Diagnostics

IntroductionThe precise determination of diagnostic cut-off points is essential for the development of multimarker panels in oncology. In previous work on pulmonary nodules, it was observed that the standard two-parameter logistic fit could be insufficient for biomarkers with asymmetric distributions. Furthermore, the calculation of empirical cut-off points based on graphical visualization presented limitations in precision and reproducibility. ObjectiveThis study presents a methodological advancement in the data analysis phase (Stage 1), introducing new Python algorithms for the direct analytical calculation of empirical intersections and robust mathematical modeling using Dual Annealing with both two-parameter and four-parameter logistic functions. This improved methodology feeds into the ThresholdXpert 1.0 software tool for combinatorial optimization of biomarker panels (Stage 2), and is applied here to the diagnostic challenge of hepatocellular carcinoma (HCC). MethodsThe methodology was first validated by re-analyzing a dataset of patients with pulmonary nodules (N=895). It was subsequently applied to an HCC dataset derived from the cohort of Jang et al. (208 HCC, 193 cirrhosis, 401 total), randomly divided into a training set (280) and an independent test set (121). Scripts were developed to compare the previous two-parameter logistic fit with the new two- and four-parameter logistic models. Finally, ThresholdXpert 1.0 was used for multimarker panel optimization. ResultsThe integration of empirical calculation, logistic modeling, and combinatorial optimization through ThresholdXpert 1.0 provides a robust and coherent framework for the development of multimarker diagnostic panels. The four-parameter logistic model provided additional validation without substantially modifying cut-off values for most biomarkers, confirming the stability of the approach while offering greater flexibility for complex distributions. When applied to hepatocellular carcinoma, the framework identified a molecular panel composed of AFP, PIVKA-II, OPN, and DKK-1 with sensitivity of 0.77 and specificity of 0.72, and an optimized panel incorporating inverse MELD that achieved the best overall balance (sensitivity 0.73, specificity 0.75) in independent external validation. These results demonstrate the potential of this approach as a generalizable tool for the optimized design of binary diagnostic systems in oncology. ConclusionThe integration of complementary mathematical modeling enhances the capability of ThresholdXpert 1.0 to identify robust diagnostic panels, as in some cases a single biomarker may outperform biomarker combinations, and vice versa. This approach enabled the integration of molecular biomarkers and clinical variables under a unified mathematical framework. Contactroberto117343@gmail.com

Urinary tract infections (UTIs) are the most common infections in both outpatient and inpatient settings, contributing significantly to morbidity, reduced quality of life, and antimicrobial overuse. Although urine culture remains the diagnostic gold standard, it poses practical limitations in clinical workflows. Rapid diagnostic methods such as urine flow cytometry (UF) offer potential for timely, reliable UTI detection. We conducted a multicenter diagnostic study to evaluate the performance of BACT-Info. and UTI-Info. flags on the UF-5000/4000 system in detecting UTIs, using presumptive Gram staining and urine culture (>10 CFU/mL) as references. A total of 763 patients with suspected UTI were enrolled, and 721 patients--with uropathogenic bacteria and complete data--were included in the final analysis (384 with culture-confirmed UTI and 337 without UTI). The diagnostic value of nitrituria was highly specific, while leukocyte esterase was sensitive. For BACT-count and WBC-count of UF-5000/4000, the AUCs were 0.85 and 0.69, respectively. Using cutoffs of WBC >82.05/{micro}L or bacteria >975.4/{micro}L, the UTI-Info flag demonstrated 89% sensitivity, 54% specificity, 69% positive predictive value, and 82% negative predictive value. Positive and negative likelihood ratios were 1.93 and 0.20, respectively. The agreement between the BACT-Info. flag and Gram typing showed Kappa values of 0.716 for Gram-negative and 0.216 for Gram-positive bacteria when compared to culture, and 0.721 and 0.401, respectively, when compared to presumptive Gram staining. The UF-5000/4000 UTI-Info. and BACT-Info. flags show promise as a rapid UTI screening tool. The combination of these flags with urinalysis parameters, nitrite testing and leukocyte has potential to be developed into a diagnostic algorithm for early and sensitive UTI prediction. Such an approach may reduce unnecessary urine cultures and support timely, appropriate empiric antibiotic therapy. Establishing optimal cutoffs tailored to specific clinical settings is essential to enhance diagnostic accuracy and improve clinical utility.

