Role of artificial intelligence and vibrational spectroscopy in cancer diagnostics

Estimation of Life Expectancy and the Expected Years of Life Lost in Patients with Major Cancers: Extrapolation of Survival Curves under High-Censored Rates

Background. The current best predictor of lifetime risk for many forms of cancer is family history. Family history is transmitted through germ line DNA. Analysis of germ-line DNA should be able to predict lifetime risk at least as well family history. Genetic risk scores, used to predict lifetime risk from DNA, usually consist of linear combinations of SNPs. These scores ignore structural variations and epistatic effects (non-linear combinations). The objective of this study is to test whether germline DNA structural information along with machine learning algorithms, which can use non-linear combinations, can be used to predict whether a person will develop different types of cancer. Methods. We tested this objective using data compiled by The Cancer Genome Atlas (TCGA) project and the UK Biobank. The TCGA data consisted of information on DNA chromosome scale length variation extracted from the peripheral blood of 8,821 different patients, each of whom had one of 32 different types of cancer. The UK Biobank data consisted of about 1500 women diagnosed with breast cancer (cases) and about 5000 women who have no record of any type of cancer(controls). We characterized structural variation by a quantitative measure of chromosomal-scale length variation. Chromosomal-scale length variation is computed from array data. A person's DNA (chromosomes 1-22) can be characterized by a series of 22 numbers, each representing the log base 2 ratio of the chromosome's length compared to the average chromosome length. Using these 22 numbers for each person, we set up a machine learning classification problem to differentiate those people diagnosed with a particular form of cancer from those who have not been diagnosed with that cancer. We used the h2o libraries in R to test how well different machine-learning algorithm can classify with these datasets. Results. In two independent datasets, the Cancer Genome Atlas (TCGA) project and the UK Biobank, we could classify whether or not a patient had a certain cancer based solely on chromosomal scale length variation. We found that all 32 different types of cancer in the TCGA dataset tested could be predicted better than chance using structural variation data. Specifically, in the TCGA dataset we measured the area under the receiver operator curve, known as the AUC, for ovarian cancer in women (0.89), glioblastoma multiforme (0.86), breast cancer in women (0.75), and colon adenocarcinoma (0.79), with a 95% confidence interval width of less than 0.01 in each case. This method could predict 10% of glioblastoma multiforme cases with less than 1 in 10,000 false positives in the TCGA dataset. In the UK Biobank dataset, we could predict breast cancer in women with an AUC=0.83. Conclusion. Genetic risk scores based on structural variation can effectively predict whether a person will eventually develop may different types of cancer. Citation Format: Chris Toh, Charmeine Ko, James P. Brody. Genetic risk scores from structural variation predict life-time individual cancer risk [abstract]. In: Proceedings of the Annual Meeting of the American Association for Cancer Research 2020; 2020 Apr 27-28 and Jun 22-24. Philadelphia (PA): AACR; Cancer Res 2020;80(16 Suppl):Abstract nr 2317.

Artificial intelligence (AI) is transforming ophthalmology by leveraging machine learning (ML) and deep learning (DL) techniques, particularly artificial neural networks (ANN) and convolutional neural networks (CNN) to mimic human brain functions and enhance accuracy through data exposure. These AI systems are particularly effective in analyzing ophthalmic images for early disease detection, improving diagnostic precision, streamlining clinical workflows, and ultimately enhancing patient outcomes. This study aims to explore the specific applications and impact of AI in the fields of glaucoma, corneal diseases, and oculoplastics. This study reviews current AI technologies in ophthalmology, examining the implementation of ML and DL techniques. It evaluates AI's role in early disease detection, diagnostic accuracy, clinical workflow enhancement, and patient outcomes. AI has significantly advanced the early detection and management of various ocular conditions. In glaucoma, AI systems provide standardized, rapid identification of disease characteristics, reducing intra- and interobserver bias and workload. For corneal diseases, AI tools enhance diagnostic methods for conditions such as keratitis and keratoconus, improving early detection and treatment planning. In oculoplastics, AI assists in the diagnosis and monitoring of eyelid and orbital diseases, facilitating precise surgical planning and postoperative management. The integration of AI in ophthalmology has revolutionized eye care by enhancing diagnostic precision, streamlining clinical workflows, and improving patient outcomes. As AI technologies continue to evolve, their applications in ophthalmology are expected to expand, offering innovative solutions for the diagnosis, monitoring, treatment, and surgical outcomes of various eye conditions.

