The Evolution of Nucleic Acid-Based Diagnosis Methods from the (pre-)CRISPR to CRISPR era and the Associated Machine/Deep Learning Approaches in Relevant RNA Design.

Nucleic acid tests (NATs) are considered as gold standard in molecular diagnosis. To meet the demand for onsite, point-of-care, specific and sensitive, trace and genotype detection of pathogens and pathogenic variants, various types of NATs have been developed since the discovery of PCR. As alternatives to traditional NATs (e.g., PCR), isothermal nucleic acid amplification techniques (INAATs) such as LAMP, RPA, SDA, HDR, NASBA, and HCA were invented gradually. PCR and most of these techniques highly depend on efficient and optimal primer and probe design to deliver accurate and specific results. This chapter starts with a discussion of traditional NATs and INAATs in concert with the description of computational tools available to aid the process of primer/probe design for NATs and INAATs. Besides briefly covering nanoparticles-assisted NATs, a more comprehensive presentation is given on the role CRISPR-based technologies have played in molecular diagnosis. Here we provide examples of a few groundbreaking CRISPR assays that have been developed to counter epidemics and pandemics and outline CRISPR biology, highlighting the role of CRISPR guide RNA and its design in any successful CRISPR-based application. In this respect, we tabularize computational tools that are available to aid the design of guide RNAs in CRISPR-based applications. In the second part of our chapter, we discuss machine learning (ML)- and deep learning (DL)-based computational approaches that facilitate the design of efficient primer and probe for NATs/INAATs and guide RNAs for CRISPR-based applications. Given the role of microRNA (miRNAs) as potential future biomarkers of disease diagnosis, we have also discussed ML/DL-based computational approaches for miRNA-target predictions. Our chapter presents the evolution of nucleic acid-based diagnosis techniques from PCR and INAATs to more advanced CRISPR/Cas-based methodologies in concert with the evolution of deep learning (DL)- and machine learning (ml)-based computational tools in the most relevant application domains.

Visibility of esophageal squamous cell carcinoma under iodine staining on texture and color enhancement imaging.

Objective: Iodine staining on white light imaging (WLI) is the gold standard for detecting and demarcating esophageal squamous cell carcinoma (ESCC). We examined the effects of texture and color enhancement imaging (TXI) on improving the endoscopic visibility of ESCC under iodine staining. Methods: Twenty ESCC lesions that underwent endoscopic submucosal dissection were retrospectively included. The color difference between ESCC and the surrounding mucosa (ΔEe) on WLI, TXI, and narrow-band imaging was assessed, and ΔEe under 1% iodine staining on WLI and TXI. Furthermore, the visibility grade determined by endoscopists was evaluated on each imaging. Result: The median ΔEe was greater on TXI than on WLI (14.53 vs. 10.71, respectively; p < 0.005). Moreover, the median ΔEe on TXI under iodine staining was greater than the median ΔEe on TXI and narrow-band imaging (39.20 vs. 14.53 vs. 16.42, respectively; p < 0.005 for both). A positive correlation in ΔEe under iodine staining was found between TXI and WLI (correlation coefficient = 0.61, p < 0.01). Moreover, ΔEe under iodine staining on TXI in each lesion was greater than the corresponding ΔEe on WLI. The visibility grade assessed by endoscopists on TXI was also significantly greater than that on WLI under iodine staining (p < 0.01). Conclusions: The visibility of ESCC after iodine staining was greater on TXI than on WLI.

Rare case of mantle cell lymphoma of the lacrimal sac

ABSTRACT Mantle cell lymphoma of the ocular and periorbital regions is extremely rare but should be considered in the differential diagnosis of lesions affecting the periorbital tissues. In this study, we present a rare case of mantle cell lymphoma of the lacrimal sac in a 65-year-old male presenting with a mass in the lacrimal sac region and epiphora. After clinical examinations and imaging studies, the mucocele was misdiagnosed. Considering the unexpected findings during external dacryocystorhinostomy, a frozen biopsy was performed, which confirmed the diagnosis of lymphoma.

Anterior lamellar corneoscleral keratoplasty for the management of corneal thinning following treatment with mitomycin-C and interferon to treat highly suspected ocular surface squamous neoplasia: a case report

ABSTRACT A patient presented with corneoscleral thinning five months after the treatment of suspected ocular squamous surface neoplasia with mitomycin-C and interferon. For tectonic and aesthetic purposes, we decided to perform lamellar corneoscleral transplantation. The approach used established new tectonic support and corneal homeostasis. This technique might be an option in similar cases.

