Significant Diagnostic Performance Research Articles

Small-sample fault diagnosis study of rolling bearings based on a residual parameterised convolutional capsule network

Although intelligent fault diagnosis has achieved good results, the application in practical engineering scenarios is still unsatisfactory due to the lack of sufficient fault signals to support the training of the diagnosis methods and the difficulty of extracting sensitive fault features from the original signals. To address the problem that small-sample fault data limit the diagnostic performance of traditional neural networks, a multi-scale residual parametric convolutional capsule network (MRCCCN) for small-sample bearing fault diagnosis is proposed. In the MRCCCN, the input fault information is averaged and segmented multiple times and then the initial features of the multi-segmented input are extracted by residual parameterised convolution. Then, the multi-branch features are fused and fed into an improved parametric capsule network to further extract fault features and store feature information using dynamic routing. The performance of the MRCCCN is validated using the Case Western Reserve University (CWRU) rolling bearing dataset and the Paderborn University rolling bearing dataset of vibration signals and compared with some advanced deep learning methods. The comparison results show that the proposed MRCCCN is able to accurately diagnose faults under small-sample conditions and still has significant diagnostic performance in small-sample variable noise tests.

Enhancing the fairness of AI prediction models by Quasi-Pareto improvement among heterogeneous thyroid nodule population

Artificial Intelligence (AI) models for medical diagnosis often face challenges of generalizability and fairness. We highlighted the algorithmic unfairness in a large thyroid ultrasound dataset with significant diagnostic performance disparities across subgroups linked causally to sample size imbalances. To address this, we introduced the Quasi-Pareto Improvement (QPI) approach and a deep learning implementation (QP-Net) combining multi-task learning and domain adaptation to improve model performance among disadvantaged subgroups without compromising overall population performance. On the thyroid ultrasound dataset, our method significantly mitigated the area under curve (AUC) disparity for three less-prevalent subgroups by 0.213, 0.112, and 0.173 while maintaining the AUC for dominant subgroups; we also further confirmed the generalizability of our approach on two public datasets: the ISIC2019 skin disease dataset and the CheXpert chest radiograph dataset. Here we show the QPI approach to be widely applicable in promoting AI for equitable healthcare outcomes.

Can triglyceride related indices be reliable markers in the assessment of polycystic ovarian syndrome?

Abstract Objectives This study aimed to evaluate the diagnostic utility of the Triglyceride Glucose (TyG), Triglyceride Glucose–Body Mass (TyG-BMI), and Lipid Accumulation Product (LAP) indices for both screening Polycystic Ovary Syndrome (PCOS) and diagnosing insulin resistance (IR) in women diagnosed with PCOS. Methods Retrospective data from medical records of 124 women were analyzed, with 71 in the PCOS group and 53 in the non-PCOS group. The PCOS diagnosis followed the 2003 Rotterdam criteria. Basic clinical and biochemical parameters were compared. The TyG index was computed using the formula ln [Triglyceride (TG) (mmol/L) × fasting plasma glukose (FPG) (mg/dL)/2]. TyG-BMI value was derived as TyG × BMI. LAP was calculated as (waist circumference (WC-58) × TG (mmol/L). IR was identified if Homeostatic Model Assessment of Insulin Resistance (HOMA-IR) was >2.7. Results TyG-BMI (AUC=0.62) and LAP indices (AUC=0.61) did not demonstrate statistically significant diagnostic performance for PCOS. Regarding IR in PCOS patients, the highest AUC was for TyG-BMI (0.84, 95 % CI: 0.73–0.93, p<0.001) with a cutoff at 116.15, showing 80 % sensitivity and 86 % specificity. LAP had an AUC of 0.86 with a cutoff of 30.21 (sensitivity 80 %, specificity 81 %), while TyG showed an AUC of 0.78 (95 % CI: 0.67–0.89, p<0.001) with a cutoff of 4.47, demonstrating a sensitivity of 70 % and specificity of 72 %. Conclusions Numerous biochemical markers have been explored for PCOS detection, however, many are expensive, not universally available, and necessitate specific test kits. TyG, TyG-BMI, and LAP indices might not serve as reliable markers for PCOS screening but could offer utility in identifying IR in Turkish women diagnosed with PCOS.

Metabolomic profiling reveals key metabolites associated with hypertension progression.

