Use Of Algorithms Research Articles

Prediction of nonsustained ventricular tachycardia development by the analysis of premature ventricular complex-related intervals on 24-hour rhythm monitoring and testing a novel index

Abstract Introduction Ventricular tachycardia (VT) and ventricular fibrillation (VF) are life- threatening arrhythmias, with non-sustained ventricular tachycardia (NSVT) serving as a potential precursor. Identifying individuals at risk of NSVT is crucial for effective management and prevention of sudden cardiac death in high-risk patients. In daily clinical practice, premature ventricular complex (PVC) and sometimes NSVT are frequently detected on 24-hour ambulatory rhythm monitoring. Purpose In this study, we aimed to predict the development of NSVT by analyzing PVC morphology and intervals in 24- hour ambulatory rhythm monitorings. Methods A retrospective analysis of 24-hour ambulatory rhythm monitoring recordings from 2018 to 2023 was conducted. Inclusion criteria required clear measurement of PVC intervals, at least 100 PVC in the recording, and two preceding normal QRS beats. NSVT diagnosis was based on four consecutive PVC lasting <30 s and a rate >100/min. Various PVC-related parameters were analyzed, and new variables were derived. Statistical analysis included Mann-Whitney U tests and ROC analysis. Results The study included 202 patients, revealing significant differences in several VES temporal variables between groups with only PVC (Group I) and PVC with NSVT (Group II). Notably, Age-Adjusted Sum of Intervals Index (AASI Index-(100 x [(Tp-to- QRSvpa)+(coupling time)+(Qtc1)]/age), long coupling times, extended Tp-to-QRSvpaintervals, and prolonged Tpe-vpa intervals were associated with NSVT development. Age played a pivotal role in predicting NSVT when integrated into a specific variable AASI index. The optimal cut-off value was 4.21, with 84% sensitivity and specificity. Conclusion The study suggests that ventricular arrhythmias may be predicted using temporal parameters of PVC, especially when age is included as a modifier. The AASI index calculated on a PVC and preceeding two normal beats on 24-hour ambulatory rhythm monitoring seems to be promising parameter. These findings hold potential for future development of artificial intelligence-based algorithms for use in any PVC to identify at-risk patient groups, provided larger datasets are utilized to refine predictive models.Variables included in the analysis for cDefinitions of variables and ROC curve

Artificial Intelligence-Based Sentinel Lymph Node Metastasis Detection in Cervical Cancer

Background/objectives: Pathological ultrastaging, an essential part of sentinel lymph node (SLN) mapping, involves serial sectioning and immunohistochemical (IHC) staining in order to reliably detect clinically relevant metastases. However, ultrastaging is labor-intensive, time-consuming, and costly. Deep learning algorithms offer a potential solution by assisting pathologists in efficiently assessing serial sections for metastases, reducing workload and costs while enhancing accuracy. This proof-of-principle study evaluated the effectiveness of a deep learning algorithm for SLN metastasis detection in early-stage cervical cancer. Methods: We retrospectively analyzed whole slide images (WSIs) of hematoxylin and eosin (H&E)-stained SLNs from early-stage cervical cancer patients diagnosed with an SLN metastasis with either H&E or IHC. A CE-IVD certified commercially available deep learning algorithm, initially developed for detection of breast and colon cancer lymph node metastases, was employed off-label to assess its sensitivity in cervical cancer. Results: This study included 21 patients with early-stage cervical cancer, comprising 15 with squamous cell carcinoma, five with adenocarcinoma, and one with clear cell carcinoma. Among these patients, 10 had macrometastases and 11 had micrometastases in at least one SLN. The algorithm was applied to evaluate H&E WSIs of 47 SLN specimens, including 22 that were negative for metastasis, 13 with macrometastases, and 12 with micrometastases in the H&E slides. The algorithm detected all H&E macro- and micrometastases with 100% sensitivity. Conclusions: This proof-of-principle study demonstrated high sensitivity of a deep learning algorithm for detection of clinically relevant SLN metastasis in early-stage cervical cancer, despite being originally developed for adenocarcinomas of the breast and colon. Our findings highlight the potential of leveraging an existing algorithm for use in cervical cancer, warranting further prospective validation in a larger population.

