High False Positive Results Research Articles

Resistant inflammatory breast lesions: can AI exclude malignancy?

BackgroundNumerous underlying causes can lead to inflammatory breast disorders. A wide range of non-specific symptoms may be presenting symptoms, which could cause a delay in diagnosis and thus improper therapy. Studies on artificial intelligence (AI) are rapidly developing and offer a wide range of possible uses in breast imaging. Artificial intelligence-based computer-assisted diagnosis (AI-CAD) holds promise in the field of mammography. It demonstrated diagnostic performances that are equivalent to or even better than those achieved by stand-alone methods. The current work aimed to identify whether AI can improve the performance of mammography in diagnosing inflammatory breast diseases and excluding the underlying malignancy in cases resistant to treatment that may reduce the need for interventional procedures such as biopsy. MethodsOur study was a retrograde one done on 34 patients with pathologically proven inflammatory breast lesions.ResultsSuppurative breast lesions gave high false positive results. This was also the case with granulomatous mastitis; while simple inflammatory lesions gave true negative results on AI interrogation.ConclusionsArtificial intelligence can be of great value in diagnosing simple inflammatory breast lesions thus following up on such lesions can usually be sufficient without asking for unneeded biopsies. On the other hand, our study showed that AI had high false positive results in suppurative lesions and granulomatous mastitis. Consequently, ultrasonography can be more reliable in their diagnosis.

Optimized deep learning-based dual segmentation framework for diagnosing health of apple farming with the internet of things

<div align="left"><p>The high disease prevalence in apple farms results in decreased yield and income. This research addresses these issues by integrating internet of things (IoT) applications and deep neural networks to automate disease detection. Existing methods often suffer from high false positives and lack global image similarity. This study proposes a conceptual framework using IoT visual sensors to mitigate apple diseases' severity and presents an intelligent disease detection system. The system employs the augmented Otsu technique for region-aware segmentation and a colour-conversion algorithm for generating feature maps. These maps are input into U-net models, optimized using a genetic algorithm, which results in the generation of suitable masks for all input leaf images. The obtained masks are then used as feature maps to train the convolution neural network (CNN) model for detecting and classifying leaf diseases. Experimental outcomes and comparative assessments demonstrate the proposed scheme's practical utility, yielding high accuracy and low false-positive results in multiclass disease detection tasks.</p></div>

Vulnerable JavaScript functions detection using stacking of convolutional neural networks.

System security for web-based applications is paramount, and for the avoidance of possible cyberattacks it is important to detect vulnerable JavaScript functions. Developers and security analysts have long relied upon static analysis to investigate vulnerabilities and faults within programs. Static analysis tools are used for analyzing a program's source code and identifying sections of code that need to be further examined by a human analyst. This article suggests a new approach for identifying vulnerable code in JavaScript programs by using ensemble of convolutional neural networks (CNNs) models. These models use vulnerable information and code features to detect related vulnerable code. For identifying different vulnerabilities in JavaScript functions, an approach has been tested which involves the stacking of CNNs with misbalancing, random under sampler, and random over sampler. Our approach uses these CNNs to detect vulnerable code and improve upon current techniques' limitations. Previous research has introduced several approaches to identify vulnerable code in JavaScript programs, but often have their own limitations such as low accuracy rates and high false-positive or false-negative results. Our approach addresses this by using the power of convolutional neural networks and is proven to be highly effective in the detection of vulnerable functions that could be used by cybercriminals. The stacked CNN approach has an approximately 98% accuracy, proving its robustness and usability in real-world scenarios. To evaluate its efficacy, the proposed method is trained using publicly available JavaScript blocks, and the results are assessed using various performance metrics. The research offers a valuable insight into better ways to protect web-based applications and systems from potential threats, leading to a safer online environment for all.

Identifying and eliminating false positives in thermal-assisted photocatalysis.

We discovered that employing inappropriate calibration curves for activity evaluation resulted in false positive results. Specifically, an artificial efficiency of hydrogen production is exaggerated by up to 2.2-fold if the calibration curves are misused, leading to considerably high false positive results. Our study highlights the importance of utilizing the correct calibration curve to ensure a true performance, and is beneficial for fostering advancements in the development of thermal-assisted photocatalysis.