Pre-hypertension is a prevalent condition among the adult population worldwide. It is characterized by asymptomatic elevations in blood pressure beyond normal levels but not yet reaching the threshold for hypertension. If left uncontrolled, pre-hypertension can progress to hypertension, thereby increasing the risk of serious complications such as heart disease, stroke, kidney damage, and others. The precise mechanisms driving the progression of hypertension remain unknown. Thus, identifying the metabolic changes associated with this condition can provide valuable insights into potential markers or pathways implicated in the development of hypertension. In this study, we utilized untargeted metabolomics profiling, which examines over 1,000 metabolites to identify novel metabolites contributing to the progression from pre-hypertension to hypertension. Data were collected from 323 participants through Qatar Biobank. By comparing metabolic profiles between pre-hypertensive, hypertensive and normotensive individuals, six metabolites including stearidonate, hexadecadienoate, N6-carbamoylthreonyladenosine, 9 and 13-S-hydroxyoctadecadienoic acid (HODE), 2,3-dihydroxy-5-methylthio- 4-pentenoate (DMTPA), and linolenate were found to be associated with increased risk of hypertension, in both discovery and validation cohorts. Moreover, these metabolites showed a significant diagnostic performance with area under curve >0.7. These findings suggest possible biomarkers that can predict the risk of progression from pre-hypertension to hypertension. This will aid in early detection, diagnosis, and management of this disease as well as its associated complications.

Diagnostic performance of MRI for residual or recurrent hepatocellular carcinoma after locoregional treatment according to contrast agent type: a systematic review and meta‑analysis.

The ideal contrast agent for imaging patients with hepatocellular carcinoma (HCC) following locoregional therapies (LRT) remains uncertain. We conducted a meta-analysis to assess the diagnostic performance of magnetic resonance imaging with extracellular contrast agent (ECA-MRI) and hepatobiliary agent (EOB-MRI) in detecting residual or recurrence HCC following LRT. Original studies comparing the diagnostic performance of ECA-MRI and EOB-MRI were systematically identified through comprehensive searches in PubMed, EMBASE, Cochrane Library and Web of Science databases. The pooled sensitivity and specificity of ECA-MRI and EOB-MRI were calculated using a bivariate-random-effects model. Subgroup-analyses were conducted to compare the diagnostic performance of ECA-MRI and EOB-MRI according to different variables. Meta-regression analysis was employed to explore potential sources of study heterogeneity. A total of 15 eligible studies encompassing 803 patients and 1018 lesions were included. Comparative analysis revealed no significant difference between ECA-MRI and EOB-MRI in the overall pooled sensitivity (87% vs. 79%) and specificity (92% vs. 96%) for the detection of residual or recurrent HCC after LRT (P = 0.41), with comparable areas under the HSROC of 0.95 and 0.92. Subgroup analyses indicated no significant diagnostic performance differences between ECA-MRI and EOB-MRI according to study design, type of LRT, most common etiology of liver disease, baseline lesion size, time of post-treated examination and MRI field strength (All P > 0.05). ECA-MRI exhibited overall comparable diagnostic performance to EOB-MRI in assessing residual or recurrent HCC after LRT.

Quantification of Antiphospholipid Antibodies: The Importance of Using an Appropriate Methodology for Each Clinical Profile.

The presence of antiphospholipid antibodies (aPLs) is associated with antiphospholipid syndrome (APS), characterized by thrombosis and obstetric morbidity. aPLs included in APS classification criteria are lupus anticoagulant, anti-cardiolipin and anti-beta-2-glycoprotein-I of IgG or IgM isotypes. Enzyme-linked immunosorbent assay is the most used diagnostic technique to determine aPLs. Recently, new automated technologies mainly based in antigen-coated beads have been developed. The aim is to compare a fluorescence enzyme immunoassay (M1) and an antigen-coated bead assay (M2) in obstetric and thrombotic APS patients. All samples from the first 1020 patients received in the Immune Service Laboratory (Hospital 12 de Octubre) during the recruitment period, without exclusions, were analysed for aPLs. The weighted kappa for both methods in all the patients was 0.39 (0.30-0.47). Agreement increased to 0.56 (0.38-0.73) in patients with autoimmune disease. Sensitivity and specificity obtained for M1 were 17.1% and 89.3%, respectively, and 12.7% and 91.4% for M2. The sensibility and specificity of IgG isotypes were higher than the IgM ones. Regarding obstetric patients, M1 obtained significant diagnostic performance and had more sensitivity 23.75 (14.95-34.58) compared to M2 12.50 (6.16-21.79). In conclusion, clinical suspicion-based method selection for aPLs should be considered. To identify obstetric APS patients, solid phase methods remain more preferable.

