.92% respectively. And for cytological method it was 96.77% and 31.57% respectively. Conclusion: There are problems in arriving at an absolute diagnosis in certain cases of tuberculous lymphadenitis when the aspirate shows polymorphous picture with occasional epithelioid cells and absence of typical Langhans giant cell or caseous necrosis. Microscopy has many advantages when it comes to speed & feasibility, its sensitivity could be improved by adjuvant methods.
Post-traumatic stress disorder (PTSD) is defined as a mental health disease that has a high probability of developing among individuals who have experienced traumatic events [...]
Introduction: Intraoperative consultation by frozen section technique is an invaluable tool for immediate diagnosis. The correlation of intraoperative frozen section diagnosis with final diagnosis on permanent section is an integral part of quality assurance in surgical pathology. Its accuracy and limitations vary with different anatomical sites. Aims & Objective: Qualitative morphological comparison between frozen section and routine formalin fixed paraffin embedded sections in different tissues, to assess the accuracy of frozen section, to detect the number and type of discrepancies and to assess the causes for discrepancies. Material and Method: The present study retrospectively reviewed frozen sections performed in the pathology department, Sirt hospital, government medical college, Bhavnagar during a period of 2 year. Diagnostic accuracy of frozen section and its morphological quality and reliability in comparison to histopathology was evaluated by 2 pathologists in a blinded fashion for the following parameters: cellular outline, nuclear and cytoplasmic features, staining pattern and overall morphology. The results were compared to the routine formalin fixed paraffin sections to evaluate diagnostic accuracy. Discordant cases were reassessed to find the reasons for discrepancy. Result: Diagnostic accuracy of frozen section was 95.1% with false negative case are 4.8% and no false positive case. Statistical analysis showed that most common indications of frozen section in the present study was presence/typing of neoplasm (61.2%) followed by assessment of margin (35.6%) and assessment of nodal status (3.2%). It was observed that nuclear details, cellular outline and overall morphological quality of frozen section was slightly inferior to that of routine histopathology section, however, staining and cytoplasmic details were comparable. The discrepancies were mainly due to technical artefacts (9.7%), sampling error (3.2%) interpretation error (1.6%), and partly due to lack of interdepartmental communication. Conclusion: Frozen section diagnosis is very useful and highly accurate procedure. Gross inspection, sampling by pathologist, frozen complemented with cytological and histological review and intimal cooperation with surgeon can avoid certain limitations and provide rapid, reliable, cost effective information necessary for optimum patient care.
Introduction: Squash smear preparation is a simple and rapid methodology for fairly accurateintraoperative diagnosis of CNS space occupying lesions. It has emerged as an important indispensibleintraoperative diagnostic aid guiding the neurosurgeon and helping in better management of patients.The current study was undertaken to study CNS tumors by squash cytology and correlating them withhistological diagnosis.Aims: To evaluate the accuracy and utility of intraoperative squash smear cytology in the evaluationof CNS tumors.Materials and Methods: A retrospective study was conducted in the Department of Pathology in atertiary care hospital from November 2019 to November 2020. A total of 74 consecutive cases wereincluded. Squash smears were prepared from the intraoperative samples and biopsy samples wereprocessed regularly. Hematoxylin and eosin staining was done and squash smear cytology results werecorrelated with the final histopathological diagnosis.Results: Out of the 74 cases studied, histopathological diagnosis was compatible with the cytologicaldiagnosis in 56 cases, pertaining to 75.67% accuracy. Remaining 18 cases showed partial discrepancyas in tumor grading or complete discrepancy.Conclusion: This study shows a high degree of cytohistological correlation. With clinicoradiologicalcorrelation, squash smear cytology could be the preferred method for intraoperative diagnosis of CNStumors.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.