Label-free fluorescence detection of human 8-oxoguanine DNA glycosylase activity amplified by target-induced rolling circle amplification

BackgroundHuman 8-oxoG DNA glycosylase 1 (hOGG1) is one of the important members of DNA glycosylase for Base excision repair (BER), the abnormal activity of which can lead to the failure of BER and the appearance of various diseases, such as breast cancer, bladder cancer, Parkinson's disease and lung cancer. Therefore, it is important to detect the activity of hOGG1. However, traditional detection methods suffer from time consuming, complicated operation, high false positive results and low sensitivity. Thus, it remains a challenge to develop simple and sensitive hOGG1 analysis strategies to facilitate early diagnosis and treatment of the relative disease. ResultsA target-induced rolling circle amplification (TIRCA) strategy for label-free fluorescence detection of hOGG1 activity was proposed with high sensitivity and specificity. The TIRCA strategy was constructed by a hairpin probe (HP) containing 8-oxoG site and a primer probe (PP). In the presence of hOGG1, the HP transformed into dumbbell DNA probe (DDP) after the 8-oxoG site of which was removed. Then the DDP formed closed circular dumbbell probe (CCDP) by ligase. CCDP could be used as amplification template of RCA to trigger RCA. The RCA products containing repeated G4 sequences could combine with ThT to produce enhanced fluorescence, achieving label-free fluorescence sensing of hOGG1. Given the high amplification efficiency of RCA and the high fluorescence quantum yield of the G4/ThT, the proposed TIRCA achieved highly sensitive measurement of hOGG1 activity with a detection limit of 0.00143 U/mL. The TIRCA strategy also exhibited excellent specificity for hOGG1 analysis over other interference enzymes. SignificanceThis novel TIRCA strategy demonstrates high sensitivity and high specificity for the detection of hOGG1, which has also been successfully used for the screening of inhibitors and the analysis of hOGG1 in real samples. We believe that this TIRCA strategy provides new insight into the use of the isothermal nucleic acid amplification as a useful tool for hOGG1 detection and will play an important role in disease early diagnosis and treatment.

The Optimization of the ARP Poisoning Attack Detection Model Using a Similar Approach Based on NetFlow Analysis

Information security and threats are a concern in the cyber era. Attacks can be malicious activities. One of them is known as ARP poisoning attack activity, which attacks by falsifying a computer's identity through illegal access to retrieve confidential information in a target computer. Besides, it has also caused service deadlocks in the network. Previous studies have been introduced for the ARP Attack Detection model using rule-based and mining-based. Still, they cannot show optimal detection performance and obtain high false positive results. This paper proposed a detection model for ARP poisoning attacks using a similarity measurement approach adopting cosine similarity. The goal is to obtain measurements of host activities similar to ARP poisoning attacks. The experiment results showed that the model got an accuracy of 97.25%, recall of 96.43%, and precision of 81% with a similarity threshold value of 0.488. Comparison results with previous studies showed higher detection accuracy than previous studies and some classification methods. It shows that the model can improve intrusion detection performance and facilitate network administrators to analyze ARP poisoning attacks in computer networks.

A Privacy-Preserving Hybrid Range Search Scheme Over Encrypted Electronic Medical Data in IoT Systems

Electronic wearable devices play an important role in the Internet of Things (IoT) systems for collecting medical data. Searching over such numerical medical data help to provide better service and treatment. However, user and data security is a major barrier to public adoption. Existing approaches designed to facilitate secure (range) searches over encrypted data generally incur expensive computational overhead, suffer from unexpected information leakage, and/or have high false-positive results. Therefore, in this paper, we design a hybrid searchable encryption scheme that supports efficient, secure, and accurate range searches over encrypted data sensed and collected from medical IoT devices. The designed graph structure helps to filter out most of the false data, and the batching processing on ciphertexts accelerates the removal of irrelevant data. Unlike most prior works, the proposed random index hides the distribution of data, and the probabilistic fixed-length trapdoor hides the range size and repetition of the query. If necessary, all the encrypted data can be refreshed by the cloud server after a range search. The scheme is proven to be secure in a simulation-based model. Then, we evaluate the performance of our proposed scheme on Microsoft Azure cloud servers and Azure IoT Central. The comparisons with several prior works demonstrate that our scheme supports more efficient secure range searches.