The potential of piR-823 as a diagnostic biomarker in oncology: A systematic review

Background Emerging evidence has demonstrated that PIWI-interacting RNAs (piRNAs) play important roles in various physiological processes and contribute to cancer progression. Moreover, piRNAs and PIWI protein levels are associated with the prognosis and chemoresistance of various cancers. The limitations of biomarkers challenge early detection and monitoring of chemoresistance and cancer relapse. Methods To evaluate the potential of piRNA as a diagnostic biomarker in oncology, we systematically reviewed previous studies on the subject. PubMed, Embase, and Cochrane databases were searched to evaluate the diagnostic relevance of piRNAs in cancer. Eighteen studies (2,352 patients) were included. The quality of each study was evaluated with AMSTAR and QUADAS-2 tool. Results & conclusions The area under the curve (AUC) values of 26 piRNAs in patients with cancer ranged from 0.624 to 0.978, with piR-9491 showing the highest value (0.978). The sensitivity of the total of 21 piRNAs in cancer patients was between 42.86 and 100, with piR-9491 showing the highest sensitivity (100). The specificity of these 21 piRNAs ranged from 60.10 to 96.67 (with piR-018569 showing the highest specificity (96.67)). Their odds ratios were between 1.61 and 44.67, and piR-12488 showed the highest odds ratio (44.67). Generally, the piRNAs in this review showed better sensitivity and AUC values than current clinical diagnostic biomarkers, although current biomarkers appear to be more specific. Reviewed piRNAs showed better diagnostic performance than currently used clinical biomarkers. Notably, piR-823 showed a significant diagnostic performance in four types of cancer (colorectal, esophageal, gastric, and renal cell cancer). However, all 18 studies included in this review were a case-control study. So, further prospective studies are required for their validation.

Predictive Performance of Triglyceride-Glucose Index on Asymptomatic Multiple Organ Damage in Patients with Newly Diagnosed Hypertension.

Background: Insulin resistance (IR) contributes to the development of hypertension and mediated organ damage (HMOD) through various mechanisms. Objectives: The objective of the study was to assess the diagnostic performance of the triglyceride-glucose (TyG) index, a surrogate marker of IR, in predicting the presence and severity of HMOD in newly diagnosed untreated hypertensive patients from an academic training and research hospital. Methods: The study included 438 patients with newly diagnosed, untreated hypertension. The control group comprised normotensive individuals matched on a 1:1 ratio based on age, gender, body mass index, and smoking using the nearest neighbor method. The presence of HMOD was defined by renal damage (microalbuminuria > 30 mg/day or proteinuria > 150 mg/day), vascular damage (carotid intima-media thickness > 0.9 mm or presence of plaque), or cardiac damage (left ventricular mass index > 95 g/m2 in women and > 115 g/m2 in men). The severity of HMOD was considered as single-, two-, or triple-organ damage. Results: TyG index values were higher in the hypertensive group than the normotensive group. An increased TyG index was independently associated with HMOD (OR: 1.33, p < 0.001). The TyG index exhibited gradually increasing threshold values for distinguishing patients with single-organ HMOD (> 8.8 with 77.8% sensitivity and 74.3% specificity), two-organ HMOD (> 9.1 with 77.6% sensitivity and 71.4% specificity), and triple-organ HMOD (> 9.4 with 71.5% sensitivity and 87.7% specificity). Conclusions: In newly diagnosed hypertensive patients, the TyG index exhibits significant diagnostic performance in predicting multiple-organ damage beyond the presence of HMOD. Since the detection of multiple-organ HMOD requires a multidisciplinary approach, the TyG index can serve as a simple and inexpensive screening tool. (REV INVEST CLIN. 2023;75(5):221-32).

FTO, PIK3CB serve as potential markers to complement CEA and CA15-3 for the diagnosis of breast cancer.

The diagnostic efficacy of carcinoembryonic antigen (CEA) and carbohydrate antigen 15-3 (CA15-3) is limited in breast cancer (BC), highlighting the necessity of exploring novel biomarkers to improve for BC diagnosis. Therefore, we assessed the diagnostic value of fat mass and obesity-associated protein (FTO), phosphatidylinositol-4,5-biphosphate 3-kinase catalytic subunit β (PIK3CB) as a potential complementary biomarker to CEA and CA153 in breast cancer by measuring serum FTO,PIK3CB levels. FTO, PIK3CB, CEA and CA15-3 levels were measured in 112 BC patients and 64 healthy controls using enzyme-linked immunosorbent assay or electrochemiluminescence immunoassay. Spearman's rank correlation analysis was conducted to assess the correlation between the levels of the 2 markers. The relationships between FTO, PIK3CB, CEA, CA15-3 and clinical characteristics were evaluated. Receiver operating characteristic curve (ROC) analysis was performed to assess the diagnostic value of FTO, PIK3CB, CEA and CA15-3 of BC. Serum FTO, PIK3CB, CEA and CA15-3 levels were significantly increased in BC. There was no correlation between FTO, PIK3CB and CEA, CA15-3. FTO and PIK3CB demonstrated significant diagnostic performance for breast cancer, with FTO achieving a specificity of 90.63%. The diagnostic performance of 2-four biomarker combinations was significantly superior to individual CEA or CA153, with a combined panel of 4 biomarkers yielding an area under the curve (AUC) of 0.918, sensitivity of 81.25% and specificity of 85.94%. In early-stage breast cancer (I + II), the combination of FTO, PIK3CB, CEA and CA153 yielded an AUC of 0.895, sensitivity of 77.22% and specificity of 85.71%. FTO and PIK3CB can be served as potential biomarkers to complement CEA and CA15-3 for BC diagnosis. Combining FTO, PIK3CB, CEA and CA15-3 improves the diagnostic efficiency of breast cancer.

