ABSTRACT

Artificial intelligence tools, particularly convolutional neural networks (CNNs), are transforming healthcare by enhancing predictive, diagnostic, and decision-making capabilities. This review provides an accessible and practical explanation of CNNs for clinicians and highlights their relevance in medical image analysis. CNNs have shown themselves to be exceptionally useful in computer vision, a field that enables machines to 'see' and interpret visual data. Understanding how these models work can help clinicians leverage their full potential, especially as artificial intelligence continues to evolve and integrate into healthcare. CNNs have already demonstrated their efficacy in diverse medical fields, including radiology, histopathology, and medical photography. In radiology, CNNs have been used to automate the assessment of conditions such as pneumonia, pulmonary embolism, and rectal cancer. In histopathology, CNNs have been used to assess and classify colorectal polyps, gastric epithelial tumours, as well as assist in the assessment of multiple malignancies. In medical photography, CNNs have been used to assess retinal diseases and skin conditions, and to detect gastric and colorectal polyps during endoscopic procedures. In surgical laparoscopy, they may provide intraoperative assistance to surgeons, helping interpret surgical anatomy and demonstrate safe dissection zones. The integration of CNNs into medical image analysis promises to enhance diagnostic accuracy, streamline workflow efficiency, and expand access to expert-level image analysis, contributing to the ultimate goal of delivering further improvements in patient and healthcare outcomes.

PMID:37794609 | DOI:10.1093/postmj/qgad095

07:11

PubMed articles on: Cancer & VTE/PE

How we manage a high D-dimer

Haematologica. 2023 Oct 26. doi: 10.3324/haematol.2023.283966. Online ahead of print.

ABSTRACT

D-dimer, a soluble fibrin degradation product that originates from plasmin-induced degradation of cross-linked fibrin, is an important biomarker of coagulation activation and secondary fibrinolysis that is routinely used to rule out venous thromboembolism (VTE), to evaluate the risk of VTE recurrence as well as the optimal duration of anticoagulant therapy. Besides VTE, D-dimer may be high due to physiologic conditions, including aging, pregnancy and strenuous physical activity. In addition, several disorders have been associated with increased D-dimer levels, spanning from disseminated intravascular coagulation to infectious diseases and cancers. Thus, it is far from unusual for hematologists to have to deal with ambulatory individuals presenting with increased Ddimer without signs or symptoms of thrombus formation. To the management of these cases by the hematologist is dedicated this narrative review.

PMID:37881856 | DOI:10.3324/haematol.2023.283966

07:11

PubMed articles on: Cancer & VTE/PE

Heterogeneous distributions in clinical events preceding anticoagulant treatment nonpersistence in patients with venous thromboembolism stratified by active cancer: A nationwide cohort study

Cancer Med. 2023 Oct 26. doi: 10.1002/cam4.6626. Online ahead of print.

ABSTRACT

BACKGROUND: Nonpersistence in anticoagulation therapy is common and associated with undesirable clinical outcomes in patients with venous thromboembolism (VTE).

METHODS: We investigated preceding clinical events of treatment nonpersistence (e.g., switching, discontinuing, or restarting) in VTE patients with and without active cancer using Korean claims database.

RESULTS: Clinically significant events including thromboembolic events, hepatic function change and surgery preceded treatment nonpersistence, but heterogeneous distributions of clinical events were observed in the presence of active cancer. Patients with active cancer had a low rate of clinical events preceding treatment nonpersistence, and new active cancer diagnosis in the nonactive cancer group was most common before the switch to parenteral anticoagulants from warfarin or non-vitamin K antagonist oral anticoagulants (NOACs).

CONCLUSION: These findings suggest that clinically significant events can precede treatment nonpersistence and largely paralleled current guidelines for patients with VTE, whereas heterogeneous distributions of clinical events were observed in the presence of active cancer.

PMID:37882319 | DOI:10.1002/cam4.6626

07:11

PubMed articles on: Cancer & VTE/PE

Anticoagulation and venous thromboembolism in patients aged 90 years and older: Data from the RIETE registry

J Am Geriatr Soc. 2023 Oct 10. doi: 10.1111/jgs.18626. Online ahead of print.