IntroductionBladder cancer (BC) remains the most common malignancy of the urinary tract, with non-muscle invasive BC (NMIBC) representing the vast majority of bladder cancer patients. The current standard of care (SOC) follow-up in NMIBC patients demands an intensive schedule and requires costly and burdensome methods, driving the development of alternative, non-invasive, cost-effective methods that may complement or serve as substitutes to cystoscopy and cytology. Uromonitor(R) is a urine biomarker test that detects hotspot mutations in three genes (TERT, FGFR3, and KRAS) for the evaluation of disease recurrence. The aim of the current study was to assess its performance comparing it to the current SOC methods. Materials and MethodsA total of 528 NMIBC surveillances from 439 individual patients were enrolled from December 2021 to June 2023. All subjects underwent SOC methods and provided an urine sample before undergoing cystoscopy for Uromonitor(R) analysis. Sensitivity, specificity, positive predictive value (PPV) and negative predictive value (NPV) were calculated for recurrence and compared to the gold-standard cystoscopy plus trans-urethral resection (TURBT) pathology. ResultsUromonitor(R) displayed a sensitivity of 87.2%, with only 6 recurrences failing to be detected by the urinary biomarker test, a specificity of 99.2%, a positive predictive value (PPV) of 93.2% and a negative predictive value (NPV) of 98.8%. Cystoscopy showed a total of 22 (31,88%) false positives not confirmed by TURBT, while Uromonitor(R) presented only 3 positive tests where no suspected lesions were found in cystoscopy. Sensitivity, specificity and NPV values for Uromonitor(R) also remained high across all NMIBC grades and stages. ConclusionIn the present study, we confirmed that the Uromonitor(R) biomarker test represents a reliable tool in the detection of NMIBC recurrence in patients undergoing routine surveillance, regardless of stage and grade. It offers either an alternative or a complement to the current SOC methods, providing rapid results and a non-invasive option, potentially improving patients quality of life and helping reduce the economic burden of NMIBC follow-up. To our knowledge, this is the largest single-center study assessing Uromonitor(R)s performance and thus validating its usefulness in clinical practice.

Trial designPilot feasibility trial. MethodsO_ST_ABSParticipantsC_ST_ABSadults attending the Outpatient Urology Clinic, having a long-term indwelling urinary catheter and have the mental capacity to consent. Consent for the donation of the urinary catheter and drainage bag were gained at the Urology Clinic, Royal United Hospital (RUH) Bath, alongside a quality-of-life questionnaire. Interventionsthere was no direct intervention to the participants, the trial was to test the functionality of the diagnostic sensor, there was no change to the participants medical care. Objectivesrecruitment of 48 participants to donate catheter and drainage bags (including re-recruits); assess the functionality of the sensor to predict impending catheter blockage in human urine; assess the functionality to release at pH > 7; and assess the microbiological profile of the patients with long-term catheters. Outcomedetermination of whether the participant had a blockage event 3 weeks post catheter change, and whether this matched with the result from the sensor. Measurements of the participants urine to assess whether the sensor could detect human urine at a pH > 7. Determine the microbial species present in the drainage bag of the participants. ResultsO_ST_ABSRecruitmentC_ST_ABSreceived 35 samples from 28 individuals. Outcometwo participants reported blockage events which were successfully detected by the sensor. However, the sensor also predicted blockage in participants that did not block within the 3-week report time period, sensitivity = 100%, specificity = 58.06%. The functionality of the sensor to detect urine above pH > 7 had a sensitivity = 78.75% and a specificity = 96.77%, which gave a p = 2.06x10-24 ({chi}2 test). Inclusion of the maintenance solution prescribed to participants, to test the predictability of the sensor, gave a sensitivity = 100%, and a specificity = 62.95%, p = 0.029 (Fisher Exact test). Microbiological analysis indicated that Proteus spp. and Pseudomonas spp. were the most commonly isolated microbes. HarmNo adverse events. ConclusionsThe sensor can predict participants more prone to catheter blockage, and it is accurate in detecting urine with a pH >7. Owing to the small sample number of this trial, the results are not statistically powered. However, the data can be used to improve the design of the sensor and inform the design of a larger, randomized clinical trial. Trial registrationTrial was ethically approved by the Research Ethics Committee (REC) number: 20/LO/0094. Integrated Research Application System (IRAS) number: 261095. Fundingtrial was funded by the Urology Foundation and an IAA seed grant, University of Bath.

ObjectivesTo increase cervical cancer screening capacity and participation, we evaluated the performance of the newly developed hrHPV ReadyMix qPCR Kit for detecting high-risk Human Papillomavirus (HPV) in urine samples while simultaneously genotyping HPV16, HPV18, and HPV52. Methods876 samples were used to assess the performance of hrHPV ReadyMix qPCR Kit in detecting high-risk HPV in standard cervical swab sample compared to the Roche cobas(R) 6800 HPV. The high-risk HPV detection in urine was compared to the corresponding paired cervical swab. ResultsThe sensitivity of HPV detection in cervical swabs using hrHPV ReadyMix qPCR Kit reached 96.55% and the specificity reached 99.87%. Despite higher Ct values, urine samples demonstrated 80.88% sensitivity and 100.00% specificity compared to cervical swabs. Our method enables population-based high-risk HPV analysis with a 6.62% HPV prevalence from cervical swabs and 6.28% from urine samples. Furthermore, urine samples using the hrHPV ReadyMix qPCR Kit showed comparable HPV type distribution and the ability to genotype HPV16 and HPV18, to Roche the cobas(R) 6800 HPV. ConclusionsSelf-collected urine samples offer a 98.48% diagnostic accuracy for detecting high- risk HPV infection. This study highlights the hrHPV ReadyMix qPCR Kits potential in enhancing cervical cancer screening, offering valuable insights for future interventions.