Recommendations for early identification of heart failure in patients with diabetes: Consensus statement of the Swiss Society of Endocrinology and Diabetology and the Heart Failure Working Group of the Swiss Society of Cardiology.

Diabetes is a well-recognised risk factor for the development of heart failure, with a prevalence higher than 30% in patients with diabetes aged over 60 years. Heart failure often emerges as the primary cardiovascular manifestation in patients with type 2 diabetes and appears to be even more prevalent in type 1 diabetes. In Switzerland, there are approximately 500,000 individuals with diabetes, and the number of affected people has been steadily rising in recent years. Therefore, the consequences of heart failure will affect an increasing number of patients, further straining the Swiss healthcare system. Early lifestyle modification and initiation of appropriate treatment can prevent or at least significantly delay the onset of symptomatic heart failure by several years. These facts underscore the urgent need for early detection of individuals with subclinical heart failure, which often remains undiagnosed until the first episode of acute heart failure requiring hospital admission occurs. To address this issue, the European Society of Cardiology, the American Diabetes Association (ADA) and other international professional societies have published recommendations on heart failure screening, diagnosis and management. To address this issue in Switzerland, experts from the Swiss Society of Endocrinology and Diabetology, the Swiss Society of Cardiology and the General Internal Medicine specialty met and prepared a consensus report including a simple diagnostic algorithm for use in everyday practice.

Recommended Minimum Elements for Transparent Reporting of Multi-Jurisdiction Algorithm Feasibility Studies

BackgroundResearch and surveillance using routinely collected health data rely on algorithms to ascertain disease cases or health measures. Where algorithm validation studies are not possible due to lack of a reference standard, algorithm feasibility studies can be used to create and assess algorithms for use in more than one population or jurisdiction. Publication of the methods used to conduct feasibility studies is critical for transparency and reproducibility. Existing guidelines applicable to feasibility studies, including the STrengthening the Reporting of OBservational studies in Epidemiology (STROBE) and REporting of studies Conducted using Observational Routinely collected health Data (RECORD) statements, may benefit from additional elements to capture aspects particular to multi-jurisdiction algorithm feasibility studies and ensure full reproducibility. MethodsA subcommittee of members from Health Data Research Network (HDRN) Canada’s Algorithms and Harmonized Data Working Group (AHD-WG) reviewed items within the STROBE and RECORD guidelines and compared these to published feasibility studies. Items not contained within STROBE or RECORD but recommended to ensure transparent reporting of feasibility studies were identified. The AHD-WG reviewed and approved these additional recommended elements. ResultsEleven additional recommended elements were identified: one element for the title and abstract, one in the introduction, five in the methods, and four in the results sections. Elements primarily addressed reporting jurisdictional data variabilities, data harmonization methods, and algorithm implementation. SignificanceImplementation of these recommended elements, alongside the RECORD guidelines, is intended to encourage consistent publication of methods that support reproducibility, as well as increase comparability and international collaborations.

Sd fgsdrte yruetuy fgsdf gsfg jhtuert yf yjkpç98olyuikyujthgbdfvs gfwetr yhry jh

x

Data Mining Virtual Contaminated Sites to Develop an Educational Learning Tool supported by a k-NN Machine Learning Predictive Algorithm for use in Environmental Engineering Education