The article presents the results of the study conducted by the author in the field of sovereign social ecology using artificial intelligence technologies. The issues of social ecology implemented on the basis of strategic programs and national projects are considered. A number of environmental programs aimed at protecting the environment and stimulating sustainable development are shown. The role of artificial intelligence (AI) in solving issues of social ecology, which is carried out through environmental monitoring, natural resource management and environmental education, is determined. The key aspects of the use of artificial intelligence (AI) technologies when they are implemented in certain areas of activity are identified. The role of generative artificial intelligence (GAI) in the implementation of social ecology technologies is shown, examples of the use of generative AI in this area are given. The prospects for the implementation of social ecology technologies in Russia and the world are shown.

114 Road traffic injury prevention: the role of artificial intelligence

Artificial intelligence (AI) is revolutionizing various sectors, including healthcare, with significant advancements in early cancer detection. Traditional methods like biopsy and imaging, though widely used, have limitations in sensitivity and invasiveness. AI, with its ability to analyze vast datasets and identify complex patterns, offers new opportunities to enhance early diagnosis accuracy. This paper discusses AI techniques, including machine learning and deep learning, applied to cancer detection, highlighting their advantages, challenges, and potential. It also explores AI-driven case studies demonstrating significant improvements in screening accuracy and patient outcomes. The paper concludes by emphasizing the future role of AI in transforming cancer diagnostics and improving survival rates. Keywords: Artificial intelligence, early cancer detection, machine learning, deep learning, cancer diagnostics.

Artificial Intelligence in the American Healthcare Industry: Looking Forward to 2030

Biomarkers that can differentiate between normal and tumor state, and can be measured in easily accessible body fluids such as blood and urine, can be very important for cancer diagnostics and disease monitoring. MicroRNAs (miRNAs), short non-coding regulatory RNA molecules, are attractive as biomarkers because they are stable in different conditions and are easy to measure with quantitative PCR (qPCR) methods. In this study we aimed to identify a universal panel of miRNAs for cancer screening that can be easily tested in the serum of healthy individuals and patients with different types of cancer. First, we measured expression of ∼800 miRNAs in 40 controls and 60 patients with bladder, breast or prostate cancer using the low density TaqMan expression arrays (Applied Biosystems) and starting from 250 ul of serum. Based on these results we selected a panel of 24 miRNAs that showed best discrimination between normal and cancer samples. These miRNAs were then re-tested as a custom-designed mini-panel in serum samples of 44 healthy controls and cancer patients (31 bladder, 25 breast and 28 prostate) and in relevant normal and tumor tissue samples (42 normal bladder and 43 bladder tumors, 44 normal breast and 42 breast tumors and in 50 normal prostate and 20 prostate tumors). Only miRNAs that expressed in the same direction in serum and tissue samples and showed significant association with cancer in both sample types were used for further analysis. The current panel consists of 16 miRNAs – 14 targets, one positive control and one negative control. Using this panel on serum samples from 44 controls, 31 bladder cancer patients, 25 breast cancer patients and 28 prostate cancer patients we performed ROC analysis and achieved complete discrimination (AUC ∼1.0) between all types of cancers and controls and good discrimination between different types of cancers (minimal AUC 0.89 for breast and bladder samples). Our results prove that miRNA detection from serum might be a promising method of cancer detection. Currently, we are performing validation studies in independent sets of samples. A combination of information on genetic susceptibility factors identified by genome-wide association studies (GWAS), other cancer-specific factors such as PSA for prostate cancer and miRNA expression profiling, might provide additional tools for early disease diagnostics and help to guide treatment options. Citation Format: {Authors}. {Abstract title} [abstract]. In: Proceedings of the 102nd Annual Meeting of the American Association for Cancer Research; 2011 Apr 2-6; Orlando, FL. Philadelphia (PA): AACR; Cancer Res 2011;71(8 Suppl):Abstract nr LB-350. doi:10.1158/1538-7445.AM2011-LB-350

