What factors influence cellular pathologists' confidence in case reporting?

Histopathology is a challenging interpretive discipline, and the level of confidence a pathologist has in their diagnosis is known to vary, which is conveyed descriptively in pathology reports. There has been little study to accurately quantify pathologists' diagnostic confidence or the factors that influence it. In this study involving sixteen pathologists from six NHS trusts, we assessed diagnostic confidence across multiple variables and four specialties. Each case was reported by four pathologists, with each pathologist reporting each case twice (on light microscopy (LM) and digital pathology (DP)). For each diagnosis, pathologists recorded their confidence on a 7-point Likert scale. This provided 16,187 diagnoses and associated confidence scores for analysis. All variables investigated were found to be significantly predictive of diagnostic confidence, except level of pathologist experience. Confidence was lower for difficult to report cases, cases where there was inter- and intra-pathologist variation in the diagnosis, and cases where the pathologist made an incorrect diagnosis. Confidence was higher, although nominally, for LM diagnoses than DP (rate ratio 1.09 (95% CI 1.01-1.18), p = 0.035), although results indicate pathologists are confident to report on DP. Lowest confidence scores were seen in areas of known diagnostic complexity and cases with quality issues. High confidence in incorrect diagnoses were almost invariably attributed to interpretive diagnostic differences which occurred across both rare and common lesions. The results highlight the value of external quality control schemes and the benefits of selective peer review when reporting.

Using Machine Learning Multiclass Classification Technique to Detect IoT Attacks in Real Time.

This paper presents a real-time intrusion detection system (IDS) aimed at detecting the Internet of Things (IoT) attacks using multiclass classification models within the PySpark architecture. The research objective is to enhance detection accuracy while reducing the prediction time. Various machine learning algorithms are employed using the OneVsRest (OVR) technique. The proposed method utilizes the IoT-23 dataset, which consists of network traffic from smart home IoT devices, for model development. Data preprocessing techniques, such as data cleaning, transformation, scaling, and the synthetic minority oversampling technique (SMOTE), are applied to prepare the dataset. Additionally, feature selection methods are employed to identify the most relevant features for classification. The performance of the classifiers is evaluated using metrics such as accuracy, precision, recall, and F1 score. The results indicate that among the evaluated algorithms, extreme gradient boosting achieves a high accuracy of 98.89%, while random forest demonstrates the most efficient training and prediction times, with a prediction time of only 0.0311 s. The proposed method demonstrates high accuracy in real-time intrusion detection of IoT attacks, outperforming existing approaches.

High Probability of Lynch Syndrome Among Colorectal Cancer Patients Is Associated With Higher Occurrence of KRAS and PIK3CA Mutations.

Background: In Indonesia, early-onset colorectal cancer (EOCRC) rates are higher in patients < 50 years old compared to Western populations, possibly due to a higher frequency of Lynch syndrome (LS) in CRC patients. We aimed to examine the association of KRAS and PIK3CA mutations with LS. Methods: In this retrospective cross-sectional single-center study, the PCR-HRM-based test was used for screening of microsatellite instability (MSI) mononucleotide markers (BAT25, BAT26, BCAT25, MYB, EWSR1), MLH1 promoter methylation, and oncogene mutations of BRAF (V600E), KRAS (exon 2 and 3), and PIK3CA (exon 9 and 20) in FFPE DNA samples. Results: All the samples (n = 244) were from Dr. Sardjito General Hospital Yogyakarta, Indonesia. KRAS and PIK3CA mutations were found in 151/244 (61.88%) and 107/244 (43.85%) of samples, respectively. KRAS and PIK3CA mutations were significantly associated with MSI status in 32/42 (76.19%) and 25/42 (59.52%) of samples, respectively. KRAS mutation was significantly associated with LS status in 26/32 (81.25%) of samples. The PIK3CA mutation was present in a higher proportion in LS samples of 19/32 (59.38%), but not statistically significant. Clinicopathology showed that KRAS mutation was significantly associated with right-sided CRC and higher histology grade in 39/151 (25.83%) and 24/151 (16.44%) samples, respectively. PIK3CA mutation was significantly associated with female sex and lower levels of tumor-infiltrating lymphocytes in 62/107 (57.94%) and 26/107 (30.23%) samples, respectively. KRAS and PIK3CA mutations did not significantly affect overall survival (120 months) in LS and non-LS patients. Conclusions: The high probability of LS in Indonesian CRC patients is associated with KRAS and PIK3CA mutations.