Recent work by Mumford et al. used high-resolution numerical simulations of contaminated sites to evaluate the state of practice for contaminated site investigation1. These simulations were originally developed in collaboration with academic and industry partners, including the U.S. Department of Defense's Environmental Security Technology Certification Program (ESTCP), as a training tool for environmental monitoring and performance optimization. This project focuses on the development of an algorithm to determine available borehole information in those simulations based on user-input, to help leverage this work to create an educational tool. The algorithm begins by validating user-specified coordinates to ensure they fall within an acceptable range. Leveraging principles from linear algebra and a grid-based mapping system, it identifies the nearest existing borehole on a predefined coordinate grid. To optimize efficiency, the algorithm utilizes a 2-D array to store and retrieve coordinate data. It calculates distances from the input coordinates to all available borehole locations on the grid, to identify the shortest distance and select the closest borehole, enabling students to map contamination within virtual sites. In addition to boreholes, the application incorporates data for Membrane Interface Probes (MIPs), monitoring wells, groundwater samples, and soil samples that are used to investigate contaminated sites, providing a comprehensive tool for training environmental professionals. The k-nearest neighbors (k-NN) algorithm predicts Membrane Interface Probe (MIP) Photoionization Detector (ECD) readings at future locations, which indicate chlorinated contaminant levels. Two models were evaluated: one using spatial data and ECD values, and another incorporating electrical conductivity (EC) and hydraulic conductivity (K), which are also measured by MIP. By making use of additional parameters, variations in soil properties were better represented, leading to more accurate predictions. Through iterative testing and refinement, the tool’s accuracy and user-interface have been enhanced, ensuring robust reliability for classroom applications. These tools are slated for integration into 4th-year subsurface contamination courses at Queen's University, Carleton, and the University of Iowa. By automating borehole selection, instructors can interact more with students and dedicate less time to data processing tasks. The k-NN application will enable the use of machine learning for site assessment to optimize MIP instrument placement to reduce bias. Assistance from Cole Van De Ven (Carleton University) and Jessica Meyer (University of Iowa) in collecting virtual contaminated site data is gratefully acknowledged.

A view of the issues of etiology and pathogenesis of clinical conditions of burning in the oral cavity: an actual problem of therapeutic dentistry

Background. The issue of burning in the oral cavity without damage against the background of various etiological factors and clinical manifestations is a difficult task for doctors and requires an integrated interdisciplinary approach. Despite the array of developments, the issue of unification of clinical signs and the examination algorithm for use in a doctor’s practice remains relevant. Materials and methods. The research is to analyze literature sources based on Scopus, Web of Science, PubMed databases, the study of which does not exceed 5 years, inclu­ding literature reviews and the results of clinical studies. Results. The work presents an analytical generalization of clinical criteria for the diagnosis of paresthetic conditions of the oral mucosa, which will allow for timely and professional diagnosis of these diseases in the daily dentist’s practice. In the first place during the analysis of etiological factors of burning sensation in the oral cavity, there is a violation of the interaction of psychological factors and neurophysiological components and an imbalance exactly of the autonomic innervation of the oral mucosa. ­Conclusions. Clinical conditions of burning sensations in the oral cavity should be considered as a multidisciplinary problem that requires the integration of physicians of different specialties.

Uncertainties in Plant Species Niche Modeling under Climate Change Scenarios

Species distribution models (SDMs) have been used to forecast the impact of climate change on species’ potential distribution, with results that might support decisions for conservation and biodiversity management. Despite their vulnerability to parameterization and data quality input, SDM use has been increasing in the last decades. In fact, inappropriate inputs and the lack of awareness about the effects of methodological decisions on results can lead to potential unreliability in results, a problem that might gain relevance when SDMs are used to predict climate change impacts on species-suitable areas. Aiming to assess how far such a topic is considered, an analysis of the calibration data and methodological decisions was conducted for recent publications (2018 to 2022) that include SDMs in this context, aiming to identify putative deviations from the consensual best practices. Results show that the parameters presented more consistently are the algorithm in use (MaxEnt was used in 98% of the studies), the accuracy measures, and the time windows. But many papers fail to specify other parameters, limiting the reproducibility of the studies. Some papers fail to provide information about calibration procedures, others consider only a fraction of the species’ range, and others provide no justification for including specific variables in the model. These options can decrease reliability in predictions under future scenarios, since data provided to the model are inaccurate from the start or there is insufficient information for output discussion.

