Search

Abstract Bladder cancer is one of the most common cancer types in the urinary system. Yet, current bladder cancer diagnosis and follow-up techniques are time-consuming, expensive, and invasive. In the clinical practice, the gold standard for diagnosis remains invasive biopsy followed by histopathological analysis. In recent years, costly diagnostic tests involving the use of bladder cancer biomarkers have been developed, however these tests have high false-positive and false-negative rates limiting their reliability. Hence, there is an urgent need for the development of cost-effective, and non-invasive novel diagnosis methods. To address this gap, here we propose a quick, cheap, and reliable diagnostic method. Our approach relies on an artificial intelligence (AI) model to analyze droplet patterns of blood and urine samples obtained from patients and comparing them to cancer-free control subjects. The AI-assisted model in this study uses a deep neural network, a ResNet network, pre-trained on ImageNet datasets. Recognition and classification of complex patterns formed by dried urine or blood droplets under different conditions resulted in cancer diagnosis with a high specificity and sensitivity. Our approach can be systematically applied across droplets, enabling comparisons to reveal shared spatial behaviors and underlying morphological patterns. Our results support the fact that AI-based models have a great potential for non-invasive and accurate diagnosis of malignancies, including bladder cancer.

The BioCompute Object (BCO) standard is an IEEE standard (IEEE 2791-2020) designed to facilitate the communication of next-generation sequencing data analysis with applications across academia, government agencies, and industry. For example, the Food and Drug Administration (FDA) supports the standard for regulatory submissions and includes the standard in their Data Standards Catalog for the submission of HTS data. We created the BCO App to facilitate BCO generation in a range of computational environments and, in part, to participate in the Advanced Track of the precisionFDA BioCompute Object App-a-thon. The application facilitates the generation of BCOs from both workflow metadata provided as plaintext and from workflow contents written in the Common Workflow Language. The application can also access and ingest task execution results from the Cancer Genomics Cloud (CGC), an NCI funded computational platform. Creating a BCO from a CGC task significantly reduces the time required to generate a BCO on the CGC by auto-populating workflow information fields from CGC workflow and task execution results. The BCO App supports exporting BCOs as JSON or PDF files and publishing BCOs to both the CGC platform and to GitHub repositories.

Abstract Background Fifth metacarpal fractures are the most common fractures of the hand. These fractures are generally treated with conservative methods. The aim of this study was to compare the radiological and clinical outcomes of two conservative treatment methods, functional metacarpal splint(FMS) and ulnar gutter splint(UGS), for the treatment of fifth metacarpal neck fractures. Methods A prospective comparative study was designed to assess the conservative treatment of isolated and closed stable fractures of the fifth metacarpal neck. In total, 58 patients were included in the study and were treated with FMS or UGS after fracture reduction in a consecutive order. Angulation, shortening and functional outcome (QuickDASH scores and grip strengths) were evaluated at the 2nd and 6th months. Results Forty patients returned for follow-up. Twenty-two patients were treated with FMS, and 18 patients were treated with UGS. The average age was 28 years (SD ± 12, range;18–43) in the FMS group and 30 years (SD ± 14, range;18–58) in the UGS group. After reduction, significant correction was achieved in both groups, but the average angulation was lower in the FMS group(16 ± 7) compared with the UGS group (21 ± 8)(p = 0.043). However, this better initial reduction in FMS group(16 ± 7) could not be maintained in the 1st month follow-up (21 ± 5) (p = 0.009). In the FMS group, the improvement in QuickDASH scores between the 2nd and 6th month follow-up was significant (p = 0.003) but not in the UGS group(p = 0.075). When the expected grip strengths were calculated, the FMS group reached the expected strength values at the 2nd month follow-up, whereas the UGS group still exhibited significantly lower grip strength at the 2nd month follow-up(p = 0.008). However, at the end of the 6th month follow-up, both groups exhibited similar reduction, QuickDASH and grip strength values. Conclusions In stable 5th metacarpal neck fractures, FMS is adequate to prevent loss of reduction and yields faster improvement in clinical scores with earlier gain of normal grip strength compared with UGS. However, in the long term, both FMS and UGS methods yield similar radiological and clinical outcomes. Patient comfort and compliance may be better with FMS due to less joint restriction, and these findings should be considered when deciding the treatment method. Trial registration ISRCTN79534571 The date of registration: 01/04/2019 Type of study/level of evidence: Therapeutic, II.