Improving Pediatric Hypertension Screening in an Academic Primary Care Setting.

Introduction: Adherence to the American Academy of Pediatrics clinical practice guidelines for screening and managing high blood pressure (BP) is low. This team sought to improve recognition and documentation of relevant diagnoses in patients aged 13-20 years who presented to general pediatric clinics. Methods: The primary outcome measure was the proportion of office visits for patients ages 13-20 with a BP ≥ 120/80 with a visit or problem list diagnosis of hypertension or elevated BP. Secondary measures included (1) the proportion of patients who had their BP measured in the right arm, (2) the proportion of patients who had a mid-arm circumference measurement recorded, and (3) the proportion of patients who had a second BP reading measured at the visit. Interventions addressed key drivers for evidence-based high BP screening: standard BP measurement, electronic health record clinical decision support, and clinical pathway adoption. Data were collected over a twenty-seven-month period and plotted using the Laney p' chart. Results: Provider documentation of elevated BP or hypertension improved from a baseline mean of 24% in April 2020 through January 2022 to 41% in February 2021 through June 2022. All secondary outcome measures also demonstrated significant improvement. Conclusions: This project demonstrates the feasibility of improving adherence to best practices of BP measurement in primary care clinics through education, acquisition of resources, and implementation of electronic health record flags for abnormal values.

Advantages of automated immunostain analyses for complex membranous immunostains: An exemplar investigating loss of E-cadherin expression in colorectal cancer.

As pathology moves towards digitisation, biomarker profiling through automated image analysis provides potentially objective and time-efficient means of assessment. This study set out to determine how a complex membranous immunostain, E-cadherin, assessed using an automated digital platform fares in comparison to manual evaluation in terms of clinical correlations and prognostication. Tissue microarrays containing 1000 colorectal cancer samples, stained with clinical E-cadherin antibodies were assessed through both manual scoring and automated image analysis. Both manual and automated scores were correlated to clinicopathological and survival data. E-cadherin data generated through digital image analysis was superior to manual evaluation when investigating for clinicopathological correlations in colorectal cancer. Loss of membranous E-cadherin, assessed on automated platforms, correlated with: right sided tumours (p = <0.001), higher T-stage (p = <0.001), higher grade (p = <0.001), N2 nodal stage (p = <0.001), intramural lymphovascular invasion (p = 0.006), perineural invasion (p = 0.028), infiltrative tumour edge (p = 0.001) high tumour budding score (p = 0.038), distant metastasis (p = 0.035), and poorer 5-year (p= 0.042) survival status. Manual assessment was only correlated with higher grade tumours, though other correlations become apparent only when assessed for morphological expression pattern (circumferential, basolateral, parallel) irrespective of intensity. Digital assessment of E-cadherin is effective for prognostication of colorectal cancer and may potentially offer benefits of improved objectivity, accuracy, and economy of time. Incorporating tools to assess patterns of staining may further improve such digital assessment in the future.

Effective Feature Engineering Framework for Securing MQTT Protocol in IoT Environments.

The explosive growth of the domain of the Internet of things (IoT) network devices has resulted in unparalleled ease of productivity, convenience, and automation, with Message Queuing Telemetry Transport (MQTT) protocol being widely recognized as an essential communication standard in IoT environments. MQTT enables fast and lightweight communication between IoT devices to facilitate data exchange, but this flexibility also exposes MQTT to significant security vulnerabilities and challenges that demand highly robust security. This paper aims to enhance the detection efficiency of an MQTT traffic intrusion detection system (IDS). Our proposed approach includes the development of a binary balanced MQTT dataset with an effective feature engineering and machine learning framework to enhance the security of MQTT traffic. Our feature selection analysis and comparison demonstrates that selecting a 10-feature model provides the highest effectiveness, as it shows significant advantages in terms of constant accuracy and superior training and testing times across all models. The results of this study show that the framework has the capability to enhance the efficiency of an IDS for MQTT traffic, with more than 96% accuracy, precision, recall, F1-score, and ROC, and it outperformed the most recent study that used the same dataset.