Amphiregulin as a Novel Biomarker in Diagnosis of Hepatocellular Carcinoma before and after Treatment

Abstract Background Hepatocellular carcinoma is the fifth most common tumour worldwide and the second most common cause of cancer-related death with a male-to-female predominance greater than 2:1. Our study depended on assessment of the diagnostic performance of serum AREG in HCC detection in addition to their correlation with different clinicopathological parameters in HCC and cirrhotic patients. Aim of the Work The aim of this work is to evaluate the diagnostic value of serum level of Amphiregulin for HCC and its prognostic value after transarterial chemo-embolization (TACE) or radiofrequency ablation (RFA). Patients and Methods The study included 60 subjects divided into two groups: group I was 30 randomly patients with liver cirrhosis as a control, group II was 30 patients with hepatocellular carcinoma who underwent intervention with TACE or RF. Results Serum AREG levels was significantly higher between HCC group and liver cirrhosis group and it is suitable for diagnostic use. It was shown that the follow up level of AREG had a significant diagnostic performance in diagnosis of HCC recurrence at cut off value of ≥ 29.7 with sensitivity of 60% and specificity was 96%. Conclusion AREG is not suitable as a diagnostic marker for HCC but can be used as a prognostic marker for HCC after treatment, as it was found to be useful in prediction of possible tumour recurrence.

Assessment of Right Lobe Size/Serum Albumin Ratio as a Non-Invasive Marker for Esophageal Varices in HCV Patients

Abstract Background Viral hepatitis was estimated to be the 7th leading cause of mortality globally. HCVassociated disease is one of the leading causes of HCC and the main indications for liver transplantation. Approximately 71 million people are chronically infected worldwide, with a total global HCV prevalence estimated at 2.5%. Egypt has the highest world prevalence of hepatitis C virus (HCV) infection, which is associated with substantial disease and economic burden. Chronic HCV infection can result in hepatic fibrosis, cirrhosis, HCC and death. One of the major complications of cirrhosis is gastroesophageal varices, the incidence of which ranges from 35% to 80%). Current guidelines recommend that all cirrhotic patients should undergo screening endoscopy at diagnosis to identify patients with varices at high risk of bleeding who will benefit from primary prophylaxis. Noninvasive identification of patients at highest risk for esophageal varices would limit investigation to those most likely to benefit. Aim of the Work The aim of our study is to determine the predictive value of noninvasive parameters (Rt. lobe diameter/ serum albumin ratio) in the prediction of esophageal varices. Patients and Methods It is a cross-sectional study carried on 100 patients collected from the Hepatology outpatient clinics and from Hepatology and Gastroenterology unit, Internal medicine department at Ain Shams University Hospital over 6-month period, with inclusion and exclusion criteria aiming at the elimination of other factors that might affect the study results. All patients were divided into 3 groups: 30 patients with Child-Pugh A, 30 patients with Child-Pugh B, and 40 patients with Child-Pugh C. patients were subjected to the following: Clinical assessment: including; Full medical history and clinical examination, laboratory investigations: (AST, ALT, Bilirubin, Albumin, INR, Alpha feto-protein, CBC), abdominal ultrasonography and doppler ultrasonography: performed after overnight fasting and the patient in supine position with emphasis on the liver right lobe diameter (cm), splenic bi-polar diameter (long axis) (cm), ascites, presence of periportal thickening, portal vein diameter (mm) and patency, upper GI endoscopy. Results Our study showed that regarding platelet count, INR, serum albumin, Liver size, liver size / serum albumin ratio there was a significant difference among esophageal varices grades. Liver size / serum albumin ratio had non-significant diagnostic performance in differentiating esophageal varices grade-I from grade-0, had significant moderate diagnostic performance in differentiating other esophageal varices grades from each other. Liver size / serum albumin ratio cutoff points had high specificity &amp; PPV but low sensitivity&amp; NPV in differentiating grade-I from grade-0, had high sensitivity&amp; NPV but moderate specificity &amp; PPV in differentiating other grades from each other. Conclusion Our study showed that there was significant moderate agreement between endoscopy and liver size / serum albumin ratio regarding esophageal varices grades. Our study stresses on the use of some of the non-invasive parameters in predicting the grade of esophageal varices in cirrhotic patients without submitting them to the invasive, time consuming and expensive procedure of endoscopy.