Abstract 3333: Exosomal non-coding RNAs as a biomarker to improve early ovarian cancer detection

Abstract Purpose: There is no consensus on screening for ovarian cancer in high-risk women because no effective biomarker or screening method exists, especially for early-stage cancer patients. The available methods, such as monitoring of CA125 levels, transvaginal ultrasound, and combination of pelvic examination are associated with high false-positive results, leading to additional unnecessary imaging tests, emotional burdens, and risk of invasive surgery for women without cancer. An effective, reliable, and non-invasive method for early detection of ovarian cancer is thus critically needed. In this research, weThus, we aim to identify a distinctive signature of exosomal small RNAs to serve as a novel biomarker for detecting early-stage ovarian cancer in high-risk population. Methods: Women of all ages and ethnical backgrounds were included in this study. Blood samples were collected in the clinic from women with germline BRCA mutations. A total of 30 patients with ovarian cancer before surgery, and 30 age-matched (mean age = 55) healthy women as controls were used. Among the 30 thirty cases, 11 patients had early (stage I) ovarian cancer. Identification of differential exosome small non-coding RNA copy numbers in plasma samples from BRCA1 mutation carriers with and without ovarian cancer was performed by next-generation RNA-Sseq. We randomly split 60 samples into two groups: training set (20 cancer, 20 normal) and , testing set (10 cancer, 10 normal). We apply 10-fold cross-validation to determine hyperparameter of five machine learning models and use the ensemble learning method to evaluate the predictive value of the small RNAs in the exosome by integrating the five machine learning models. Results: The ensemble learning model achieved the testing accuracy of 85% with the sensitivity of 70% and the specificity of 100% by using small RNA and CA125 abundance level as input features. While uUsing CA125 alone, the testing accuracy equals to 90% with the sensitivity of 80% and the specificity of 100%. For the 11 eleven early-stage patient samples, our ensemble learning model made 2 false negative predictions with a total accuracy of 95.1% (sensitivity=81.8%, specificity=100%) while using CA125 alone had five 5 false negative predictions with a total accuracy of 87.8% (sensitivity=54.5%, specificity=100%). All 30 control samples had been correctly classified. Conclusions: We found that ensemble learning model using combining both exosome small RNAs and CA125 will not improve the prediction accuracy for late-stage cancer patients compared to CA125 alone but will significantly improve the prediction accuracy for early-stage patients. Our research findings may indicate a two-pronged strategy in assessing ovarian cancer risks using existing CA125 test followed by small RNA features to detect early-stage ovarian cancer. We are now collecting a larger number of early-stage cancer patient samples for validation. Citation Format: Yuliang Cao, Cun Han, Jianting Sheng, Samuel Mok, Stephen T.C. Wong. Exosomal non-coding RNAs as a biomarker to improve early ovarian cancer detection [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2023; Part 1 (Regular and Invited Abstracts); 2023 Apr 14-19; Orlando, FL. Philadelphia (PA): AACR; Cancer Res 2023;83(7_Suppl):Abstract nr 3333.

High-risk HPV testing vs liquid-based cytology for cervical cancer screening among 25- to 30-year-old women: A historical cohort study.

High-risk human papilloma virus (hrHPV) DNA testing is more sensitive than cytology screening, achieving greater protection against cervical cancer. Controversy exists regarding the preferred screening method for women 25-30 years of age. At this age, infection with HPV is common and usually transient. Consequently, hrHPV screening in this age group is fraught with high false-positive screening results, leading to more colposcopies and unnecessary treatments with the potential for harm. In the present study, we aimed to compare the results of two screening methods in relation to high-grade cervical intraepithelial lesion detection rate in the young age group of 25-30 years. Retrospective information on cervical cytology, hrHPV testing, colposcopy referrals and histologic results, from one screening round, were retrieved from the Maccabi HealthCare Health Maintenance Organization centralized database during the study period from March 1, 2017 to April 1, 2019 for 25- to 30-year-old women. Screening with hrHPV testing for types 16, 18 and 12 other hrHPV types was compared with the conventional PAP liquid-based cytology (LBC) test. Odds ratio (OR) of detection with 95% confidence interval (CI) was calculated for cervical intraepithelial neoplasia (CIN) grade 3 or higher (CIN 3+). During the study period, 42 244 women 25-30 years old underwent cervical cancer screening; of them, 20 997 were screened with LBC between March 1, 2017 and March 1, 2018 and compared with 21 247 who were screened with hrHPV between April 1, 2018 and April 1, 2019. Testing for hrHPV resulted in a higher colposcopy referral rate compared with primary LBC screening: 9.8% vs 7.8%, respectively; (OR 1.28; 95% CI 1.2-1.37; p< 0.001). Screening with hrHPV led to significantly higher detection of CIN 3+ lesions (OR 1.4; 95% CI 1.2-1.6; p< 0.001) compared with LBC. HPV infections with non-16/18 hrHPV (other hrHPV) were the most prevalent (84.8%). In women 25-30 years old, primary hrHPV screening was associated with a higher detection rate of CIN 3+ compared with cytology screening and should be considered for primary screening in this age group.