Clinical, epidemiological, and care profile of hospitalized patients with retinoblastoma in Brazil

ABSTRACT Purpose: To describe the epidemiological and clinical profile of hospitalized patients with retinoblastoma in Brazil. Methods: Using data from the Hospital Cancer Registry of the Instituto Nacional de Câncer, patients with the morphological codes of retinoblastoma who were diagnosed between 2000 to 2018, aged 0-19 years, and followed up in registered hospitals (analytical cases) were selected. The relative and absolute frequencies of demographic, clinical, diagnostic, therapeutic, and outcome variables were described. Hospital performance indicators were calculated and compared between hospitals qualified and not qualified to treat pediatric oncology cases and between hospitals with different case volumes (<20, 20-75, >75 cases). Results: Of the 2,269 identified analytical cases from 86 institutions, 48% were from the Southeast, 54% were male, and 66% were aged <4 years. The proportion of missing data (NA) was too high for several variables. Approximately 84% of the patients were from the public health system, 40% had a positive family history, and 88% had unilateral involvement. The first treatment included surgery in 58.3% of the patients (NA=2), Approximately 36.6% of these patients achieved complete remission, 10.8% achieved partial remission, and 12.7% died (NA=59%). Hospital performance indicators were within the target in >90% of the patients. The median time between the first appointment and diagnosis (6 days, interquartile range [IQR] 1-14) was significantly lower and the median time to death was longer (343 days, IQR, 212-539) in high-volume hospitals (>75 cases) than in medium- and low-volume hospitals. Conclusions: Despite the high proportion of missing data, we found that the delay in diagnosis is due to prehospital factors. Additionally, there is a need for educational programs for healthcare professionals and families that emphasize early identification and referral to specialized centers. Future studies should focus on the impact of Hospital Cancer Registry data completeness on outcomes, causes of delay in diagnosis, regional inequalities, and barriers to accessing specialized services.

Interval-specific likelihood ratios and probability-based models for interpreting combined CSF biomarkers for Alzheimer's disease.

BACKGROUND: In Alzheimer's disease (AD) diagnosis, a cerebrospinal fluid (CSF) biomarker panel is commonly interpreted with binary cutoff values. However, these values are not generic and do not reflect the disease continuum. We explored the use of interval-specific likelihood ratios (LRs) and probability-based models for AD using a CSF biomarker panel. METHODS: CSF biomarker (Aß1-42, tTau and pTau181) data for both a clinical discovery cohort of 241 patients (measured with INNOTEST) and a clinical validation cohort of 129 patients (measured with EUROIMMUN), both including AD and non-AD dementia/cognitive complaints were retrospectively retrieved in a single-center study. Interval-specific LRs for AD were calculated and validated for univariate and combined (Aß1-42/tTau and pTau181) biomarkers, and a continuous bivariate probability-based model for AD, plotting Aß1-42/tTau versus pTau181 was constructed and validated. RESULTS: LR for AD increased as individual CSF biomarker values deviated from normal. Interval-specific LRs of a combined biomarker model showed that once one biomarker became abnormal, LRs increased even further when another biomarker largely deviated from normal, as replicated in the validation cohort. A bivariate probability-based model predicted AD with a validated accuracy of 88% on a continuous scale. CONCLUSIONS: Interval-specific LRs in a combined biomarker model and prediction of AD using a continuous bivariate biomarker probability-based model, offer a more meaningful interpretation of CSF AD biomarkers on a (semi-)continuous scale with respect to the post-test probability of AD across different assays and cohorts.

AI for BPH Surgical Decision-Making: Cost Effectiveness and Outcomes.

PURPOSE OF REVIEW: Benign prostatic hyperplasia (BPH) is prevalent in nearly 70% of men over the age of 60, leading to significant clinical challenges due to varying symptom presentations and treatment responses. The decision to undergo surgical intervention is not straightforward; the American Urological Association recommends consideration of surgical treatment after inadequate or failed response to medical therapy. This review explores the role of artificial intelligence (AI), including machine learning and deep learning models, in enhancing the decision-making processes for BPH management. RECENT FINDINGS: AI applications in this space include analysis of non-invasive imaging modalities, such as multiparametric Magnetic Resonance Imaging (MRI) and Ultrasound, which enhance diagnostic precision. AI models also concatenate serum biomarkers and histopathological analysis to distinguish BPH from prostate cancer (PC), offering high accuracy rates. Furthermore, AI aids in predicting patient outcomes post-treatment, supporting personalized medicine, and optimizing therapeutic strategies. AI has demonstrated potential in differentiating BPH from PC through advanced imaging and predictive models, improving diagnostic accuracy, and reducing the need for invasive procedures. Despite promising advancements, challenges remain in integrating AI into clinical workflows, establishing standard evaluation metrics, and achieving cost-effectiveness. Here, we underscore the potential of AI to improve patient outcomes, streamline BPH management, and reduce healthcare costs, especially with continued research and development in this transformative field.