The Reliability of Ultrasound in Diagnosis of Idiopathic Pulmonary Fibrosis

Abstract Background Idiopathic pulmonary fibrosis (IPF) is defined as a specific form of chronic, progressive fibrosing interstitial pneumonia of unknown cause. IPF is the most common and severe form of idiopathic interstitial pneumonia, with an unpredictable and variable clinical course, and is associated with an extremely poor prognosis. Objective To determine role of Ultrasound in diagnosis of idiopathic pulmonary fibrosis. Patients and Methods This cross-sectional study was conducted at tertiary care hospital at Ain Shams University hospitals from May 2021 till November 2021 and performed on total 60 patients diagnosed with idiopathic pulmonary fibrosis and had previous clinical features, documented high-resolution computed tomography (HRCT) scan findings and comparing it with lung ultrasound findings. Results Consequently, B-lines number and Pleural lines thickness statistically had significant high diagnostic performance in the diagnosis of IPF with cut-off of ≥ 3.0 which indicates that B-lines number ≥3.0 and Pleural lines thickness ≥3.0 mm had perfect sensitivity and LR+, while Pleural lines interruption had perfect specificity. B-lines number ≥3.0 had highest diagnostic accuracy, Youden’s index and kappa. Our research study revealed that B-lines number and Pleural lines thickness statistically were significantly higher in multiple zones spread cases (p value&amp;lt;0.001). Pleural lines interruption statistically was significantly more frequent in multiple zones spread cases. Conclusion As evident from the current study, this study introduced and thoroughly evaluated lung US features, which showed a high correlation with the high-resolution CT findings. Chest ultrasound could constitute an additional monitoring tool for IPF, which is a rapidly progressive disease, usable by the pulmonologist at the patient’s bedside or during a consultation, easily available, non-irradiating, achievable in a short time and immediately informative, for a trained sonographer.

Pre-Operative Evaluation of Color Doppler Ultrasonography to Predict Malignancy in Ovarian Masses at Ain-Shams University

Background Ovarian cancer is the second most common gynecologic malignancy in developed countries and the third most common gynecologic malignancy in developing countries. This cancer is characterized by high malignancy, difficult early detection, low survival rate, and high fatality rate. Transvaginal ultrasonography is the first choice for imaging to differentiate between a benign and a malignant adnexal mass. Aim of the Work The aim of the study is to determine predictive value of pre-operative resistance index (RI) of color Doppler of ovarian vessels in identifying potential ovarian malignancy at Ain Shams maternity hospital between May 2015 and May 2020. Methods this retrospective observational study, was done on total 379 patients who underwent laparotomy for adnexal masses at Ain Shams University hospitals over five years period between May 2015 and May 2020 with inclusion and exclusion criteria. Medical records of the study population were revised to assess demographic data, ultrasound criteria and histopathological result Results Thin wall and clear content are negatively correlated with ovarian malignancy and these correlators statistically significant. While presence of papillae and septation are positively correlated with ovarian malignancy and these findings were statistically highly significant. Masses proved to be ovarian malignancy were mostly unilateral, more than 5 cm size, thick wall, with turbid content, solid consistency, unilocular with papillae and septation. RI in our study was lower in malignant lesions ranging between (0.22–0.60) and the Mean±SD of resistance index values in the ovarian cancer (0.48±0.07). Resistance index at cut off value ≤0.54 had high specificity and negative predictive value but moderate sensitivity and positive predictive value in diagnosing ovarian malignancy. Conclusion As evident from the current study, thick wall, turbid content, solid consistency, papillae and septations were significantly most frequent in ovarian cancer. Resistance index was significantly highest in ovarian malignancy. In current study RI was lower in malignant lesions. From the results of current study we can conclude that the pre-operative resistance index (RI) of color Doppler of ovarian vessels had significant high diagnostic performance in predicting ovarian cancer. Resistance index at cut off value≤0.54 in diagnosis of ovarian cancer has sensitivity (85.2%), specificity (91.6%), accuracy (90.2%), positive predictive value (73.4%) and negative predictive value (95.8%).

