Search

Background: The introduction of multiparameter MRI and novel biomarkers has greatly improved the prediction of clinically significant prostate cancer (csPCa). However, decision-making regarding prostate biopsy and prebiopsy examinations is still difficult. We aimed to establish a quick and economic tool to improve the detection of csPCa based on routinely performed clinical examinations through an automated machine learning platform (AutoML). Methods: This study included a multicenter retrospective cohort and two prospective cohorts with 4747 cases from 9 hospitals across China. The multimodal data, including demographics, clinical characteristics, laboratory tests, and ultrasound reports, of consecutive participants were retrieved using extract-transform-load tools. AutoML was applied to explore potential data processing patterns and the most suitable algorithm to build the Prostate Cancer Artificial Intelligence Diagnostic System (PCAIDS). The diagnostic performance was determined by the receiver operating characteristic curve (ROC) for discriminating csPCa from insignificant prostate cancer (PCa) and benign disease. The clinical utility was evaluated by decision curve analysis (DCA) and waterfall plots. Results: The random forest algorithm was applied in the feature selection, and the AutoML algorithm was applied for model establishment. The area under the curve (AUC) value in identifying csPCa was 0.853 in the training cohort, 0.820 in the validation cohort, 0.807 in the Changhai prospective cohort, and 0.850 in the Zhongda prospective cohort. DCA showed that the PCAIDS was superior to PSA or fPSA/tPSA for diagnosing csPCa with a higher net benefit for all threshold probabilities in all cohorts. Setting a fixed sensitivity of 95%, a total of 32.2%, 17.6%, and 26.3% of unnecessary biopsies could be avoided with less than 5% of csPCa missed in the validation cohort, Changhai and Zhongda prospective cohorts, respectively. Conclusions: The PCAIDS was an effective tool to inform decision-making regarding the need for prostate biopsy and prebiopsy examinations such as mpMRI. Further prospective and international studies are warranted to validate the findings of this study. Trial registration: Chinese Clinical Trial Registry ChiCTR2100048428. Registered on 06 July 2021. [ABSTRACT FROM AUTHOR]

Background: The purpose of this study was to assess the clinical outcome of percutaneous kyphoplasty (PKP) assisted with mixed reality (MR) technology in treatment of osteoporotic vertebral compression fracture (OVCF) with intravertebral vacuum cleft (IVC). Method: Forty cases of OVCF with IVC undergoing PKP were randomized into a MR technology-assisted group (group A) and a traditional C-arm fluoroscopy group (group B). Both groups were performed PKP and evaluated by VAS scores, ODI scores, radiological evidence of vertebral body height, and kyphotic angle (KA) at pre-operation and post-operation. The volume of injected cement, fluoroscopy times, and operation time were recorded. And cases of non-PMMA-endplates-contact(NPEC) in radiological evidence was also recorded postoperatively. The clinical outcomes and complications were evaluated afterwards. All patients received 10 to 14 months follow-up, with an average of 12 months. Result: This MR-assisted group (group A) acquired more about the amount of the polymethyl methacrylate (PMMA) injection and postoperative vertebral height and less about postoperative KA, fluoroscopy times, and operation time compared with the control group (group B) (P < 0.05). The VAS scores and ODI scores in both groups have improved, but more significantly in group A (P < 0.05). Also, more cases achieve both-endplates-touching of cement in group A (P < 0.05). And there are less of the loss of vertebral height, KA, and occurrence of re-collapse of the vertebra in group A during the follow-up (P < 0.05). Conclusion: PKP assisted with MR technology can accurately orientate the position of IVC area, which can be augmented by the balloon leading to more satisfied vertebral height improvement, cement diffusion, and pain relief. Trial registration: ClinicalTrials.gov Identifier: NCT03959059. Registered 25 September 2016. [ABSTRACT FROM AUTHOR]