Background Lung cancer mortality is rising in Libya, but access to molecular diagnostics for EGFR mutations--essential for guiding tyrosine kinase inhibitor therapy--remains severely limited. Selecting an appropriate testing platform requires balancing analytical performance against cost and infrastructure constraints. Methods We conducted a prospective comparative validation study using formalin-fixed paraffin-embedded (FFPE) tissue samples from Libyan non-small cell lung cancer (NSCLC) patients. Following stringent DNA quality control, samples were tested in parallel across four platforms: multiplex real-time PCR (MRT-PCR), reverse hybridization strip assay (RHSA), agarose gel electrophoresis (AGE), and immunohistochemistry (IHC). Performance was assessed by inter-method concordance, turnaround time, and cost per test. Results Of 30 initial samples, only six (20%) met quality thresholds (A260/A280 1.70-1.90; concentration [≥]10 ng/{micro}L), highlighting pre-analytical challenges. Three samples harbored EGFR exon 19 deletions. A critical discordance was identified: one sample tested negative by MRT-PCR (Ct {approx}38, {Delta}Ct=13) but positive by RHSA, AGE, and IHC, indicating a false-negative result from the reference method. IHC and RHSA offered the most favorable balance of cost (USD 40-75/test) and operational feasibility, while MRT-PCR (USD 150/test) required specialized infrastructure. Conclusions Relying solely on automated PCR may lead to under-diagnosis in low-cellularity or degraded FFPE samples. We recommend a hybrid algorithm: IHC as a cost-effective primary screen, followed by RHSA for confirmation. This approach optimizes resource allocation and improves diagnostic equity in Libya.

ObjectivesTo propose a tool to detect and locate malignant nodules and microcalcifications in mammography and judge its potential as a screening tool. MethodsIn this institutional review board approved retrospective study we presented a new tool based on deep learning techniques to predict and locate lesions in mammograms, called quantusMM. 3,114 mammograms from 976 patients were collected from Onkologikoa (Instituto Oncologico de Kutxa) databases for this purpose: 1,248 images with malignant nodules, 736 with malignant microcalcifications and 1,131 without any suspicious findings. The proposed methods split the images in patches to be able to locate the lesions in the image. Then, these methods select the patches most likely to have a lesion based on the brightness values of the pixels. 80% of the selected patches (with the corresponding outcome) were used to train deep learning algorithms and the remaining 20% were used to test the performance to classify into malignant parts or control parts. ResultsThe proposed methods obtain an area under the ROC curve (AUC) of 95.5% to predict malignant nodules using the patches, and 90.4% to predict malignant nodules into the whole images. To predict malignant microcalcifications the method obtains an AUC of 99.0% into patches and 90.0% into the whole images. ConclusionsThe proposed tool shows potential to predict and locate malignant nodules and microcalcification lesions in mammography. This new approach could help in the first screening of patients and also could greatly benefit radiologists to support decision making.

Over the last 6 years, five-year survival rate for pancreatic cancer patients has increased from 6 to 10% after the initial diagnosis, which makes it one of the deadliest cancer types. This disease is known as the "silent killer" because early detection is challenging due to the location of the pancreas in the body and the nonspecific clinical symptoms. The Bossmann group has developed ultrasensitive nanobiosensors for protease/arginase detection comprised of Fe/Fe3O4 nanoparticles, cyanine 5.5, and designer peptide sequences linked to TCPP. Initial data obtained from both gene expression analysis and protease/arginase activity detection in serum indicated the feasibility of early pancreatic cancer detection. Several matrix metalloproteinases (MMPs, -1, -3, and -9), cathepsins (CTS) B and E, neutrophil elastase, and urokinase plaminogen activator (uPA) have been identified as candidates for proximal biomarkers. In this study, we have confirmed our initial results from 2018 performing serum sample analysis assays using a larger group sample size (n=159), which included localized (n=33) and metastatic pancreatic cancer (n=50), pancreatitis (n=26), and an age-matched healthy control group (n=50). The data obtained from the eight nanobiosensors capable of ultrasensitive protease and arginase activity measurements were analyzed by means of an optimized information fusion-based hierarchical decision structure. This permits the modeling of early-stage detection of pancreatic cancer as a multi-class classification problem. The most striking result is that this methodology permits the detection of localized pancreatic cancers from serum analyses with 96% accuracy.