Performance of diagnostic assays used to detect Cryptosporidium oocysts in faecal samples of cattle in Kuwait and genotyping of Cryptosporidium species

BackgroudCryptosporidium species are zoonotic protozoan parasites responsible for gastroenteritis in various animals and humans. The diagnosis of Cryptosporidium presents many challenges. This research attempted to match the diagnostic efficiency of the modified Ziehl–Neelsen technique (mZN), immunochromatographic assays (IC), and enzyme-linked immunosorbent assay (ELISA) for the detection of Cryptosporidium in faecal samples of cattle in Kuwait. In addition, polymerase chain reaction (PCR) was utilised to determine the predominant species infecting cattle in Kuwait and correlating the detected species with the results of different diagnostic tests used, the presence or absence of clinical signs, and the age group of the infected cattle.ResultsOf 400 analysed faecal samples, Cryptosporidium positive samples were 23%, 15.25%, and 14% using IC, ELISA, and mZN. IC had the highest sensitivity (74.07%), and mZN had the highest specificity (98.29%) using a composite reference standard (CRS) as a gold standard. The rapid IC test results in high false-positive results of cryptosporidiosis, whereas using mZN alone is insufficient to declare a negative faecal sample. Only 74.5% (35/47) of Cryptosporidium-positive samples by the three assays could be amplified by PCR. This study was the first to genotype Cryptosporidium in Kuwait. Cryptosporidium parvum (n = 26) was the dominant species detected from cattle samples, followed by C. andersoni (n = 6), C. bovis (n = 2), and C. raynae (n = 1). The findings showed a statistically relevant relationship between diarrhoea and the detection of Cryptosporidium spp. in faecal samples of cattle (p-value = 0.0003). Pre-weaned calves were the most vulnerable age group to Cryptosporidium spp. infection (p-value = 0.0007).ConclusionFor screening of Cryptosporidium infection in faecal samples, antigen detection or PCR methods combined with one of the microscopy techniques should be used. Cryptosporidium parvum was the prepoderant Cryptosporidium spp. recovered from cattle samples in Kuwait followed by C. andersoni. Cryptosporidium parvum is a significant risk factor for diarrhoea in pre-weaned calves. However, further study is needed as many other causes of diarrhoea in calves must be ruled out before a diagnosis of Cryptosporidium diarrhoea can be made.

MIDDLE CEREBRAL ARTERY AND UMBILICAL ARTERY DOPPLER STUDIES TO PREDICT OUTCOME OF PREGNANCIES.

In about 30% of post term pregnancies, the foetuses develop a post maturity syndrome. post term pregnancy is associated with increased risk of both intrauterine and postnatal death. Nowadays, Doppler ultrasound velocimetry of uteroplacental umbilical and fetal vessels has become established method of antenatal monitoring, allowing noninvasive assessment of fetal circulation. Circulatory changes, reected in certain fetal Doppler waveforms, predict adverse perinatal outcome. Umbilical arteries are the common vessels assessed by Doppler ultrasound, but recent studies conrm the efcacy of middle cerebral artery (MCA) Doppler assessment for detecting fetal compromise. Objective- To predict outcome of pregnancies by using umbilical artery and Middle cerebral artery doppler ndings. Methodology- Study group consists of 65 pregnant women with gestational age of 40-42 weeks and control groups include the same number of pregnant women with gestational age of 36-40 weeks. All the antenatal women in the subject &amp; control groups were examined by routine ultrasound scan and Doppler subsequently.The peak systolic, end diastolic, and mean velocity were recorded from these vessels, and Umbilical artery S/D ratio, PI and Middle Cerebral Artery PI and CPR were calculated.Comparison of all variables were done using by·a software package Sensitivity, Specicity, Positive predictive value, Negative predictive value of different arterial Doppler indices and cerebroplacental ratio (CPR) were evaluated. ResultNo statistical signicant difference was noted in UA S/D, UAPI, UARI, MCA S/D, MCAPI MCARI in pregnancy with normal and adverse perinatal outcome. Only CPR showed signicant difference for predicting adverse perinatal outcome (p=0.001). Conclusion- None of the Doppler indices except CPR is sensitive enough. Although CPR cut-off value of 1.335 assures the obstetrician of fetal wellbeing, it's low specicity and high false positive results lead to unnecessary tests, undue concern and unnecessary interference.