Digital pathology for reporting histopathology samples, including cancer screening samples - definitive evidence from a multisite study.

AIMS: To conduct a definitive multicentre comparison of digital pathology (DP) with light microscopy (LM) for reporting histopathology slides including breast and bowel cancer screening samples. METHODS: A total of 2024 cases (608 breast, 607 GI, 609 skin, 200 renal) were studied, including 207 breast and 250 bowel cancer screening samples. Cases were examined by four pathologists (16 study pathologists across the four speciality groups), using both LM and DP, with the order randomly assigned and 6 weeks between viewings. Reports were compared for clinical management concordance (CMC), meaning identical diagnoses plus differences which do not affect patient management. Percentage CMCs were computed using logistic regression models with crossed random-effects terms for case and pathologist. The obtained percentage CMCs were referenced to 98.3% calculated from previous studies. RESULTS: For all cases LM versus DP comparisons showed the CMC rates were 99.95% [95% confidence interval (CI) = 99.90-99.97] and 98.96 (95% CI = 98.42-99.32) for cancer screening samples. In speciality groups CMC for LM versus DP showed: breast 99.40% (99.06-99.62) overall and 96.27% (94.63-97.43) for cancer screening samples; [gastrointestinal (GI) = 99.96% (99.89-99.99)] overall and 99.93% (99.68-99.98) for bowel cancer screening samples; skin 99.99% (99.92-100.0); renal 99.99% (99.57-100.0). Analysis of clinically significant differences revealed discrepancies in areas where interobserver variability is known to be high, in reads performed with both modalities and without apparent trends to either. CONCLUSIONS: Comparing LM and DP CMC, overall rates exceed the reference 98.3%, providing compelling evidence that pathologists provide equivalent results for both routine and cancer screening samples irrespective of the modality used.

Optimizing the selection of natural fibre reinforcement and polymer matrix for plastic composite using LS-SVM technique.

The manufacturing sector is paying close attention to plastic matrix composites (PMCs) reinforced with natural fibres for improving their products. Due to the fact that PMC reinforced with naturally occurring fibres is more affordable and has superior mechanical qualities. Based on the application material requirements, An important step in the production of PMC is choosing the right natural fibres for reinforcing and determining how much of each. This investigation aimed that Artificial Intelligence (AI) or soft computing based approaches are used to determine the right amount of natural fibres in PMCs to make the manufacturing process simpler. However, techniques in the literature are not concentrated on finding suitable material. Hence in this investigation, a local search with support vector machine (LS-SVM) optimization technique is proposed for the optimal selection of appropriate proportions of suitable fibres. Modelling of the Proposed LS-SVM Optimization was demonstrated. In this proposed technique around four kinds of polymers/plastics and 14 natural fibres are considered, which are optimized in various proportions. The optimization performance is evaluated based on the tensile strength, flexural yield strength and flexural yield modulus. The proposed LS-SVM Optimization was evacuated by developing solutions for medical applications (Case 1), Transportation applications (Case 2) and other notable applications (Case 3) in terms of tensile and flexural properties of the material. The maximum flexure stress in case 1, case 2, and case 3 is observed as 53 MPa, 45 MPa and 26 MPa respectively. Similarly, the maximum flexure stress in case 1, case 2, and case 3 is observed as 53 MPa, 45 MPa and 26 MPa respectively. Hence the proposed method recommended for choosing optimal decision on the choice of fiber and their quantity in the composite matrix.

Deep Learning Technology to Recognize American Sign Language Alphabet.