IntroductionUntreated urinary tract infections (UTIs) can lead to complications, including renal deterioration due to upper urinary tract involvement. Proteinuria, characterized by excessive protein in the urine, is often indicative of kidney damage. The protein-to-creatinine ratio (P/C ratio) test is a convenient and reliable method for assessing proteinuria. This study aimed to evaluate the urine protein-to-creatinine ratio (UPCR) in UTI patients and its association with renal impairment. Materials and MethodsEighty patients with confirmed UTI and suspected proteinuria were recruited. Urine screening included pyuria (white blood cell presence) as an initial indicator of UTI, followed by microscopic examination of centrifuged urinary sediments. The urine supernatant was analyzed for protein using the urine strip method. ResultsAfter applying exclusion criteria, forty-six patients (n=46) were included in the statistical analysis. Of these, 26% had normal proteinuria (<15 mg/mM Cr), 35% had moderate proteinuria (15-50 mg/mM Cr), and 39% exhibited severe proteinuria (>50 mg/mM Cr). Patients were categorized into three stages (I, II, and III) with mean creatinine excretion values of 33.9 {+/-} 13.9 mg/dL, 31.2 {+/-} 17.2 mg/dL, and 29 {+/-} 13.6 mg/dL, respectively, all significantly below the reference interval (168 {+/-} 132 mg/dL). ConclusionIncreased urinary protein excretion correlates with heightened risk of renal complications, a leading factor in mortality. Urinary protein excretion was markedly elevated in Stage III patients. The P/C ratio proved to be a more accurate diagnostic marker within the urine profile, highlighting proteinuria in UTI patients as a potential risk factor for renal impairment.

This study introduces The Potential Sensor, a proof-of-principle system designed for nocturnal erection detection. The article introduces a novel approach to non-invasive ED diagnostics, which aims to optimize patient comfort and consequently system validity through avoidance of applying pressure-based measurements. A literature review on erection physiology and applicable sensor technologies showed evaluated concepts for measuring penile erection, including temperature, circumference, movement, blood oxygenation, and arterial pulse as suitable for application in a patient-friendly diagnostic system. This guided the development of system requirements for a device designed to quantify both erection duration and erection quality through simultaneous assessment of multiple physiological principles. The proposed system integrates four commercially available sensor types (thermistors, stretch sensors, accelerometers, and pulse oximeters) and connects these to a microprocessor that transmits data via Bluetooth. Initial testing of the sensor components confirmed precision and accuracy of the device, demonstrating readiness for future feasibility and clinical validation studies. The Potential Sensor offers a unique diagnostic approach, which presents as a promising alternative to traditional nocturnal penile tumescence and rigidity tests, by enhancing patient comfort. This novel approach has the potential not only to reintroduce non-invasive diagnostics in clinical practice, but also to improve the understanding of physiological mechanisms underlying erectile dysfunction.

BackgroundUroepithelial carcinoma is a serious threat to human health and causes heavy economic burden. Enhanced CT is widely used in screening or preliminary diagnosis of uroepithelial tumors. However, false-positive results of enhanced CT will bring unnecessary mental pain, expensive examination costs, physical injuries, and other adverse consequences; while false-negative results of enhanced CT bring delayed treatment, and patients will thus have to bear the adverse consequences of poor prognosis, high treatment costs, poor quality of life, and short survival period. There is an urgent need to find convenient, cost-effective and non-invasive diagnostic methods to reduce the false-negative and false-positive rates of enhanced CT in uroepithelial tumors. The aim of this study was to evaluate the diagnostic value of YiDiXie-SS and YiDiXie-HS in uroepithelial carcinoma. Patients and methods319 subjects (malignant group, n=240; benign group, n=79) were finally included in this study. Remaining serum samples from the subjects were collected and tested by applying the YiDiXie all-cancer detection kit to evaluate the sensitivity and specificity of YiDiXie-SS and YiDiXie-HS. ResultsThe sensitivity of YiDiXie-SS in enhanced CT-positive patients was 96.3% (95% CI: 96.3% - 98.3%; 158/164)and its specificity was 64.3% (95% CI: 38.8% - 83.7%; 9/14). This means that the application of YiDiXie -SS reduces the false-positive rate of urological enhanced CT by 64.3% (95% CI: 38.8% - 83.7%; 9/14) with essentially no increase in malignancy leakage. The sensitivity of YiDiXie-HS in enhanced CT-negative patients was 85.5% (95% CI: 75.9% - 91.7%; 65/76)and its specificity was 84.6% (95% CI: 73.9% - 91.4%; 55/65). This means that the application of YiDiXie-HS reduces the false-negative rate of urological enhanced CT by 85.5% (95% CI: 75.9% - 91.7%; 65/76). ConclusionYiDiXie -SS substantially reduces the rate of urological enhanced CT false positives with essentially no increase in delayed treatment of malignancies. YiDiXie-HS substantially reduces the false negative rate of urological enhanced CT. YiDiXie -SS and YiDiXie -HS have an important diagnostic value in uroepithelial carcinoma, and are expected to solve the problems of "high false-positive rate of urological enhanced CT" and "high false-negative rate of urological enhanced CT" in uroepithelial carcinoma. Clinical trial numberChiCTR2200066840.