Diagnostic Performance of 99mTc-Methoxy-Isobuty-Isonitrile (MIBI) for Risk Stratification of Hypofunctioning Thyroid Nodules: A European Multicenter Study.

99mTc-MIBI (MIBI) imaging is able to exclude malignancy of hypofunctioning thyroid nodules (TNs) with high probability but false positive results are frequent due to low specificity. Therefore, pre-test selection of appropriate TNs is crucial. For image evaluation visual and semiquantitative methods (Washout index, WOInd) are used. Aim of this study was to evaluate the diagnostic performance of MIBI imaging in hypofunctioning TNs with indeterminate fine-needle aspiration cytology results in a multicentric European setting. Patients with hypofunctioning TNs, EU-TIRADS 4 or 5, Bethesda III/IV and MIBI imaging were included. For visual evaluation the intensity of MIBI uptake in the TN was compared to normal thyroid tissue. 358 patients with 365 TNs (n = 68 malignant) were included. Planar imaging (SPECT) showed a sensitivity, specificity, positive predictive value, negative predictive value, and accuracy of 96% (94%), 21% (22%), 22% (15%), 96% (96%), and 35% (32%). The WOInd (38.9% of all cases, optimal cutoff: −19%) showed a sens 100% (spec 89%, PPV 82%, NPV 100%, ACC 93%). For hypofunctioning TNs at intermediate or high risk with indeterminate cytology, a MIBI negative result on visual evaluation is an effective tool to rule-out thyroid malignancy. The semi-quantitative method could considerably improve overall diagnostic performance of MIBI imaging.

Pan-TRK Immunohistochemistry and NTRK Gene Fusions in Primary Carcinomas of the Liver.

Gene fusions involving NTRK are not common in solid tumors. The aim of this study was to investigate the TRK protein expression and molecular characteristics of gene fusions in primary liver carcinomas. A total of 110 hepatocellular carcinomas (HCC) and 69 intrahepatic cholangiocarcinomas were retrieved for tissue microarray (TMA) construction and clinicopathologic characterization. Immunohistochemistry (IHC) for pan-TRK was initially performed on TMA slides and evaluated for staining intensity. Twelve (10.9%) of 110 HCC showed weak cytoplasmic TRK expression by IHC on TMA, while all others, including 69 intrahepatic cholangiocarcinomas, were negative for TRK. The TRK expression did not correlate with patient's age, sex, tumor differentiation, or tumor stage. The 12 cases were then validated by IHC on whole sections but all turned out to be negative. Further, RNA sequencing analysis did not detect any NTRK fusions in all 12 HCC cases; however, it did identify many fusions frequently involving genes that encode mitochondrial and ribosomal proteins, microRNAs, and some transcription factors. A few fusions were recurrent, including MT-ATP6/MT-ATP8 fusion (n=9, 75%), Ig κ light chain gene IGKV/IGKJ fusion (n=5, 41.7%), and histocompatibility complex gene HLA-C/HLA-B fusion (n=4, 33.3%). In summary, NTRK fusion is very rare in primary liver carcinomas. IHC on TMA for TRK expression yields high false positive results, which should be validated on whole sections and confirmed by molecular genetic studies such as RNA sequencing. Many fusions involving genes other than NTRK are detected in HCC, the significance of which warrants further studies.

EP444: Cases of isodicentric and isochromosome-related false negatives on SNP-based cell free DNA aneuploidy screening