Current status and prospect of gut and oral microbiome in pancreatic cancer: Clinical and Translational Perspectives.

Pancreatic cancer is a highly lethal malignancy, and its diagnosis and treatment continue to pose significant challenges. Despite advancements in surgical and comprehensive treatment methods, the five-year survival rate remains below 12%. With the rapid development of microbiome science, the gastrointestinal microbiota, which is readily accessible, has emerged as a novel area of interest in pancreatic cancer research. Dysbiosis in these microbial communities can induce persistent inflammatory responses and affect the host's immune system, promoting cancer development and impacting the efficacy of treatments like chemotherapy and immunotherapy. This review delves into the roles of both gut and oral microbiota in the onset, progression, diagnosis, and treatment of pancreatic cancer. It analyzes the potential of utilizing these microbiomes as biomarkers and therapeutic targets from a clinical application perspective. Furthermore, it discusses future research directions aimed at harnessing these insights to advance the diagnosis and treatment strategies for pancreatic cancer. By focusing on the non-invasive sampling and accessibility of gut and oral microbiota, this review aims to provide an up-to-date overview of the microbiome's role in clinical and translational medicine for pancreatic cancer, offering insights into improving diagnosis and treatment outcomes.

Retrospective Study on Penicillin Allergy Delabeling and Evaluation of an Antibiotic Allergy Assessment Tool.

BACKGROUND: It has been reported that 95% of patients labeled as penicillin-allergic may be mislabeled. However, the process of delabeling has not advanced due to a shortage of allergy specialists capable of conducting accurate assessments. To address this issue, The Antibiotics Allergy Assessment Tool (AAAT) has been proposed as a tool to evaluate patients who can be delabeled by non-specialists. OBJECTIVE: This study aims to identify patients who can be delabeled and to evaluate patients who are likely to be delabeled using AAAT. METHODS: Patients admitted to the hospital between January 1, 2017, and December 31, 2021, with documented penicillin allergy labels were included in the study. Patients who demonstrated tolerance to labeled antibiotics or were labeled without explicit allergy declarations were defined as delabeling. Subsequently, patients who did not meet the criteria for delabeling were evaluated for their potential to be delabeled using the AAAT, retrospectively. RESULTS: 530 patients were selected, of which 62 (11.7%) were delabeled. The AAAT evaluation of the remaining patients indicated that at least an additional 137 (25.8%) patients could potentially be delabeled. CONCLUSION: The use of AAAT demonstrated the potential to delabel approximately third as many patients without the need for specialist evaluation. To promote broader delabeling efforts in the future, prospective studies should investigate the safety and effectiveness of evaluation tools such as the AAAT.

Prenatal Sonographic Features of Rubinstein-Taybi Syndrome-A Small Case Series of a Rare Syndrome.

Rubinstein-Taybi syndrome (RSTS) is a rare syndrome characterized by intellectual disability, distinctive facial features and distal limb abnormalities. RSTS is indicated by clinical features and confirmed via genetic testing. In this prenatal case series, we report four cases of RSTS with various sonographic features. Some features, such as corpus callosum dysgenesis, are nonspecific, but they may be the first sign apparent, as they appear early in pregnancy. Others, like beaked nose, shawl scrotum, premature coccygeal ossification, and overly mature scrotal sac with excessive rugae, are distinctive, but they may only be apparent in advanced gestation.

Sclerosing Odontogenic Carcinoma: UPLIFTS and pitfalls.

Sclerosing Odontogrenic Carcinoma (SOC) is a recent addition to the category of odontogenic tumours, which was first described by Koutlas et al. in 2008. It was described as primary intraosseous carcinoma with bland cytology, sclerotic stroma with presence of local infiltration showing aggressive behaviour. Following its discovery and the presentation of first case, only a handful of cases have been reported till date, which may be due to underreporting of the cases or inclusion of the case to other diagnosis since the features of this tumour overlaps with many other lesions of the oral cavity. Due to this factor, the pathogenesis of this category of tumours still remains enigmatic. The clinical features as a result of this factor are also not reported of the consistent type and overlaps with the already existing clinical features of other lesions. This lesion has only appeared till date twice in WHO classification of Odontogenic Cysts and Tumours. Thereby, the literature on this category is still in paucity. Therefore, the present review takes into account all of the features, diagnostic criteria and the markers discovered for this lesion and would provide an insight into whether this lesion is justified as a malignant lesion or should not be considered as a separate category of odontogenic tumour.