Machine Learning (ML), a subset of Artificial Intelligence (AI), is gaining popularity in the architectural, engineering, and construction (AEC) sector. This systematic study aims to investigate the roles of AI and ML in improving construction processes and developing more sustainable communities. This study intends to determine the various roles played by AI and ML in the development of sustainable communities and construction practices via an in-depth assessment of the current literature. Furthermore, it intends to predict future research trends and practical applications of AI and ML in the built environment. Following the Preferred Reporting Items for Systematic Reviews (PRISMA) guidelines, this study highlights the roles that AI and ML technologies play in building sustainable communities, both indoors and out. In the interior environment, they contribute to energy management by optimizing energy usage, finding inefficiencies, and recommending modifications to minimize consumption. This contributes to reducing the environmental effect of energy generation. Similarly, AI and ML technologies aid in addressing environmental challenges. They can monitor air quality, noise levels, and waste management systems to quickly discover and minimize pollution sources. Likewise, AI and ML applications in construction processes enhance planning, scheduling, and facility management.

The COVID-19 pandemic came with disruptions in every aspect of human existence, with all the sectors of the economies of the world affected greatly. In the health sector, the pandemic halted and reversed progress in health and subsequently shortened life expectancy, especially in developing and underdeveloped nations. On the other hand, machine learning and artificial intelligence contributed a great deal to the handling of the pandemic globally. Therefore, the current study aimed to assess the role played by artificial intelligence and machine learning in addressing the dangers posed by the COVID-19 pandemic, as well as extrapolate the lessons on the fourth industrial revolution and sustainable development goals. Using qualitative content analysis, the results indicated that artificial intelligence and machine learning played an important role in the response to the challenges posed by the COVID-19 pandemic. Artificial intelligence, machine learning, and various digital communication tools through telehealth performed meaningful roles in scaling customer communications, provided a platform for understanding how COVID-19 spreads, and sped up research and treatment of COVID-19, among other notable achievements. The lessons we draw from this is that, despite the disruptions and the rise in the number of unintended consequences of technology in the fourth industrial revolution, the role played by artificial intelligence and machine learning motivates us to conclude that governments must build trust in these technologies, to address health problems going forward, to ensure that the sustainable development goals related to good health and wellbeing are achieved.

This chapter addresses how machine learning (ML) and artificial intelligence (AI) are revolutionizing the field of healthcare disease prediction. It describes how to employ public information and machine learning algorithms to forecast conditions including osteoarthritis, breast cancer, and Alzheimer's. Case studies from real-life scenarios show how predictive models work effectively for early diagnosis and customized responses. Critical analysis is done on ethical issues such as model interpretability and patient privacy. The chapter places a strong emphasis on the necessity of ethical frameworks and competent data handling to direct the incorporation of ML into healthcare. This chapter adds to the continuing discussion on AI's role in healthcare by providing a thorough analysis of disease prediction in osteoarthritis, Alzheimer's, and breast cancer, promoting better patient care and public health outcomes.

In today’s era, the healthcare domain is highly influenced by the widespread applications of big data analytics and artificial intelligence (AI). These technologies are being used for high-level molecular research, drug development and predictive analysis of various diseases. Currently, big data and AI are being used in several aspects against corona virus disease 2019 (COVID-19) pandemic. Literature as well as the genomic studies available for various strains of severe acute respiratory syndrome coronavirus 2, suggest how the concepts of big data and AI are being implemented to understand COVID-19 better which can assist with its antiviral drug development as well as vaccine production. These concepts of big data and AI have effectively helped with the contact tracing, epidemiology, molecular studies, medical diagnosis and treatment of COVID-19 that can help against future pandemics. Similarly, with this computational approach, various disease patterns are being recognized in different types of cancer. AI plays a major role in biomarker identification for disease progression to recognize novel hallmarks of cancer as well as in the predictive analysis of the disease. This allows an early-stage diagnosis of cancer which leads to a better prognosis. With an interdisciplinary collaboration of big data and predictive analytics, patient risk can be analyzed and estimated concerning the new treatment options available for cancer. Such high-throughput technologies have improvised the diagnosis and treatment options available for various diseases. With the advancements in science and technology and the introduction of computational models, public health and medicine have been completely revolutionized for the betterment of society.