On the optimality of voronoi‐based column selection

AbstractWhile there exists a rich array of matrix column subset selection problem (CSSP) algorithms for use with interpolative and CUR‐type decompositions, their use can often become prohibitive as the size of the input matrix increases. In an effort to address these issues, in earlier work we developed a general framework that pairs a column‐partitioning routine with a column‐selection algorithm. Two of the four algorithms presented in that work paired the Centroidal Voronoi Orthogonal Decomposition (CVOD; Centroidal Voronoi Tessellation Based Proper Orthogonal Decomposition Analysis, 2003, 137–150) and an adaptive variant (adaptCVOD) with the Discrete Empirical Interpolation Method (DEIM; SIAM J. Sci. Computer. 38 (2016), no. 3, A1454–A1482). In this work, we extend this framework and pair the CVOD‐type algorithms with any CSSP algorithm that returns linearly independent columns. Our results include detailed error bounds for the solutions provided by these paired algorithms, as well as expressions that explicitly characterize how the quality of the selected column partition affects the resulting CSSP solution. In addition to examples involving matrix approximation, we test several of our partition‐based constructions on tasks commonly encountered in model order reduction (MOR).

Electrical conductivity based algorithm for precise application of liquid nitrogenous fertilizers

Precise application of nitrogenous fertilizers mainly urea ammonium nitrate (UAN) and granular urea (both pure and neem-coated) in aqueous form, is critically important for basal and foliar applications. The physicochemical properties of aqueous solution of these nitrogenous fertilizers plays important role in design of any liquid fertilizer application system. The study was carried out during 2019–20 at ICAR-Indian Agricultural Research Institute, New Delhi with an aim to develop algorithms for use in sensors-based systems for real time monitoring of available N concentration in the fertilizer solution before its application. The physicochemical properties like pH, electrical conductivity (EC), specific gravity (SG), dynamic viscosity (DV), surface tension (ST) and percentage light absorbance (LA) of urea ammonium nitrate (UAN-28%), pure urea, and neem coated urea in diluted form (pre-selected N-concentrations i.e. 0.78, 0.9, 1.08, 1.33, 1.75, 2.54 and 4.67% corresponding to the dilution ratios of 1:35, 1:30, 1:25, 1:20, 1:15, 1:10 and 1:05) were measured and analyzed for their significance with N-concentration. Electrical conductivity (EC) alone showed a significant relationship with N-concentrations. Prediction models were developed for diluted UAN and granular urea fertilizers based on the EC and N-concentrations. The regression models in terms of EC to predict N-concentration had coefficients of determination (R2) of 0.998, 0.998, and 0.999 for diluted UAN, pure urea, and neem coated urea with water, respectively showed a great potential for their sensor based precise application. The controlled application of diluted liquid fertilizers with water can be achieved through sensing relevant physicochemical property.

Development of a Tremor Detection Algorithm for Use in an Academic Movement Disorders Center.

Tremor, defined as an "involuntary, rhythmic, oscillatory movement of a body part", is a key feature of many neurological conditions including Parkinson's disease and essential tremor. Clinical assessment continues to be performed by visual observation with quantification on clinical scales. Methodologies for objectively quantifying tremor are promising but remain non-standardized across centers. Our center performs full-body behavioral testing with 3D motion capture for clinical and research purposes in patients with Parkinson's disease, essential tremor, and other conditions. The objective of this study was to assess the ability of several candidate processing pipelines to identify the presence or absence of tremor in kinematic data from patients with confirmed movement disorders and compare them to expert ratings from movement disorders specialists. We curated a database of 2272 separate kinematic data recordings from our center, each of which was contemporaneously annotated as tremor present or absent by a movement physician. We compared the ability of six separate processing pipelines to recreate clinician ratings based on F1 score, in addition to accuracy, precision, and recall. The performance across algorithms was generally comparable. The average F1 score was 0.84±0.02 (mean ± SD; range 0.81-0.87). The second highest performing algorithm (cross-validated F1=0.87) was a hybrid that used engineered features adapted from an algorithm in longstanding clinical use with a modern Support Vector Machine classifier. Taken together, our results suggest the potential to update legacy clinical decision support systems to incorporate modern machine learning classifiers to create better-performing tools.

Comparative Efficiency Analysis of Hashing Algorithms for Use in zk-SNARK Circuits in Distributed Ledgers

Comparative Efficiency Analysis of Hashing Algorithms for Use in zk-SNARK Circuits in Distributed Ledgers

Using Video Technology and AI within Parkinson's Disease Free-Living Fall Risk Assessment.