Assessment of the Value of Mean Plathlet Volume, Des Gamma Carboxy Prothrombin and Alpha Feto Protein in Early Detection of HCC

Abstract Background Primary liver cancer is the sixth most commonly diagnosed cancer and the fourth leading cause of cancer mortality worldwide, with an estimated 841,000 cases (9.3 cases per 100,000 person-years) and 782,000 deaths (8.5 deaths per 100,000 person-years) in 2018. HCC being often associated with liver cirrhosis masks symptoms of cancer progression and thus the clinical course of HCC is mostly asymptomatic. Aim of the Work To determine the value of mean platelet volume, Des gamma Carboxy prothrombin and Alfa-feto protein in early detection of Hepatocelluler carcinoma Patients and Methods This case cross sectional comparative study had been carried out after the approval of the Ethics Committees of the faculty of medicine Ain Shams university on 105 subjects, age range 25-68 year selected from: Patients attending Hepatology and virology outpatient clinic at ElDemerdash hospital Also Liver transplantation center at Ain Shams specialized hospital in Cairo after informed consent were taken from the patients Results In this study HCC was found to be more prevalent in men 28 (80.0%) than in women 7 (20.0%). In our study AFP, MPV and DCP were highest in HCC group, followed by CLD group and lowest in control group. The differences between all groups were significant in MPV and DCP, with no significant difference between CLD and HCC in AFP. In the present study, DCP values of HCC group showed a highly significant increase upon comparison with the non malignant groups (II, and III). The sensitivity of DCP was higher than AFP in detecting HCC patients (97.1% versus 54.3%), Conclusion Measurement of MPV is non-invasive, cheap and quick, and may therefore serve as a predictor of HCC in patients with CLD. Low sensitivity and specificity, on the other hand, suggests that this may be an adjunctive parameter to some other markers like AFP. Further studies with larger samples are needed to determine the association of MPV with HCC. For a single test DCP had highest significant diagnostic performance in differentiating HCC from CLD groups. In detection of HCC testing AFP≥ 40.0 if positive considered positive. If negative, retest for DCP≥ 69.3 if positive considered positive, otherwise is negative. This although deceased specificity and Positive predictive value, it raised sensitivity and Negative Predictive Value to 100.0% when combining both AFP and DCP.

Assessment of the Value of Mean Platelet Volume, Des Gamma Carboxy Prothrombin and Alpha Feto Protein in Early Detection of HCC

Abstract Background Hepatocellular carcinoma (HCC) is the most common primary malignant tumor of the liver. AFP is the gold standard tumor marker for HCC, mean platelet volume (MPV) is a parameter obtained from complete blood count (CBC) by automated analyzers, shown to be increased in multiple malignancies and inflammatory conditions. This cross sectional comparative study was designed to evaluate the diagnostic usefulness of MPV as a diagnostic marker in HCC patients due to cirrhosis. Aim of the Work To determine the value of mean platelet volume, Des gamma Carboxy prothrombin and Alfa-feto protein in early detection of Hepatocelluler carcinoma Patients and Methods 105 patients were enrolled in this study, they were divided into 3 equal groups Group A: Hepatocelluler carcinoma patients (HCC) Group B: Liver cirrhosis patients Group C: Healthy Control group each is 35 patients. MPV, AFP, DCP were evaluated in all groups. Ultrasound and Triphasic CT. were also done to Group A&amp;B to confirm or exclude the diagnosis of HCC and in group C as they are candidates for LDLT donors. Results Our results showed that regarding the diagnostic performance of the three tested tumor markers (AFP, MPV and DCP) in differentiating HCC from CLD groups that AFP had area under curve (AUC) of 0.719, Standard error (SE) of 0.061, Confidence interval (CI) of 0.599-0.839 and P value of 0.002 at a cut point of ≥ 40.0, MPV had area under curve (AUC) of 0.801, Standard error (SE) of 0.063, Confidence interval (CI) of 0.678 − 0.924 and P value of &amp;lt; 0.001 at a cut point of ≥ 10.2, while DCP had area under curve (AUC) of 0.842, Standard error (SE) of 0.047, Confidence interval (CI) of 0.750 − 0.935 and P value of &amp;lt; 0.001 at a cut point of ≥ 69.3 proving that DCP had the highest significant diagnostic performance in differentiating HCC from CLD groups also DCP≥ 69.3 had highest sensitivity(of 97.1%) and NPV(of 96.3%). AFP≥ 40.0 had highest specificity (of 91.4%) and PPV (of 86.4%). Youden’s index was highest in DCP ≥69.3, followed by MPV ≥10.2 and lowest in AFP ≥40.0. MPV had moderate sensitivity and specificity in between AFP and DCP with values of 71.4% and 85.7% respectively with also moderate PPV of 83.3 and NPV of 75% Conclusion Measurement of MPV is non-invasive, cheap and quick, and may therefore serve as a predictor of HCC in patients with CLD. Low sensitivity and specificity, on the other hand, suggests that this may be an adjunctive parameter to some other markers like AFP. Further studies with larger samples are needed to determine the association of MPV with HCC. For a single test DCP had highest significant diagnostic performance in differentiating HCC from CLD groups. In detection of HCC testing AFP≥ 40.0 if positive considered positive. If negative, retest for DCP≥ 69.3 if positive considered positive, otherwise is negative. This although deceased specificity and Positive predictive value, it raised sensitivity and Negative Predictive Value to 100.0% when combining both AFP and DCP. The benefit of increasing the sensitivity is not to miss cases with HCC while the decreased specificity and PPV can be compensated by further imaging studies to eliminate the false positive cases.