Cell free DNA (cfDNA) screening has been established as routine prenatal care to assess the risk of common numerical aneuploidies (trisomy 21, 18, and 13). Clinical laboratories use a variety of methodologies for cfDNA screening, including massively parallel sequencing, fluorescent imaging of single DNA molecules, and single nucleotide polymorphism (SNP)-based platforms. All cfDNA screening has high sensitivity and high specificity, but false-positive and false-negative results still occur. False-negative cfDNA results involving trisomy 13 and trisomy 18 are rare but have significant clinical and emotional impacts on families and healthcare providers. We describe two cases of fetuses with low-risk cfDNA aneuploidy screening results from a SNP-based platform and a subsequent diagnosis of a numerical aneuploidy involving an isochromosome or isodicentric chromosome. Case one presented to maternal fetal medicine care at 30 weeks gestational age with multiple anomalies. Serum screening performed at 13 weeks was low risk for trisomy 21 (1 in 1,000) and trisomy 18 (1 in 10,000). Trisomy 13 risk was not assessed. At a 25-week ultrasound, a two-vessel cord and urinary tract dilation were identified. Follow-up ultrasound at 29 weeks identified multiple anomalies: inferior vermian hypoplasia, small cerebellum, enlarged cisterna magna, left-sided congenital diaphragmatic hernia, pleural effusion, enlarged echogenic kidneys with duplicated collecting systems, bilateral foot polydactyly, and micrognathia. The patient declined amniocentesis. SNP-based cfDNA aneuploidy screening was performed at 30 weeks, and the results returned low risk (<1 in 10,000) for trisomy 21, trisomy 13, trisomy 18, and monosomy X, with a fetal fraction of 24.2%. Fetal echocardiogram at 32 weeks identified an atrial septal defect, ventral septal defects, and minor valve abnormalities. Fetal MRI at 32 weeks identified severe microphthalmia, hypotelorism, incomplete cleft palate, postaxial polydactyly of the right hand, cerebral dysgenesis, corpus callosum hypoplasia, septum pellucidum abnormality, dysmorphic lateral ventricles, prominent extra-axial spaces, misshapen pons, and brachycephaly, and it confirmed the findings seen on prior ultrasounds. The pregnancy was delivered at 34 weeks, and the child passed away on day of life three. Postnatal karyotype results were abnormal: 46,XX,+13,der(13;13)(q10;q10). This result is consistent with an unbalanced Robertsonian translocation resulting in three copies of chromosome 13, demonstrating that isochromosome 13 was not detected by the SNP-based cfDNA aneuploidy screening. Follow-up parental karyotypes were normal, confirming that the translocation occurred de novo. Case two presented to maternal fetal medicine care at 12 weeks gestational age due to an increased nuchal translucency of 5.54 mm. SNP-based cfDNA aneuploidy screening was performed at 10 weeks, and the results returned low risk (<1 in 10,000) for trisomy 21, trisomy 13, trisomy 18, and monosomy X, with a fetal fraction of 11.4%. Chorionic villus sampling was performed at 13 weeks. CVS karyotype results were abnormal: 46,XY,idic(18)(p11.3)[5]/46,XY[15]. CVS microarray was also abnormal with a 4.9Mb deletion of 18p11.32p11.31, 3.9Mb duplication of 18p11.31p11.2, and 69Mb duplication of 18p11.2q23. This result is consistent with an isodicentric chromosome 18, likely to produce a phenotype similar to trisomy 18, and was not detected by the SNP-based cfDNA aneuploidy screening. A follow-up ultrasound at 16 weeks identified a two-vessel cord, marginal cord insertion, umbilical cord cyst, omphalocele, absent nasal bone, strawberry-shaped skull, and a unilateral choroid plexus cyst. The pregnancy ended in an uncomplicated dilation and evacuation at 16 weeks gestational age. Parental follow-up testing was not pursued. We present two cases of false-negative cfDNA aneuploidy screening results due to isochromosome 13 and isodicentric chromosome 18. It is critical that providers and patients understand that cfDNA testing is a screening test where false negative results are rare but possible. While SNP-based cfDNA is a highly effective cfDNA screening methodology, it has unique limitations for trisomies caused by isochromosomes and isodicentric chromosomes.