Falls are a major concern for people with Parkinson's disease (PwPD), but accurately assessing real-world fall risk beyond the clinic is challenging. Contemporary technologies could enable the capture of objective and high-resolution data to better inform fall risk through measurement of everyday factors (e.g., obstacles) that contribute to falls. Wearable inertial measurement units (IMUs) capture objective high-resolution walking/gait data in all environments but are limited by not providing absolute clarity on contextual information (i.e., obstacles) that could greatly influence how gait is interpreted. Video-based data could compliment IMU-based data for a comprehensive free-living fall risk assessment. The objective of this study was twofold. First, pilot work was conducted to propose a novel artificial intelligence (AI) algorithm for use with wearable video-based eye-tracking glasses to compliment IMU gait data in order to better inform free-living fall risk in PwPD. The suggested approach (based on a fine-tuned You Only Look Once version 8 (YOLOv8) object detection algorithm) can accurately detect and contextualize objects (mAP50 = 0.81) in the environment while also providing insights into where the PwPD is looking, which could better inform fall risk. Second, we investigated the perceptions of PwPD via a focus group discussion regarding the adoption of video technologies and AI during their everyday lives to better inform their own fall risk. This second aspect of the study is important as, traditionally, there may be clinical and patient apprehension due to ethical and privacy concerns on the use of wearable cameras to capture real-world video. Thematic content analysis was used to analyse transcripts and develop core themes and categories. Here, PwPD agreed on ergonomically designed wearable video-based glasses as an optimal mode of video data capture, ensuring discreteness and negating any public stigma on the use of research-style equipment. PwPD also emphasized the need for control in AI-assisted data processing to uphold privacy, which could overcome concerns with the adoption of video to better inform IMU-based gait and free-living fall risk. Contemporary technologies (wearable video glasses and AI) can provide a holistic approach to fall risk that PwPD recognise as helpful and safe to use.

Creation of a prototype simulator object for quality control of bone segmentation algorithms for use in tomographic post-processing software

Considering the growing influence of Artificial Intelligence (AI) in medicine, especially in radiology, and the advances in computational power and theoretical understanding of AI algorithms (MESKÓ; GÖRÖG, 2020), concerns about the reliability of these methods arise. This study developed a prototype simulator object for quality control of bone segmentation algorithms in computed tomography. To achieve this objective, a 3D simulator object was created using advanced printing techniques, with materials that faithfully replicate the density and hardness of human bones, such as RadioMatrix. The results indicated that bone segmentation in post-processing software is strongly influenced by tissue density and that currently available AI models lack explainability (EXAI). The analysis revealed the need for algorithms that consider not only density but also the specific shapes and characteristics of bones. It is concluded that the developed prototype is effective in the evaluation and quality control of bone segmentation algorithms, promoting greater safety in clinical application and better explainability of bone segmentation algorithms in post-processing software for computed tomography.

Body Composition and Energy Expenditure in Youth With Spina Bifida: Protocol for a Multisite, Cross-Sectional Study.

Obesity prevalence in youth with spina bifida is higher than in their typically developing peers. Obesity is associated with lifelong medical, psychological, and economic burdens. Successful prevention or treatment of obesity in individuals with spina bifida is compromised by (1) the lack of valid and reliable methods to identify body fat in a clinical setting and (2) limited data on energy expenditure that are necessary to provide daily caloric recommendations. The objectives of this study will be to develop 2 algorithms for use in youth with spina bifida in a clinical setting, one to model body fat and one to predict total daily energy expenditure. In addition, physical activity and dietary intake will be described for the sample. This multisite, prospective, national clinical study will enroll 232 youth with myelomeningocele aged 5 to 18 years (stratified by age and mobility). Participants will be enrolled for 1 week. Data obtained include 4 measures of body composition, up to 5 height measures, a ramped activity protocol, and a nutrition and physical activity screener. Participants will wear an accelerometer for the week. On the final study day, 2 samples of urine or saliva, which complete the doubly labeled water protocol, will be obtained. The analysis will include descriptive statistics, Bland-Altman plots, concordance correlation, and regression analysis. The study received extramural federal funding in July 2019. Data collection was initiated in March 2020. As of April 2024, a total of 143 (female participants: n=76, 53.1%; male participants: n=67, 46.9%) out of 232 participants have been enrolled. Data collection is expected to continue throughout 2024. A no-cost extension until November 2025 will be requested for data analysis and dissemination of findings. This study furthers previous pilot work that confirmed the acceptability and feasibility of obtaining alternate height, body composition, and energy expenditure measures. The findings from this study will enhance screening, prevention, and treatment of abnormal weight status by facilitating the accurate identification of youths' weight status category and recommendations of daily caloric needs for this population that is at higher risk of obesity. Furthermore, the findings have the potential to impact outcomes for youth diagnosed with disabilities other than spina bifida who experience similar challenges related to alterations in body composition or fat distribution or measurement challenges secondary to mobility issues or musculoskeletal problems. DERR1-10.2196/52779.