Historically, individuals with hearing impairments have faced neglect, lacking the necessary tools to facilitate effective communication. However, advancements in modern technology have paved the way for the development of various tools and software aimed at improving the quality of life for hearing-disabled individuals. This research paper presents a comprehensive study employing five distinct deep learning models to recognize hand gestures for the American Sign Language (ASL) alphabet. The primary objective of this study was to leverage contemporary technology to bridge the communication gap between hearing-impaired individuals and individuals with no hearing impairment. The models utilized in this research include AlexNet, ConvNeXt, EfficientNet, ResNet-50, and VisionTransformer were trained and tested using an extensive dataset comprising over 87,000 images of the ASL alphabet hand gestures. Numerous experiments were conducted, involving modifications to the architectural design parameters of the models to obtain maximum recognition accuracy. The experimental results of our study revealed that ResNet-50 achieved an exceptional accuracy rate of 99.98%, the highest among all models. EfficientNet attained an accuracy rate of 99.95%, ConvNeXt achieved 99.51% accuracy, AlexNet attained 99.50% accuracy, while VisionTransformer yielded the lowest accuracy of 88.59%.

Investigating genomic, proteomic, and post-transcriptional regulation profiles in colorectal cancer: a comparative study between primary tumors and associated metastases.

INTRODUCTION: Approximately 50% of patients with primary colorectal carcinoma develop liver metastases. This study investigates the possible molecular discrepancies between primary colorectal cancer (pCRC) and their respective metastases. METHODS: A total of 22 pairs of pCRC and metastases were tested. Mutation profiling of 26 cancer-associated genes was undertaken in 22/22primary-metastasis tumour pairs using next-generation sequencing, whilst the expression of a panel of six microRNAs (miRNAs) was investigated using qPCRin 21/22 pairs and 22 protein biomarkers was tested using Reverse Phase Protein Array (RPPA)in 20/22 patients' tumour pairs. RESULTS: Among the primary and metastatic tumours the mutation rates for the individual genes are as follows:TP53 (86%), APC (44%), KRAS (36%), PIK3CA (9%), SMAD4 (9%), NRAS (9%) and 4% for FBXW7, BRAF, GNAS and CDH1. The primary-metastasis tumour mutation status was identical in 54/60 (90%) loci. However, there was discordance in heterogeneity status in 40/58 genetic loci (z-score = 6.246, difference = 0.3793, P < 0.0001). Furthermore, there was loss of concordance in miRNA expression status between primary and metastatic tumours, and 57.14-80.95% of the primary-metastases tumour pairs showed altered primary-metastasis relative expression in all the miRNAs tested. Moreover, 16 of 20 (80%) tumour pairs showed alteration in at least 3 of 6 (50%) of the protein biomarker pathways analysed. CONCLUSION: The molecular alterations of primary colorectal tumours differ significantly from those of their matched metastases. These differences have profound implications for patients' prognoses and response to therapy.

Patient-Specific Preictal Pattern-Aware Epileptic Seizure Prediction with Federated Learning.

Electroencephalography (EEG) signals are the primary source for discriminating the preictal from the interictal stage, enabling early warnings before the seizure onset. Epileptic siezure prediction systems face significant challenges due to data scarcity, diversity, and privacy. This paper proposes a three-tier architecture for epileptic seizure prediction associated with the Federated Learning (FL) model, which is able to achieve enhanced capability by utilizing a significant number of seizure patterns from globally distributed patients while maintaining data privacy. The determination of the preictal state is influenced by global and local model-assisted decision making by modeling the two-level edge layer. The Spiking Encoder (SE), integrated with the Graph Convolutional Neural Network (Spiking-GCNN), works as the local model trained using a bi-timescale approach. Each local model utilizes the aggregated seizure knowledge obtained from the different medical centers through FL and determines the preictal probability in the coarse-grained personalization. The Adaptive Neuro-Fuzzy Inference System (ANFIS) is utilized in fine-grained personalization to recognize epileptic seizure patients by examining the outcomes of the FL model, heart rate variability features, and patient-specific clinical features. Thus, the proposed approach achieved 96.33% sensitivity and 96.14% specificity when tested on the CHB-MIT EEG dataset when modeling was performed using the bi-timescale approach and Spiking-GCNN-based epileptic pattern learning. Moreover, the adoption of federated learning greatly assists the proposed system, yielding a 96.28% higher accuracy as a result of addressing data scarcity.

Ensemble-Learning Framework for Intrusion Detection to Enhance Internet of Things' Devices Security.