Evaluation of Pathology Resources for Cervical Cancer Detection Between 2018 & 2022: a Retrospective Study at Moi Teaching and Referral Hospital, Western Kenya.

Background: Cervical cancer cases are increasing in sub-Saharan Africa, particularly in Kenya, exacerbated by inadequate histopathology resources, posing a significant barrier to timely diagnosis and treatment. There has been little research on the availability and evolution of histopathology resources for diagnosing cervical cancer over the years. This retrospective study evaluated this evolution at Moi Teaching and Referral Hospital in Kenya between 2018 and 2022. Methods: We used a mixed-methods approach. An in-depth interview was conducted with one of MTRH's pathology laboratory staff to assess the equipment, personnel, and quality control trends between 2018 and 2022. A thematic analysis was conducted in NVivo. We also retrospectively conducted a comprehensive inventory review of laboratory resources from 2018-2022 via purposive sampling. Microsoft Excel and Stata version 17 were utilized for descriptive statistical analysis. Turnaround time (TAT) was assessed against the UK's National Health Service Cervical Screening Program guidelines. Results: The number of histopathology laboratory personnel at MTRH increased from 2018 to 2022, during which the facility included two pathologists, one records person, and one office administrator. Patient annual visits increased from approximately 350,000 in 2018 to approximately 500,000 in 2022. However, the histopathology personnel-to-population ratio decreased from 1.5 pathologists and 2.7 histo-technicians per 100,000 in 2018 to 1.4 pathologists and 1.8 histo-technicians per 100,000 in 2022. Despite this decrease, lab equipment, automatic tissue processors and embedding machines were added, and an average 14-day turnaround time was maintained for pathology reports. Conclusions: Despite a decreased personnel-to-patient ratio, the addition of crucial histopathology equipment mirrors the operational commitment of the Moi Teaching and Referral Hospital. The 14-day TAT is commendable, contributes to operational effectiveness and significantly contributes to timely detection. The hospital's dedication to upgrading its infrastructure underscores a proactive approach to addressing growing healthcare demands and improving patient outcomes, even with limited human resources. The decline in the personnel-to-patient ratio underscores challenges in diagnosis, emphasizing the need to address workforce and infrastructure gaps to improve patient care within similar low-resource settings.

Harnessing the potential of genomic characterization of mutational profiles to improve early diagnosis of lung cancer.

INTRODUCTION: Lung Cancer (LC) continues to be a leading cause of cancer-related mortality globally, largely due to the asymptomatic nature of its early stages and the limitations of current diagnostic methods such as Low-Dose Computed Tomography (LDCT), whose often result in late diagnosis, highlighting an urgent need for innovative, minimally invasive diagnostic techniques that can improve early detection rates. AREAS COVERED: This review delves into the potential of genomic characterization and mutational profiling to enhance early LC diagnosis, exploring the current state and limitations of traditional diagnostic approaches and the revolutionary role of Liquid Biopsies (LB), including cell-free DNA (cfDNA) analysis through fragmentomics and methylomics. New genomic technologies that allow for earlier detection of LC are scrutinized, alongside a detailed discussion on the literature that shaped our understanding in this field. EXPERT OPINION: Despite the promising advancements in genomic characterization techniques, several challenges remain, such as the heterogeneity of LC mutations, the high cost, and limited accessibility of Next-Generation Sequencing (NGS) technologies. Additionally, there is a critical need of standardized protocols for interpreting mutational data. Future research should focus on overcoming these barriers to integrate these novel diagnostic methods into standard clinical practice, potentially revolutionizing the management of LC patients.

The Distribution, Diversity, and Control of Dirofilariosis in Brazil: A Comprehensive Review.