Prostate cancer (PCa) remains the most frequently diagnosed malignancy in men and the second leading cause of cancer-related mortality worldwide. Population-based prevention and screening programmes have improved early detection rates; however, current diagnostic pathways--largely driven by prostate-specific antigen (PSA) testing and imaging--still suffer from limited sensitivity and specificity. This limitation contributes to substantial rates of unnecessary biopsies, overdiagnosis and overtreatment, highlighting the need for more accurate molecular stratification tools. In recent years, circulating microRNAs (miRNAs) have emerged as promising biomarkers for cancer diagnosis, risk reclassification, prediction of tumour progression and treatment response. Among them, miR-410-3p and miR-141-5p have been consistently implicated in prostate cancer biology. Previous studies in tumour tissues and prostate cancer cell lines have demonstrated that elevated miR-410-3p expression correlates with discordant clinical scenarios in which PSA levels fail to match biopsy, surgical or digital rectal examination findings, as well as with poor patient prognosis. In parallel, miR-141-5p exhibits complementary behaviour, supporting the rationale for a dual-biomarker approach based on relative expression patterns rather than single-marker quantification. Mechanistically, miR-410-3p has been shown to exert oncogenic activity through downregulation of PTEN, leading to activation of the AKT/mTOR signalling pathway. Notably, divergent expression dynamics of miR-410-3p have been reported between tumour tissues, cancer cell lines and peripheral blood, reinforcing the value of combined assessment with miR-141-5p. Large cohort studies (n > 500) have confirmed upregulation of miR-141-5p in prostate cancer patients at both epithelial and stromal levels, while concomitant reduction of circulating miR-410-3p has been associated with increased risk of biochemical recurrence. In this study, we present the design, molecular configuration and preclinical evaluation of a novel RTqPCR-based diagnostic system that leverages residual blood volumes routinely discarded after PSA testing. The system enables semi-quantitative, parallel detection of miR-410-3p and miR-141-5p in plasma, providing a non-invasive molecular readout of prostate cancer progression and recurrence risk. The results support the feasibility of this approach as a complementary diagnostic tool with the potential to reduce reliance on invasive procedures such as biopsy, surgery and digital rectal examination, while improving molecular precision in prostate cancer management.

PurposeThe retrograde urethrogram (RUG) has been a key diagnostic tool for over a century, remaining essential despite the availability of other imaging techniques for screening, diagnosis and follow up of Urethral strictures. However, interpretation of RUG images has to be done manually and needs experience on the part of the treating urologist, which calls for a common understanding of RUGs and presents a chance to improve stricture management in a practical way. Artificial intelligence (AI) algorithms present a novel way to prevent human discrepancy while concomitantly improving the accuracy of stricture identification and classification. MethodsO_ST_ABSDatasetC_ST_ABSWe have used a balanced dataset which includes RUGs of 168 strictured cases and 178 non-strictured(healthy) cases. Task#1The primary requirement is to identify the Urethral region in any clinically obtained RUGs and detect the presence of stricture in it. We successfully deployed a Segmentation and Classification model to categorize the whole dataset as strictured or non-strictured RUGs. Task#2On obtaining superior accuracy, we effectively went on to identify the type of stricture based on their location, which is of clinical importance. ResultsWith the above-mentioned available RUG dataset from 346 cases, we could train our Deep learning model and achieve a significant accuracy of 91.53% in detection and categorizing the type of stricture. At the end, a 10-fold cross-validation yielded an accuracy of about 86.66%. ConclusionOur attempts have successfully validated that using Deep learning (DL) tools, one could readily (i) Detect the presence of stricture in a given RUG and (ii) ultimately locate and classify these strictures effectively. Thus, these Deep learning tools could be of great clinical assistance for Urinary stricture related disease management.

BackgroundSARS-CoV-2 has been responsible for more than 550 million cases of COVID-19 worldwide. RT-PCR is considered the "gold standard" for the diagnosis of patients suspected of having COVID-19. During the heightened waves of the pandemic, more rapid tests have been required. Point-of-care tests (POCT) for COVID-19 include antigen tests, serological tests, and other molecular-based platforms. The ID NOW COVID-19 assay (Abbott) performs an isothermal gene amplification of a target encoding the RNA-dependent RNA polymerase of SARSCoV-2. The main objective of this study was to evaluate the organizational impact following the implementation of a POC testing platform ID NOW in a maternity ward. Materials and MethodsThis retrospective study included pregnant women admitted for Groupe Hospitalier Paris Saint-Joseph Paris. The study was conducted over 2 periods lasting 6 months each. The first period (P1) corresponded to the 2nd wave in France (July to December 2020) whereas the second (P2) period focused on the 3rd wave (February to July 2021). During P1, viral detection was performed by RT-PCR at the hospitals laboratory. During P2, it was performed with the ID NOW COVID-19 test directly in the delivery room by nursing staff after training and certification. Our primary endpoint was the length of time in the birth room from admission to discharge in the postpartum period. Results2447 pregnant women were included, 1053 during P1 and 1394 during P2. The median age, percentage of singleton pregnancies, mean gestational age, percentage of nulliparous individuals, percentage of vaginal deliveries, and COVID19 positivity rate were comparable between the two periods. During P2, the length of stay in the delivery room was significantly shorter than during P1 (17.9 vs 14.7 hours, p<0.001). ConclusionAnalysis of the data from this study following the implementation of the ID NOW POCT in the maternity ward indicates a significant decrease in the length of stay in the birth room. This outcome needs to be confirmed in a multicenter cohort, in particular to precise the specific impact of COVID-19 care on delays.