The Internet of Things (IoT) comprises a network of interconnected nodes constantly communicating, exchanging, and transferring data over various network protocols. Studies have shown that these protocols pose a severe threat (Cyber-attacks) to the security of data transmitted due to their ease of exploitation. In this research, we aim to contribute to the literature by improving the Intrusion Detection System (IDS) detection efficiency. In order to improve the efficiency of the IDS, a binary classification of normal and abnormal IoT traffic is constructed to enhance the IDS performance. Our method employs various supervised ML algorithms and ensemble classifiers. The proposed model was trained on TON-IoT network traffic datasets. Four of the trained ML-supervised models have achieved the highest accurate outcomes; Random Forest, Decision Tree, Logistic Regression, and K-Nearest Neighbor. These four classifiers are fed to two ensemble approaches: voting and stacking. The ensemble approaches were evaluated using the evaluation metrics and compared for their efficacy on this classification problem. The accuracy of the ensemble classifiers was higher than that of the individual models. This improvement can be attributed to ensemble learning strategies that leverage diverse learning mechanisms with varying capabilities. By combining these strategies, we were able to enhance the reliability of our predictions while reducing the occurrence of classification errors. The experimental results show that the framework can improve the efficiency of the Intrusion Detection System, achieving an accuracy rate of 0.9863.

Associations between AI-Assisted Tumor Amphiregulin and Epiregulin IHC and Outcomes from Anti-EGFR Therapy in the Routine Management of Metastatic Colorectal Cancer.

PURPOSE: High tumor production of the EGFR ligands, amphiregulin (AREG) and epiregulin (EREG), predicted benefit from anti-EGFR therapy for metastatic colorectal cancer (mCRC) in a retrospective analysis of clinical trial data. Here, AREG/EREG IHC was analyzed in a cohort of patients who received anti-EGFR therapy as part of routine care, including key clinical contexts not investigated in the previous analysis. EXPERIMENTAL DESIGN: Patients who received panitumumab or cetuximab ± chemotherapy for treatment of RAS wild-type mCRC at eight UK cancer centers were eligible. Archival formalin-fixed paraffin-embedded tumor tissue was analyzed for AREG and EREG IHC in six regional laboratories using previously developed artificial intelligence technologies. Primary endpoints were progression-free survival (PFS) and overall survival (OS). RESULTS: A total of 494 of 541 patients (91.3%) had adequate tissue for analysis. A total of 45 were excluded after central extended RAS testing, leaving 449 patients in the primary analysis population. After adjustment for additional prognostic factors, high AREG/EREG expression (n = 360; 80.2%) was associated with significantly prolonged PFS [median: 8.5 vs. 4.4 months; HR, 0.73; 95% confidence interval (CI), 0.56-0.95; P = 0.02] and OS [median: 16.4 vs. 8.9 months; HR, 0.66 95% CI, 0.50-0.86; P = 0.002]. The significant OS benefit was maintained among patients with right primary tumor location (PTL), those receiving cetuximab or panitumumab, those with an oxaliplatin- or irinotecan-based chemotherapy backbone, and those with tumor tissue obtained by biopsy or surgical resection. CONCLUSIONS: High tumor AREG/EREG expression was associated with superior survival outcomes from anti-EGFR therapy in mCRC, including in right PTL disease. AREG/EREG IHC assessment could aid therapeutic decisions in routine practice. See related commentary by Randon and Pietrantonio, p. 4021.

In Vitro Culture and Histological Evaluation of 3D Organotypic Cultures.

Organotypic cultures allow cells to grow in a system which mimics in vivo tissue organization. Here we describe a method for establishing 3D organotypic cultures (using intestine as an example system), followed by methods for demonstrating cell morphology and tissue architecture using histological techniques and molecular expression analysis using immunohistochemistry, though the system is also amenable to molecular expression analysis, such as by PCR, RNA sequencing, or FISH.

Activated tissue resident memory T-cells (CD8+CD103+CD39+) uniquely predict survival in left sided "immune-hot" colorectal cancers.