RF AND ANTI-CCPANTIBODY TESTS- A COMPARATIVE STUDY IN THE DIAGNOSIS OF RHEUMATOID ARTHRITIS IN A TERTIARY CARE HOSPITAL

INTRODUCTION: Rheumatoid arthritis (RA) is autoimmune disease associated with chronic inammation of joints causing deformities and functional impairment. Diagnosis primarily depends on clinical manifestations because of lack of suitable diagnostic tests. Rheumatoid factor (RF) is an autoantibody specic for Fc portion of human IgG. RF has low specicity as high false positive results are common in general population. Anti CCP antibody is also useful marker to diagnose rheumatoid arthritis and included in one of the criteria of American College of Rheumatology (ACR) /European League against Rheumatism (EULAR) classication of RA. Thus the present study was planned to compare the diagnostic utility of RF and Anti CCP antibody test in Rheumatoid arthritis patients in a Tertiary Care Hospital. AIM &amp; OBJECTIVE: To compare the diagnostic utility of RF and Anti CCP antibody test in Rheumatoid arthritis patients. Material &amp; METHODS: A total of 200 samples were taken from clinically suspected RA patients over a period of one year.RF was determined by latex agglutination method (SPAN DIAGNOSTICS Ltd.) and Anti CCP antibody by ECLIA (e-Cobas analyzer). The tests were performed as per manufacturer's instructions. RESULTS &amp; DISCUSSION: Out of total 200 samples tested, Both RF and Anti CCP Antibody was positive in 100cases(50%). Only RF positivity was seen in 104(52%) and only Anti CCP antibody was positive in 140 (70%). We found Anti –CCP Sensitivity, Specicity,Positive predictive value,Negative predictive value result as 73.52% , 93.75%, 96.10%, 62.50% respectively.In present study combination of Anti CCPantibody and Rheumatoid factor together have shown positive predictive value for Rheumatoid Arthritis patients which lack specic signs and symptoms related to diagnosis of RA. Conclusion: Anti CCP antibody test and RF can be used concomitantly to diagnose Rheumatoid arthritis and can be used in clinical settings so that appropriate management can be initiated to decrease future morbidity.

Multiple Chromatographic Analysis of Urine in the Detection of Bladder Cancer

Bladder cancer (BC) is the most common type of carcinoma of the urological system. Recently, there has been an increasing interest in non-invasive diagnostic tumor markers due to the invasive attribute of cystoscopy, which is still considered the gold standard diagnostic method. However, markers published in the literature so far do not meet expectations for replacing cystoscopy due to their low specificity and excessively high false-positive results, which can be mainly caused by frequently occurring hematuria also in benign cases. No reliable non-invasive method has yet been identified that can distinguish patients with bladder cancer and non-malignant hematuria patients. Our work examined the possibilities of non-targeted biomarkers of urine to distinguish patients with malignant and non-malignant diseases of the bladder using 3D HPLC in combination with computer processing of multiple datasets. Urine samples from 47 patients, 23 patients with bladder cancer (BC) and 24 patients with non-malignant hematuria (NMHU), were enrolled in clinical trials. For the separation and subsequent analysis of a large number of urine components, 3D HPLC (high-performance liquid chromatography) with an absorption and fluorescence detector was used. The obtained dataset was further subjected to various uni- and multi-dimensional statistical analyses and mathematical modeling. We found 334 chromatographic peaks, of which 18 peaks were identified as significantly different for BC and NMHU patients. Using receiver operating characteristic (ROC) analysis, we assessed the informative ability of significant chromatographic peaks (90% sensitivity and 74% specificity). By logistic regression, we identified the optimal and simplified set of seven chromatographic peaks (5 absorptions plus 2 fluorescence) with strong classification power (100% sensitivity and 100% specificity) for distinguishing patients with bladder cancer and those with non-malignant hematuria. Partial least square discriminant analysis (PLS-DA) model and orthogonal projection to latent structure discriminant analysis (OPLS-DA) with 100% sensitivity and 96% specificity were used to distinguish BC and NMHU patients. Multivariate statistical analysis of urinary metabolomic profiles of patients revealed that BC patients can be discriminated from NMHU patients and the results can likely contribute to an early and non-invasive diagnosis of BC.

DeepCervix: A deep learning-based framework for the classification of cervical cells using hybrid deep feature fusion techniques

Cervical cancer, one of the most common fatal cancers among women, can be prevented by regular screening to detect any precancerous lesions at early stages and treat them. Pap smear test is a widely performed screening technique for early detection of cervical cancer, whereas this manual screening method suffers from high false-positive results because of human errors. To improve the manual screening practice, machine learning (ML) and deep learning (DL) based computer-aided diagnostic (CAD) systems have been investigated widely to classify cervical Pap cells. Most of the existing studies require pre-segmented images to obtain good classification results. In contrast, accurate cervical cell segmentation is challenging because of cell clustering. Some studies rely on handcrafted features, which cannot guarantee the classification stage's optimality. Moreover, DL provides poor performance for a multiclass classification task when there is an uneven distribution of data, which is prevalent in the cervical cell dataset. This investigation has addressed those limitations by proposing DeepCervix, a hybrid deep feature fusion (HDFF) technique based on DL, to classify the cervical cells accurately. Our proposed method uses various DL models to capture more potential information to enhance classification performance. Our proposed HDFF method is tested on the publicly available SIPaKMeD dataset and compared the performance with base DL models and the late fusion (LF) method. For the SIPaKMeD dataset, we have obtained the state-of-the-art classification accuracy of 99.85%, 99.38%, and 99.14% for 2-class, 3-class, and 5-class classification. This method is also tested on the Herlev dataset and achieves an accuracy of 98.32% for 2-class and 90.32% for 7-class classification. The source code of the DeepCervix model is available at: https://github.com/Mamunur-20/DeepCervix.