The Contact Surface Area (CSA) is a predictor for peri-operative parameters and represent the contact area between the tumor and the respective organ. Nowadays, a precise method for calculating CSA is yet to be found in the literature. We tested a new CSA calculation method as a predictor of intra-operative parameters in robot assisted partial nephrectomy (RAPN). The study population consisted of all consecutive patients treated with RAPN at a single high-volume European institution (between 2020 to 2023; 82 patients). We proposed a new method to measure the real value of CSA using an algorithm that leverages the geometry of kidneys and tumors obtained from 3D reconstruction. These reconstructions were obtained using the certified medical software Materialized Mimics InPrint. Peri-operative parameters of patients were recorded in an anonymous database. We explored the correlation between RCSA, CSA of Hsieh (HCSA), PADUA and R.E.N.A.L. scores with peri-operative parameters using Spearmans correlation. Furthermore, we examined which of RCSA, PADUA and R.E.N.A.L. score better describes the intra-operative parameters, Warm Ischemia Time (WIT), Operating Time (OT), and Estimated Blood Loss (EBL) using Receiver Operating Characteristic (ROC) curve analysis. Multivariable linear regression analyses were performed. We observed a significant correlation between RCSA and WIT, OT and EBL. Moreover, RCSA outperformed both the PADUA and R.E.N.A.L. score as demonstrated in the ROC curve analysis. In ROC analysis was chosen a threshold for each of the parameters: for WIT 20 minutes, for OT 180 minutes and for EBL 200 mL. At multivariable regression analysis, RCSA emerged as the only independent predictor for WIT, OT and EBL (B=0.39 & p=0.03, B=0.35 & p=0.01, B=0.48 & p<0.001, respectively). Our original and effective 3D RCSA calculation method was favorably associated to intra-operative surgical outcomes. As compared to PADUA and RENAL score, our calculated RCSA represented a better predictor of intra-operative parameters.

BackgroundRenal cancer is a serious threat to human health and causes heavy economic burden. Enhanced CT is widely used in the diagnosis of renal tumors. However, false-positive results of enhanced CT will bring unnecessary mental pain, expensive examination costs, physical injuries, and even adverse consequences such as organ removal and loss of function; while false-negative results of enhanced CT bring delayed treatment, and patients will thus have to bear the adverse consequences of poor prognosis, high treatment costs, poor quality of life, and short survival period. There is an urgent need to find convenient, cost-effective and non-invasive diagnostic methods to reduce the false-positive and false-negative rates of enhanced CT in renal tumors. The aim of this study was to evaluate the diagnostic value of YiDiXie -SS, YiDiXie-HS and YiDiXie-D in renal cancer. Patients and methods309 subjects (malignant group, n=244; benign group, n=65) were finally included in this study. Remaining serum samples from the subjects were collected and tested by applying the YiDiXie all-cancer detection kit to evaluate the sensitivity and specificity of YiDiXie-SS, YiDiXie-HS and YiDiXie-D, respectively. ResultsYiDiXie-SS had a sensitivity of 98.6% (95% CI: 95.8% - 99.6%; 204/207) and a specificity of 71.4% (95% CI: 45.4% - 88.3%; 10/14) in renal enhanced CT-positive patients. This means that the application of YiDiXie -SS reduces the false-positive rate of renal enhanced CT by 71.4% (95% CI: 45.4% - 88.3%; 10/14) with essentially no increase in malignant tumor leakage. The sensitivity of YiDiXie-HS in renal enhanced CT-negative patients was 86.5% ( 95% CI: 72.0% - 94.1%; 32/37) and its specificity was 84.3% (95% CI: 72.0% - 91.8%; 43/51). This means that the application of YiDiXie-HS reduces the false-negative rate of enhanced CT by 86.5% (95% CI: 72.0% - 94.1%; 32/37). The sensitivity of YiDiXie -D in renal enhanced CT-positive patients was 31.9% (95% CI: 25.9% - 38.5%; 66/207) and its specificity was 92.9% (95% CI: 68.5% - 99.6%; 13/14). This means that YiDiXie-SS reduces the false positive rate of enhanced CT by 92.9% (95% CI: 68.5% - 99.6%; 13/14). ConclusionYiDiXie-SS dramatically reduces the false-positive rate of renal enhanced CT with essentially no increase in delayed treatment of malignant tumors. YiDiXie-HS dramatically reduces the false-negative rate of renal enhanced CT. YiDiXie -D dramatically reduces the false-positive rate of renal enhanced CT. The YiDiXie test has significant diagnostic value in renal tumors, and is expected to solve the problems of "high false-positive rate of renal enhanced CT" and "high false-negative rate of renal enhanced CT". Clinical trial numberChiCTR2200066840.