Introduction: Characterization of the tumour immune infiltrate (notably CD8+ T-cells) has strong predictive survival value for cancer patients. Quantification of CD8 T-cells alone cannot determine antigenic experience, as not all infiltrating T-cells recognize tumour antigens. Activated tumour-specific tissue resident memory CD8 T-cells (TRM) can be defined by the co-express of CD103, CD39 and CD8. We investigated the hypothesis that the abundance and localization of TRM provides a higher-resolution route to patient stratification. Methods: A comprehensive series of 1000 colorectal cancer (CRC) were arrayed on a tissue microarray, with representative cores from three tumour locations and the adjacent normal mucosa. Using multiplex immunohistochemistry we quantified and determined the localization of TRM. Results: Across all patients, activated TRM were an independent predictor of survival, and superior to CD8 alone. Patients with the best survival had immune-hot tumours heavily infiltrated throughout with activated TRM. Interestingly, differences between right- and left-sided tumours were apparent. In left-sided CRC, only the presence of activated TRM (and not CD8 alone) was prognostically significant. Patients with low numbers of activated TRM cells had a poor prognosis even with high CD8 T-cell infiltration. In contrast, in right-sided CRC, high CD8 T-cell infiltration with low numbers of activated TRM was a good prognosis. Conclusion: The presence of high intra-tumoural CD8 T-cells alone is not a predictor of survival in left-sided CRC and potentially risks under treatment of patients. Measuring both high tumour-associated TRM and total CD8 T-cells in left-sided disease has the potential to minimize current under-treatment of patients. The challenge will be to design immunotherapies, for left-sided CRC patients with high CD8 T-cells and low activate TRM,that result in effective immune responses and thereby improve patient survival.

BZR proteins: identification, evolutionary and expression analysis under various exogenous growth regulators in plants.

BACKGROUNDS: The BRASSINAZOLE-RESISTANT (BZR) family of transcription factors affects a variety of developmental and physiological processes and plays a key role in multiple stress-resistance functions in plants. However, the evolutionary relationship and individual expression patterns of the BZR genes are unknown in various crop plants. METHODS AND RESULTS: In this study, we performed a genome-wide analysis of the BZR genes family in wheat and rice. Here, we found a total of 16 and 6 proteins containing the BZR domain in wheat and rice respectively. The phylogenetic analysis divided the identified BZR proteins from several plants into five subfamilies. The intron/exon structural patterns and conserved motifs distribution revealed that BZR proteins exhibite high specificities in each subfamily. Moreover, the co-expression and protein-protein interaction analysis suggested that BZR proteins may interact/co-expressed with several other proteins to perform various functions in plants. The presence of different stresses, hormones and light-responsive cis-elements in promoter regions of BZR genes imply its diverse functions in plants. The expression patterns indicated that many BZR genes regulate organ development and differentiation. BZR genes significantly respond to exogenous application of brassinosteroids, melatonin and abiotic stresses, demonstrating its key role in various developmental and physiological processes. CONCLUSION: The present study establishes the foundation for future functional genomics studies of BZR genes through reverse genetics and to further explore the potential of BZR genes in mitigating the stress tolerance in crop plants.

Genome Profiling of SARS-CoV-2 in Indonesia, ASEAN and the Neighbouring East Asian Countries: Features, Challenges and Achievements.

Whole-genome sequencing (WGS) has played a significant role in understanding the epidemiology and biology of SARS-CoV-2 virus. Here, we investigate the use of SARS-CoV-2 WGS in Southeast and East Asian countries as a genomic surveillance during the COVID-19 pandemic. Nottingham-Indonesia Collaboration for Clinical Research and Training (NICCRAT) initiative has facilitated collaboration between the University of Nottingham and a team in the Research Center for Biotechnology, National Research and Innovation Agency (BRIN), to carry out a small number of SARS-CoV-2 WGS in Indonesia using Oxford Nanopore Technology (ONT). Analyses of SARS- CoV-2 genomes deposited on GISAID reveal the importance of clinical and demographic metadata collection and the importance of open access and data sharing. Lineage and phylogenetic analyses of two periods defined by the Delta variant outbreak reveal that: (1) B.1.466.2 variants were the most predominant in Indonesia before the Delta variant outbreak, having a unique spike gene mutation N439K at more than 98% frequency, (2) Delta variants AY.23 sub-lineage took over after June 2021, and (3) the highest rate of virus transmissions between Indonesia and other countries was through interactions with Singapore and Japan, two neighbouring countries with a high degree of access and travels to and from Indonesia.