Decision support for prioritizing critical societal services in optimal post-disaster critical lifeline recovery

AbstractCritical societal services, such as health care, education, law enforcement, and emergency response, are key to societal well-being and safety. Disruption to these services may arise from direct damage to the buildings from which the services are provided, or indirectly as a consequence of damage to supporting lifelines. The order in which lifeline elements are restored post-disaster affects not only the timing for restoring the lifeline services to its customers, but also the timing for restoring critical services that rely on these lifelines. In this paper, a mathematical formulation of the problem of prioritizing critical societal services in lifeline service restoration treated by multiple, specialized crews and exact algorithmic approach for its solution are proposed. Two approaches to accelerate the solution algorithm for use in realistic settings, where efficiency and scalability are essential, are presented. The developed techniques can be embedded in a decision support tool for real-time application with real-time information. To illustrate the proposed modeling and solution methodology and assess its efficiency for large, complex multi-lifeline applications, numerical experiments were run on a synthetic yet real-world network involving three key lifelines, including power, water, and transportation, as well as two hospitals that rely on them. The analysis of this case study shows that cross-lifeline collaboration in prioritization and scheduling in restoration action affects not only the return of services from the individual lifelines, but also of critical services on which, particularly in disaster settings, lives may depend.

The Detection of Railheads: An Innovative Direct Image Processing Method

This study presents a fully automated railhead detection method based on a direct image processing algorithm for use on a railway track. This method functions at a much faster pace than artificial intelligence algorithms that process rail images on embedded systems or low-power devices, as it does not require the use of significant computing resources. With the use of this method, railheads can be analyzed to identify the presence of cracks and other defects. We converted color images to halftone images, performed histogram equalizations to improve the contrast, applied a Gaussian filter to reduce the presence of noise, utilized convolutional filters to extract any vertical and horizontal lines, applied the Canny method and Sobel filters to refine the boundaries of the extracted lines, applied the Hough transform technique to extract lines belonging to the railhead images, and identified the segments with the highest brightness values to process the images of the railheads under study. The method of railhead separation described in this article will allow for further comprehensive diagnostics of the condition of rail threads to ensure the safe and sustainable operation of railway transport. The implementation of intelligent maintenance systems and effective monitoring of railway track conditions can reduce the negative impact on the environment and contribute to the advancement of rail transport as a sustainable, safe, and more environmentally friendly mode of transportation.

A systematic review on research utilising artificial intelligence for open source intelligence (OSINT) applications

This paper presents a systematic review to identify research combining artificial intelligence (AI) algorithms with Open source intelligence (OSINT) applications and practices. Currently, there is a lack of compilation of these approaches in the research domain and similar systematic reviews do not include research that post dates the year 2019. This systematic review attempts to fill this gap by identifying recent research. The review used the preferred reporting items for systematic reviews and meta-analyses and identified 163 research articles focusing on OSINT applications leveraging AI algorithms. This systematic review outlines several research questions concerning meta-analysis of the included research and seeks to identify research limitations and future directions in this area. The review identifies that research gaps exist in the following areas: Incorporation of pre-existing OSINT tools with AI, the creation of AI-based OSINT models that apply to penetration testing, underutilisation of alternate data sources and the incorporation of dissemination functionality. The review additionally identifies future research directions in AI-based OSINT research in the following areas: Multi-lingual support, incorporation of additional data sources, improved model robustness against data poisoning, integration with live applications, real-world use, the addition of alert generation for dissemination purposes and incorporation of algorithms for use in planning.