Radiomics, an emerging field in medical imaging, leverages advanced mathematical analysis to extract quantitative metrics from medical images, aiding in the early detection, diagnosis, and treatment of lung cancer. This study focuses on improving the risk prediction of small lung nodules using machine learning models. We employed a stacking ensemble approach, integrating Principal Component Analysis (PCA) for dimensionality reduction and selected features from the Small Nodule Radiomics-Predictive Vector (SN-RPV). Base models employed in the stacking ensemble were Support Vector Machine (SVM), Random Forest, k-Nearest Neighbors (KNN), and Naive Bayes classifiers. Despite the theoretical advantages of stacking ensembles, our models demonstrated poorer performance on the test set compared to the simpler SN-RPV model by Hunter et al. This outcome highlights the challenges of overfitting and underscores the importance of model simplicity and interpretability in clinical applications. Future research should explore alternative regularization techniques to improve the generalization of complex ensemble methods.

BackgroundBreast cancer is a serious threat to womens health and breast cancer screening is of great importance. Breast ultrasound or mammography is widely used for screening or diagnosis of breast tumors, However, false-positive breast ultrasound or mammogram results can lead to misdiagnosis and wrong puncture biopsy, while false-negative breast ultrasound or mammogram results can lead to missed diagnosis and delayed treatment. There is an urgent need to find a convenient, cost-effective and noninvasive method to reduce the false-positive rate and the false-negative rate of breast ultrasound or mammography. The aim of this study was to evaluate the diagnostic value of YiDiXie-SS, YiDiXie-HS and YiDiXie-D in breast cancer. Patients and methods816 subjects (malignant group, n=778; benign tumor group, n=38) were finally included in this study. The remaining serum samples were collected and tested by YiDiXie all-cancer detection kit. The sensitivity and specificity of YiDiXie tests were evaluated respectively. ResultsThe sensitivity of YiDiXie-SS was 97.8% (95% CI: 96.5% - 98.6%) and its specificity was 63.2% (95% CI: 47.3% - 76.6%). This means that YiDiXie-SS has an extremely high sensitivity and relatively high specificity in breast tumors.YiDiXie-HS has a sensitivity of 84.4% (95% CI: 81.7% - 86.8%) and a specificity of 86.8% (95% CI: 72.7% - 94.2%). This means that YiDiXie-HS has high sensitivity and specificity in breast tumors.YiDiXie-HS has a sensitivity of 73.8% (95% CI: 70.6% - 76.7%) and a specificity of 94.7% (95% CI: 82.7% - 99.1%). This means that YiDiXie-D has relatively high sensitivity and very high specificity in breast tumors. The sensitivity of YiDiXie-SS in ultrasound and mammography-positive patients was 97.8% (95% CI: 96.5% - 98.7%), 97.6% (95% CI: 95.8% - 98.6%), and the specificity was 63.6% (95% CI. 46.6% - 77.8%), 58.3% (95% CI: 32.0% - 80.7%), respectively. This means that the application of YiDiXie-SS reduced ultrasound and mammography false-positive rates by 63.6% (95% CI: 46.6% - 77.8%) and 58.3% (95% CI: 32.0% - 80.7%), respectively, with essentially no increase in the leakage of malignant tumors. The sensitivity of YiDiXie-HS in ultrasound and mammography-negative patients was 84.8% (95% CI: 69.1% - 93.9%), 85.7% (95% CI: 76.7% - 91.6%), and the specificity was 60.0% (95% CI. 23.1% - 92.9%), 80.0% (95% CI: 37.6% - 99.0%), respectively. This means that the application of YiDiXie-HS reduced the false-negative rates of ultrasound and mammography by 84.8% (95% CI: 69.1% - 93.9%), 85.7% (95% CI: 76.7% - 91.6%), respectively. The sensitivity of YiDiXie-D in ultrasound and mammography-positive patients was 74.0% (95% CI: 70.8% - 77.0%), 76.9% (95% CI: 73.0% - 80.4%), and the specificity was 93.9% (95% CI. 80.4% - 98.9%), 91.7% (95% CI: 64.6% - 99.6%), respectively. This means that YiDiXie-D reduced the false positive rate of ultrasound and mammography by 93.9% (95% CI: 80.4% - 98.9%), 91.7% (95% CI: 64.6% - 99.6%), respectively. The sensitivity of YiDiXie -D in ultrasound and mammography-negative patients was 72.7% (95% CI: 55.8% - 84.9%), 75.0% (95% CI: 64.8% - 83.0%), and its specificity was 100% (95% CI. 56.6% - 100%), 100% (95% CI: 56.6% - 100%), respectively. This means that YiDiXie-D reduces the false negative rate of ultrasound and mammography by 72.7% (95% CI: 55.8% - 84.9%) and 75.0% (95% CI: 64.8% - 83.0%), respectively, while maintaining a high specificity. ConclusionYiDiXie-SS has extremely high sensitivity and relatively high specificity in breast tumors.YiDiXie-HS has high sensitivity and high specificity in breast tumors.YiDiXie-D has relatively high sensitivity and extremely high specificity in breast tumors.YiDiXie-SS significantly reduces the rate of false positives by breast ultrasound or mammography with essentially no increase in delayed treatment of breast cancer. YiDiXie-HS significantly reduces the rate of false negatives on breast ultrasound or mammograms.YiDiXie-D significantly reduces the rate of false positives on breast ultrasound or mammograms or significantly reduces the rate of false negatives while maintaining a high level of specificity. YiDiXie tests has significant diagnostic value in breast cancer and is expected to solve the problems of "high false positive rate" and "high false negative rate" of breast ultrasound or mammography.