In the digital age, Artificial Intelligence (AI) is pivotal in enhancing cybersecurity, offering advanced capabilities to detect and mitigate cyber threats efficiently. This article delves into AI's role in strengthening cyber security, emphasizing its ability to proactively identify vulnerabilities, forecast attacks, and automate incident responses. It also addresses the challenges and ethical concerns associated with AI in cyber security, such as the potential for misuse by cybercriminals to conduct sophisticated attacks and issues related to data privacy and algorithmic bias. The piece highlights the necessity of a balanced approach to leveraging AI, advocating for collaboration among stakeholders to navigate the ethical and regulatory complexities. Ultimately, it underscores AI's indispensable role in developing resilient cyber security frameworks and fostering a secure digital environment amidst an increasingly complex threat landscape.

Objective: Artificial intelligence has made a significant breakthrough with its ability to analyze complex data and identify hidden patterns, especially in the field of gait biomechanics.The aim of this study was to review and classify different AI approaches in gait biomechanics analysis.Methods: The present study was a systematic review.Searches were conducted in the Web of Science, SID, Magiran, Scopus, ISC, PubMed, and Google Scholar databases between 2020 and 2025 in both Persian and English.Inclusion criteria comprised experimental or applied studies using artificial intelligence for the analysis of human gait, involving data from healthy individuals or patients with neurological, muscular, or musculoskeletal conditions; reporting model performance metrics (e.g., accuracy, sensitivity, specificity) or measurable biomechanical parameters; employing direct motion capture or wearable/imaging sensors; and utilizing cross-sectional designs, algorithm validation, or clinical prediction/diagnostic approaches.Exclusion criteria included theoretical studies, narrative reviews without original data, editorials, case reports, animal studies or simulations without human data, studies relying solely on classical statistical methods without artificial intelligence, articles with incomplete data or limited accessibility, studies focusing on activities other than gait, and studies with low methodological quality.Of the 85 identified articles, 13 studies met the eligibility criteria.Study quality was assessed using the Downs and Black questionnaire.Findings: Based on the review of 14 studies on artificial intelligence and gait (including 7 studies on healthy individuals and 7 on patients), it was found that more than half of the studies (53.8%) used wearable sensors, approximately 23.1% employed markerless systems such as KinaTrax, 23% utilized machine/deep learning methods, and 10% applied conventional motion analysis systems.Cumulative analysis indicated that wearable sensors, particularly when combined with machine learning models such as Stack and SVR, were highly capable of classifying gait episodes (mean sensitivity 0.961 and MAE% below 2.1% for key parameters), reflecting the relatively high accuracy of these approaches.In studies using machine learning, the combination of ResNet101 and Nave Bayes performed well in classifying body posture (sensitivity 0.87), and LSTM models also yielded notable results for gait path prediction in VR environments, particularly for short-term predictions (14.5 mm error), although long-term predictions required additional data such as eye-tracking.Furthermore, the use of smart insoles combined with the RF algorithm demonstrated the feasibility of extracting digital biomarkers for managing conditions such as sarcopenia, although the number of studies was limited and sample sizes were small. Conclusion:The present findings indicate that the combination of wearable sensors particularly self-powered triboelectric sensors with machine and deep learning methods (such as SVR, ResNet101, and LSTM) has considerable potential for analyzing biomechanical gait parameters and predicting movement trajectories in laboratory and simulated environments, such as VR.However, the existing evidence is limited to small sample sizes and controlled conditions, and few studies have been conducted on actual patients or in clinical settings.Therefore, any clinical or rehabilitation applications of these technologies still require further research and validation in real-world environments.

This paper examines the transformative impact of artificial intelligence (AI) on pharmacogenomics, signaling a paradigm shift in personalized medicine. With a focus on enhancing drug response prediction and treatment optimization, AI, particularly machine learning and deep learning algorithms, navigates the complexity of genomic data. By elucidating intricate relationships between genetic factors and drug responses, AI augments the identification of genetic markers and contributes to the development of comprehensive models. The review emphasizes AI's role in guiding treatment decisions, minimizing adverse reactions, and optimizing drug dosages in clinical settings. Ethical considerations, challenges, and future directions are also discussed. This work underscores the synergy of AI and pharmacogenomics, offering a more effective and patient-centric approach to drug therapy, marking a significant advancement in the field of personalized medicine.