Brazil's extensive coastline, tropical and subtropical climate, and well-preserved environment represent a conducive setting for dirofilariosis, a zoonotic mosquito-borne disease. Although this condition has long been recognised in the country, it has been relatively under-studied, and it is currently considered to be an emerging disease. Diagnosis, treatment, and control remain challenging due to the extensive gaps in knowledge. In order to help address this issue, this review aims to (i) summarise the available literature on the distribution of Dirofilaria spp. in Brazilian dogs over the last decade, (ii) review case reports of dirofilariosis in cats, wild animals, and humans over the last twenty years, and (iii) highlight the benefits of taking a One Health approach to managing this disease. While there have been several prevalence studies in dogs, disease distribution is poorly characterised in cats, and little is known about the occurrence of the parasite in wildlife. Human cases are sporadically reported, and no large-scale studies have been undertaken to date. Evidence indicates that Dirofilaria immitis is the main species circulating in Brazil, although Dirofilaria repens has also been detected. Molecular studies have also suggested the circulation of a highly virulent form of D. immitis, which may be genetically distinct from those of the Old World. A programme of epidemiological, ecological, genomic, and pathogenicity-based studies is required to quantify the impact of dirofilariosis in Brazil on both veterinary and public health and to inform others on its control.

Lesion Localization and Pathological Diagnosis of Ovine Pulmonary Adenocarcinoma Based on MASK R-CNN.

Ovine pulmonary adenocarcinoma (OPA) is a contagious lung tumour caused by the Jaagsiekte Sheep Retrovirus (JSRV). Histopathological diagnosis is the gold standard for OPA diagnosis. However, interpretation of traditional pathology images is complex and operator dependent. The mask regional convolutional neural network (Mask R-CNN) has emerged as a valuable tool in pathological diagnosis. This study utilized 54 typical OPA whole slide images (WSI) to extract 7167 typical lesion images containing OPA to construct a Common Objects in Context (COCO) dataset for OPA pathological images. The dataset was categorized into training and test sets (8:2 ratio) for model training and validation. Mean average specificity (mASp) and average sensitivity (ASe) were used to evaluate model performance. Six WSI-level pathological images (three OPA and three non-OPA images), not included in the dataset, were used for anti-peeking model validation. A random selection of 500 images, not included in the dataset establishment, was used to compare the performance of the model with assessment by pathologists. Accuracy, sensitivity, specificity, and concordance rate were evaluated. The model achieved a mASp of 0.573 and an ASe of 0.745, demonstrating effective lesion detection and alignment with expert annotation. In Anti-Peeking verification, the model showed good performance in locating OPA lesions and distinguished OPA from non-OPA pathological images. In the random 500-image diagnosis, the model achieved 92.8% accuracy, 100% sensitivity, and 88% specificity. The agreement rates between junior and senior pathologists were 100% and 96.5%, respectively. In conclusion, the Mask R-CNN-based OPA diagnostic model developed for OPA facilitates rapid and accurate diagnosis in practical applications.

Assessment of Thoracic Radiographic Alterations in Dogs with Heartworm and Their Correlation with Pulmonary Hypertension, Pre- and Post-Adulticide Treatment.

Pulmonary hypertension (PH) is a prevalent and severe complication in dogs infected with Dirofilaria immitis. This study aimed to elucidate the progression of PH by analyzing radiographic parameters and the Right Pulmonary Artery Distensibility (RPAD) Index at three key time points: diagnosis (day 0), discharge (day 90), and six months post-discharge (day 270). Fifty-two heartworm-infected dogs were divided into two groups: non-hypertensive and hypertensive. Radiographic measurements, including Vertebral Heart Size (VHS), CrPA/R4 ratio, and CdPA/R9 ratio, along with the RPAD Index, were assessed on Days 0, 90, and 270. Results indicated that, in Group A, the RPAD Index improved significantly from 42% on Day 0 to 43.16% on Day 90, with no significant change by Day 270 (42%). In contrast, hypertensive dogs exhibited a persistently low RPAD Index, averaging 17% throughout this study (p < 0.001). Radiographic parameters in hypertensive dogs showed continuous elevation compared to non-hypertensive dogs, with significant increases in VHS, CrPA/R4, and CdPA/R9 ratios on day 270 compared to day 0 (p < 0.05). The results confirmed that PH persisted in dogs with D. immitis after adulticide treatment, highlighting the importance of regular radiographic monitoring for assessing and managing long-term outcomes in dogs with PH during and after adulticide treatment. Continuous surveillance is thus essential for the effective post-treatment management of PH in dogs.

The Diagnosis of Wilkie's Syndrome Associated with Nutcracker Syndrome: A Case Report and Literature Review.