Primary care and mental health: Where do we go from here?

Primary care has been dubbed the “de facto” mental health system of the United States since the 1970s. Since then, various forms of mental health delivery models for primary care have proven effective in improving patient outcomes and satisfaction and reducing costs. Despite increases in collaborative care implementation and reimbursement, prevalence rates of major depression in the United States remain unchanged while anxiety and suicide rates continue to climb. Meanwhile, primary care task forces in countries like the United Kingdom and Canada are recommending against depression screening in primary care altogether, citing lack of trials demonstrating improved outcomes in screened vs unscreened patients when the same treatment is available, high false-positive results, and small treatment effects. In this perspective, a primary care physician and two psychiatrists address the question of why we are not making headway in treating common mental health conditions in primary care. In addition, we propose systemic changes to improve the dissemination of mental health treatment in primary care.

Evaluation of Correlation between Serum Free Light-Chain Assay and Bone Marrow Study in Multiple Myeloma Patients.

Background: Multiple myeloma is a hematologic malignancy manifested by the secretion of abnormal immunoglobulin. Different methods have been described for diagnosis and patient response to management. Serum free light-chain assay is recently approved in the diagnosis of multiple myeloma patients. This study aimed to evaluate the diagnostic accuracy of serum free light-chain assay and its agreement to bone marrow findings. Materials and Methods: Forty-six patients with the diagnosis of multiple myeloma were enrolled in the study. The patients were grouped into newly diagnosed cases (22 patients,47.8%) and known cases who were under treatment (24 patients,52.2%). Bone marrow study was done and percentage and clonal status of plasma cells were evaluated by a combination of immunohistochemistry and flow cytometry. Free light-chain assay was done in all patients and sensitivity, specificity, positive predictive value, and negative predictive value were analyzed. Results: Thirty of 46 patients showed monoclonal plasma cell infiltration and 16 patients showed polyclonal plasma cell infiltration based on bone marrow findings. An abnormal κ/λ ratio was seen in 15(68.18%) of new cases and 16(66.6%) of known cases. Sensitivity, specificity, PPV and NPV for κ⁄λ ratio were 72.73%, 46.15%, 71%, and 50%, respectively. Conclusion: In conclusion, due to high false positive and false negative results, the presence of an abnormal serum FLC ratio was not equal to the presence of monoclonal gammopathy, and observation of a normal ratio does not exclude the presence of monoclonal gammopathy.

Brain Tumor Classification Based on Fine-Tuned Models and the Ensemble Method

Brain tumors are life-threatening for adults and children. However, accurate and timely detection can save lives. This study focuses on three different types of brain tumors: Glioma, meningioma, and pituitary tumors. Many studies describe the analysis and classification of brain tumors, but few have looked at the problem of feature engineering. Methods are needed to overcome the drawbacks of manual diagnosis and conventional feature-engineering techniques. An automatic diagnostic system is thus necessary to extract features and classify brain tumors accurately. While progress continues to be made, the automatic diagnoses of brain tumors still face challenges of low accuracy and high false-positive results. The model presented in this study, which offers improvements for feature extraction and classification, uses deep learning and machine learning for the assessment of brain tumors. Deep learning is used for feature extraction and encompasses the application of different models such as fine-tuned Inception-v3 and fine-tuned Xception. The classification of brain tumors is explored through deep- and machine-learning algorithms including softmax, Random Forest, Support Vector Machine, K-Nearest Neighbors, and the ensemble technique. The results of these approaches are compared with existing methods. The Inception-v3 model has a test accuracy of 94.34% and achieves the highest performance compared with other recently reported methods. This improvement may be sufficient to support a significant role in clinical applications for brain tumor analysis. Furthermore, this type of approach can be used as an effective decision-support tool for radiologists in medical diagnostics as a second opinion based on the magnetic resonance imaging (MRI) analysis. It may also save valuable time for radiologists who have to manually review numerous MRI images of patients.