**Background:** Acute pancreatitis (AP) is a common gastrointestinal emergency with a subset of patients progressing to severe acute pancreatitis (SAP), which carries substantial morbidity and mortality. Current clinical severity scores such as BISAP, APACHE II, Ranson, and the Modified CT Severity Index require upon 48 hours of observation before reliable assessment is possible, limiting early triage. Machine learning (ML) approaches using routine admission laboratory values may enable earlier, more accurate prediction. **Methods:** We evaluated 11 models spanning three architectural families classical ML (Logistic Regression, Random Forest, Gradient Boosting), feedforward deep learning (MLP, Residual MLP, Attention MLP), and recurrent deep learning (LSTM, Stacked LSTM, Bidirectional LSTM, LSTM+Attention, CNN-LSTM) on a Chinese AP cohort of 722 patients (585 severe, 137 mild) labelled according to the 2012 Revised Atlanta Classification. Performance was assessed via 5-fold stratified cross-validation using AUC-ROC, F1 score, sensitivity, specificity, and PPV, with decision thresholds optimised for maximal F1. **Results:** Random Forest achieved the highest AUC of 0.877 (F1=0.917, sensitivity=96.8%, PPV=87.1%), followed closely by Gradient Boosting (AUC=0.874, F1=0.918). Classical ML models consistently outperformed deep learning counterparts. CNN-LSTM was the best recurrent model (AUC=0.777) but remained inferior to all classical approaches. LSTM-family models produced AUC values of 0.684-0.777, reflecting the cross-sectional tabular nature of the data. **Conclusions:** Random Forest provides robust, high-sensitivity early prediction of SAP severity using routine admission data. External prospective validation is required before clinical deployment. **Keywords:** acute pancreatitis; severity prediction; machine learning; random forest; deep learning; LSTM; Revised Atlanta Classification; early triage

IntroductionLow-dose computed tomography (LDCT) lung cancer screening has significantly enhanced early detection and patient survival rates in the population at risk. Current screening methods, that primarily rely on LDCT imaging, will very likely benefit from molecular biomarkers to achieve a more comprehensive, accurate, personalized and non-invasive risk assessment leveraging multimodal tools. We present a novel open access multimodal (imaging, proteomics and demographic) dataset designed to provide an available research resource on LDCT-based early lung cancer detection. The dataset includes annotated screening LDCT scans and plasma proteomics generated by proximity extension assay (Olink) platform. MethodsThe dataset integrates data from control screened individuals without nodules or with benign nodules, and LDCT-diagnosed lung cancer individuals, matched by sex, age and time between image and sample collection. Both radiological and molecular signatures were collected within a six month window, providing detailed insights into disease progression. Nodules were considered as lung cancer cases if biopsy-confirmed lung cancer was diagnosed within 5 years after imaging, enabling the study of longitudinal biomarker evolution and its correlation with imaging findings. To complement the dataset, clinical and demographic data are also available in open access, providing a detailed overview of patient characteristics. The informed consent signed by the participants allows for unrestricted open access for requests directy or indirectly related to lung cancer research. ResultsThe dataset consists of annotated screening LDCT scans and plasma proteomics data measured with most of the Olink Target 96 platforms (1078 individual proteins across 12 panels focused on a specific area of disease or biology) for a total of 211 screening participants. There are 67 lung cancer patients, 68 matched controls with benign pulmonary nodules, 71 matched controls without nodules and 5 surgically excised false positive lesions. Experiments were performed to assess the technical quality and provide a proof-of-concept of usability of the dataset, showing the alignment with findings from previous published studies. ConclusionThis comprehensive dataset aims to facilitate research towards the development of personalized multimodal artificial intelligence models. We also aim to support the investigation of the relationship between imaging and molecular data, paving the way for more accurate understanding of early lung cancer biology. Finally, our open access dataset may help to develop or validate individualized risk prediction models that could significantly advance early lung cancer detection and intervention strategies.