Superior mesenteric artery (SMA) syndrome or Wilkie's syndrome is a vascular compression disorder that causes the abnormal compression of the third portion of the duodenum by the SMA. It has a low incidence rate, which is higher in young women, and is rarely associated with the Nutcracker phenomenon: a condition of the compression of the left renal vein between the SMA and the aorta, which manifests as pain in the left flank and pelvis. Here, we report on the case of a 54-year-old woman with a history of repeated episodes of abdominal pain caused by the Nutcracker syndrome and Wilkie's syndrome.

AI-Enhanced ECG Applications in Cardiology: Comprehensive Insights from the Current Literature with a Focus on COVID-19 and Multiple Cardiovascular Conditions.

The application of artificial intelligence (AI) in electrocardiography is revolutionizing cardiology and providing essential insights into the consequences of the COVID-19 pandemic. This comprehensive review explores AI-enhanced ECG (AI-ECG) applications in risk prediction and diagnosis of heart diseases, with a dedicated chapter on COVID-19-related complications. Introductory concepts on AI and machine learning (ML) are explained to provide a foundational understanding for those seeking knowledge, supported by examples from the literature and current practices. We analyze AI and ML methods for arrhythmias, heart failure, pulmonary hypertension, mortality prediction, cardiomyopathy, mitral regurgitation, hypertension, pulmonary embolism, and myocardial infarction, comparing their effectiveness from both medical and AI perspectives. Special emphasis is placed on AI applications in COVID-19 and cardiology, including detailed comparisons of different methods, identifying the most suitable AI approaches for specific medical applications and analyzing their strengths, weaknesses, accuracy, clinical relevance, and key findings. Additionally, we explore AI's role in the emerging field of cardio-oncology, particularly in managing chemotherapy-induced cardiotoxicity and detecting cardiac masses. This comprehensive review serves as both an insightful guide and a call to action for further research and collaboration in the integration of AI in cardiology, aiming to enhance precision medicine and optimize clinical decision-making.

Inflammatory Protein Panel: Exploring Diagnostic Insights for Peripheral Artery Disease Diagnosis in a Cross-Sectional Study.

Cytokine-induced neutrophil chemoattractant 1 (CINC-1), a cluster of differentiation 95 (CD95), fractalkine, and T-cell immunoglobulin and mucin domain 1 (TIM-1) are circulating proteins known to be involved in inflammation. While their roles have been studied in neurological conditions and cardiovascular diseases, their potential as peripheral artery disease (PAD) biomarkers remain unexplored. We conducted a cross-sectional diagnostic study using data from 476 recruited patients (164 without PAD and 312 with PAD). Plasma levels of CINC-1, CD95, fractalkine, and TIM-1 were measured at baseline. A PAD diagnosis was established at recruitment based on clinical exams and investigations, defined as an ankle-brachial index < 0.9 or toe-brachial index < 0.67 with absent/diminished pedal pulses. Using 10-fold cross-validation, we trained a random forest algorithm, incorporating clinical characteristics and biomarkers that showed differential expression in PAD versus non-PAD patients to predict a PAD diagnosis. Among the proteins tested, CINC-1, CD95, and fractalkine were elevated in PAD vs. non-PAD patients, forming a 3-biomarker panel. Our predictive model achieved an AUROC of 0.85 for a PAD diagnosis using clinical features and this 3-biomarker panel. By combining the clinical characteristics with these biomarkers, we developed an accurate predictive model for a PAD diagnosis. This algorithm can assist in PAD screening, risk stratification, and guiding clinical decisions regarding further vascular assessment, referrals, and medical/surgical management to potentially improve patient outcomes.

Enhanced Immunohistochemistry Interpretation with a Machine Learning-Based Expert System.

BACKGROUND: In recent decades, machine-learning (ML) technologies have advanced the management of high-dimensional and complex cancer data by developing reliable and user-friendly automated diagnostic tools for clinical applications. Immunohistochemistry (IHC) is an essential staining method that enables the identification of cellular origins by analyzing the expression of specific antigens within tissue samples. The aim of this study was to identify a model that could predict histopathological diagnoses based on specific immunohistochemical markers. METHODS: The XGBoost learning model was applied, where the input variable (target variable) was the histopathological diagnosis and the predictors (independent variables influencing the target variable) were the immunohistochemical markers. RESULTS: Our study demonstrated a precision rate of 85.97% within the dataset, indicating a high level of performance and suggesting that the model is generally reliable in producing accurate predictions. CONCLUSIONS: This study demonstrated the feasibility and clinical efficacy of utilizing the probabilistic decision tree algorithm to differentiate tumor diagnoses according to immunohistochemistry profiles.