Urinary neutrophil gelatinase-associated lipocalin (uNGAL) and kidney injury molecule-1 (uKIM-1) as markers of active lupus nephritis

Background and objectivesDespite much research about lupus nephritis, none of the urinary biomarkers has been proven to be truly reflecting lupus nephritis activity, response to treatment, or prognosis. We aimed to study urinary biomarkers in lupus nephritis and test their relation to kidney damage.Patients and methodsForty patients with systemic lupus erythematosus (SLE) were divided into two graoups: (1) lupus nephritis group with biopsy-proven proliferative lupus nephritis (classes III and IV) and who did not receive immunosuppressive drugs within the preceding 3 months except for glucocorticoids and (2) lupus non-nephritis group with SLE patients without any renal manifestation. We assessed disease activity by the SLE disease activity index. uNGAL, uKim-1, uNGAL to urinary creatinine excretion (mg/dl), and uKim-1 to urinary creatinine excretion were measured in random spot urine samples at the time of renal biopsy and 6 months after the induction therapy.ResultsThe LN group before treatment showed higher levels of uNGAL and uKIM-1 (P-value < 0.001). ROC analysis showed that uNGAL at level of > 59 has a 95 % sensitivity, a 100 % specificity, and an AUC = 0.996 in the ability to diagnose LN. While the uKIM-1 ROC showed that at level of > 1.6, it has an 85 % sensitivity, an 80 % specificity, and an AUC = 0.919. uNGAL and uKIM levels were significantly lower after treatment (P-value < 0.001). No significant correlations were found between urinary markers before and after treatment with other clinical, inflammatory, and serological markers of lupus nephritis.ConclusionuNGAL, uKIM, uNGAL/Creat ratio, and uKIM/Creat ratio can be used as a predictor and a marker of disease activity for lupus nephritis.Key Points• Renal biopsy is the current standard for diagnosis of lupus nephritis and none of the urinary biomarkers has been fully concluded to have a diagnostic power to reflect the activity or the response to treatment.• However, based on the finding of the current study, uNGAL, uKIM, uNGAL/Creat ratio, and uKIM/Creat ratio showed significant diagnostic performance and were powerful indices of renal involvement in systemic lupus patients and as markers of disease activity.

Circulating miR-26b-5p and miR-451a as diagnostic biomarkers in medullary thyroid carcinoma patients

Purpose/methodsThe determination of tumour biomarkers is paramount to advancing personalized medicine, more so in rare tumours like medullary thyroid carcinoma (MTC), whose diagnosis is still challenging. The aim of this study was to identify non-invasive circulating biomarkers in MTC. To achieve this goal, paired MTC tissue and plasma extracellular vesicle samples were collected from multiple centres and microRNA (miRNA) expression levels were evaluated.ResultsThe samples from a discovery cohort of 23 MTC patients were analysed using miRNA arrays. Lasso logistic regression analysis resulted in the identification of a set of circulating miRNAs as diagnostic biomarkers. Among them, miR-26b-5p and miR-451a, were highly expressed and their expression decreased during follow-up in disease-free patients in the discovery cohort. Circulating miR-26b-5p and miR-451a were validated using droplet digital PCR in a second independent cohort of 12 MTC patients.ConclusionThis study allowed the identification and validation of a signature of two circulating miRNAs, miR-26b-5p and miR-451a, in two independent cohorts reporting a significant diagnostic performance for MTC. The results of this study offer advancements in molecular diagnosis of MTC proposing a novel non-invasive tool to use in precision medicine.