An unsupervised H&E-based machine-learning approach for precise prediction of tumor microenvironment subtypes.

e13593 Background: Precision oncology increasingly relies on accurate classification of the tumor microenvironment (TME), which influences therapeutic responses and prognostication in cancer. While histological observation via H&E staining remains the gold standard due to the detailed spatial context and morphological information provided, its lack of reproducibility limits its use in clinics. Next-generation sequencing (NGS) reliably provides valuable insights into the molecular landscape of tumors. Here we debut an unsupervised machine-learning approach that leverages both the rich detail in H&E slides and the reproducibility of NGS to enhance TME classification. Methods: An ML-based image analysis algorithm was developed using a convolutional neural network (CNN) deep learning model. Using over 600 images from the TCGA COAD and READ datasets and from 139 colorectal cancer (CRC) samples in an internal cohort, we trained the CNN model to curate features from small patches of whole slide images (WSIs). Then, clusters were created from these H&E WSIs without prior labeling. The clusters were validated by experienced pathologists to confirm cluster homogeneity and filter artifacts. We trained a classifier to categorize molecular features from the WSIs into TME subtypes. Performance was measured using the area under the receiver operating characteristic curve (AUC-ROC), based on the model's ability to correctly classify the Fibrotic (F) and Immune Desert (D) TME subtypes (1), as well as MSI status identified by whole exome sequencing. The F subtype corresponds with high stromal content, low immune infiltration, and the worst prognosis. The D subtype corresponds with a cold immune TME and an intermediate prognosis. Progression-free survival (PFS) data from TCGA were used to examine prognostic significance. Results: We obtained 0.86, 0.79, 0.72, and 0.71 AUC scores for predicting the ID and F TMEs, MSI status, and KRAS mutation status, respectively. PFS data analysis showed our H&E-based approach to yield similar or better prognostic significance compared to NGS-based TME classification (ID vs others, p=0.05 (H&E) and 0.2 (NGS); F vs others, p=0.07 (H&E) and 0.09 (NGS)). Our findings showed a notable correlation with RNA- and DNA-based predictions of ID and F TMEs and MSI, with enhanced precision and more robust subtype identification while achieving high embedding consistency. Conclusions: By harnessing the inherently rich detail in histological images, our H&E-based approach complements NGS-based TME analysis. Our findings advocate for the integration of advanced image analysis into the standard TME characterization workflow to refine prognostic and therapeutic strategies for CRC. We will expand this algorithm for use with other cancer types to realize its potential as a promising adjunct to NGS for precise TME classification. 1. Bagaev et al., 2021.

EmoTunes: Your Emotional Soundtrack

The human face is an important organ of an individual’s body and it especially plays an important role in extraction of an individual‘s behavior and emotional state. Manually segregating the list of songs and generating an appropriate playlist based on an individual’s emotional features is a very tedious, time consuming, labor intensive and upheld task. Various algorithms have been proposed and developed for automating the playlist generation process.However the proposed existing algorithms in use are computationally slow, less accurate and sometimes even require use of additional hardware like EEG or sensors. This proposed system based on facial expression extracted will generate a playlist automatically thereby reducing the effort and time involved in rendering the process manually. Thus the proposed system tends to reduce the computational time involved in obtaining the results and the overall cost of the designed system, thereby increasing the overall accuracy of the system. Testing of the system is done on both user dependent (dynamic) and user independent (static) dataset. Facial expressions are captured using an inbuilt camera. The accuracy of the emotion detection algorithm used in the system for real time images is around 85-90%, while for static images it is around 98- 100%.The proposed algorithm on an average calculated estimation takes around 0.95-1.05 sec to generate an emotion based music playlist. Thus, it yields better accuracy in terms of performance and computational time and reduces the designing cost, compared to the algorithms used in the literature survey. Keywords—Audio Emotion Recognition, Music Information Retrieval, Emotion Extraction Module, Audio Feature Extraction Module, Artificial Neural Networks, Confusion Matrix, Viola and Jones Face Detection