Circulating miRNA-192 and miR-29a as Disease Progression Biomarkers in Hepatitis C Patients with a Prevalence of HCV Genotype 3.

MicroRNAs miR-29a and miR-192 are involved in inflammatory and fibrotic processes of chronic liver disease, and circulating miR-29a is suggested to diagnose fibrosis progression due to hepatitis C virus (HCV) infection. This study aimed to evaluate the expression profile of circulating miR-192 and 29a in a patient cohort with a high frequency of HCV genotype-3. A total of 222 HCV blood samples were collected and serum were separated. Patients were classified into mild, moderate, and severe liver injury based on their Child-Turcotte-Pugh CTP score. RNA was isolated from the serum and used for quantitative real-time PCR. The HCV genotype-3 (62%) was the predominant HCV genotype. In HCV patients, the serum miR-192 and miR-29a levels were significantly upregulated in comparison to healthy controls (p = 0.0017 and p = 0.0001, respectively). The progression rate of miR-192 and 29a in the patient group with mild was highly upregulated compared to patients with moderate and severe hepatitis infection. The ROC curve of miR-192 and miR-29a of moderate liver disease had a significant diagnostic performance compared to the other HCV-infected groups. The increase in miR-29a and miR-192 serum levels was even slightly higher in patients with HCV genotype-3 than in non-genotype-3 patients. In conclusion, serum miR-192 and miR-29a levels significantly increased during the progression of chronic HCV infection. The marked upregulation in patients with HCV genotype-3 suggests them as potential biomarkers for hepatic disease, independently of the HCV genotype.

MRI-based radiomic score increased mrTRG accuracy in predicting rectal cancer response to neoadjuvant therapy.

To develop a magnetic resonance imaging (MRI)-based radiomics score, i.e., "rad-score," and to investigate the performance of rad-score alone and combined with mrTRG in predicting pathologic complete response (pCR) in patients with locally advanced rectal cancer following neoadjuvant chemoradiation therapy. This retrospective study included consecutive patients with LARC who underwent neoadjuvant chemoradiotherapy followed by surgery from between July 2011 to November 2015. Volumes of interest of the entire tumor on baseline rectal MRI and of the tumor bed on restaging rectal MRI were manually segmented on T2-weighted images. The radiologist also provided the ymrTRG score on the restaging MRI. Radiomic score (rad-score) was calculated and optimal cut-off points for both mrTRG and rad-score to predict pCR were selected using Youden's J statistic. Of 180 patients (mean age = 63years; 60% men), 33/180 (18%) achieved pCR. High rad-score (> - 1.49) yielded an area under the curve (AUC) of 0.758, comparable to ymrTRG 1-2 which yielded an AUC of 0.759. The combination of high rad-score and ymrTRG 1-2 yielded a significantly higher AUC of 0.836 compared with ymrTRG 1-2 and high rad-score alone (p < 0.001). A logistic regression model incorporating both high rad-score and mrTRG 1-2 was built to calculate adjusted odds ratios for pCR, which was 4.85 (p < 0.001). Our study demonstrates that a rectal restaging MRI-based rad-score had comparable diagnostic performance to ymrTRG. Moreover, the combined rad-score and ymrTRG model yielded a significant better diagnostic performance for predicting pCR.

Denoising Fault-Aware Wavelet Network: A Signal Processing Informed Neural Network for Fault Diagnosis

Deep learning (DL) is progressively popular as a viable alternative to traditional signal processing (SP) based methods for fault diagnosis. However, the lack of explainability makes DL-based fault diagnosis methods difficult to be trusted and understood by industrial users. In addition, the extraction of weak fault features from signals with heavy noise is imperative in industrial applications. To address these limitations, inspired by the Filterbank-Feature-Decision methodology, we propose a new Signal Processing Informed Neural Network (SPINN) framework by embedding SP knowledge into the DL model. As one of the practical implementations for SPINN, a denoising fault-aware wavelet network (DFAWNet) is developed, which consists of fused wavelet convolution (FWConv), dynamic hard thresholding (DHT), index-based soft filtering (ISF), and a classifier. Taking advantage of wavelet transform, FWConv extracts multiscale features while learning wavelet scales and selecting important wavelet bases automatically; DHT dynamically eliminates noise-related components via point-wise hard thresholding; inspired by index-based filtering, ISF optimizes and selects optimal filters for diagnostic feature extraction. It's worth noting that SPINN may be readily applied to different deep learning networks by simply adding filterbank and feature modules in front. Experiments results demonstrate a significant diagnostic performance improvement over other explainable or denoising deep learning networks. The corresponding code is available at https://github.com/albertszg/DFAWnet.