Iranian Journal of Blood and Cancer
Volume:15 Issue: 3, Sep 2023

The emergence of technology has long been a defining characteristic of human civilization, and in our current era, artificial intelligence (AI) stands as one of the most advanced innovations. Through the integration of AI into machines, the aim has been to unlock unprecedented levels of convenience. However, we now find ourselves at a crucial juncture where a significant question arises: Do humans continue to hold dominion, or have AI-equipped machines taken the reins? With its profound ability to reshape human capabilities, it is not surprising to propose that AI may represent the next stage of evolution. As we delve deeper into the potential of AI, it becomes imperative to ponder whether the emergence of AI as a form of evolved human beings is inevitable, and if so, what implications it may hold for the future of humanity. Taken together, it is essential for society to ensure the development and deployment of AI in a manner that prioritizes the safety and well-being of humanity while also giving careful consideration to ethical and legal concerns.

In recent years, artificial intelligence (AI) has revolutionized several aspects of human life. The availability of high-dimensionality datasets with progression in high-performance computing, and innovative deep learning architectures which are the subdomains of AI, have led to promising functions of AI in the medical contexts, particularly in oncology. Regarding the capacity of AI models in recognition and learning patterns as well as associations, these systems can be utilized in various aspects of cancer research including cancer diagnosis and treatment. To be precise, AI models are able to analyze medical images such as stained histopathology slides and radiology images and consequently pave the way for cancer diagnosis, grading, classification, tumor characterization, and prognosis prediction. Moreover, AI algorithms can assess a myriad of medical data to recognize patterns and make predictions about patient treatment outcomes, enabling more personalized treatment plans. Accordingly, AIassisted cancer treatment strategies have been shown to notably improve the quality of cancer treatment with chemotherapy, immunotherapy, and even radiotherapy while reducing the treatment toxicities.

The field of cancer research has been profoundly impacted by the utilization of artificial intelligence (AI), particularly through the analysis of medical records encompassing genomics, transcriptomics, proteomics, and imaging data. Subdomains of AI, such as machine learning (ML) and deep learning (DL), possess the capability to analyze intricate patterns within these records. This allows for groundbreaking advancements in cancer diagnosis, prognosis, and treatment by extracting valuable insights from sources such as histology and radiology imaging. The integration of AI-based models has led to improved prediction, diagnosis, and even treatment of various types of cancer, resulting in enhanced performance within the field of oncology. However, AI also faces challenges including ethical and legal considerations, data quality and accessibility, and issues pertaining to model interpretability. It is crucial to develop and evaluate AI-based systems in collaboration with clinicians and researchers to ensure their safety, reliability, and validity in cancer research.

Traditionally, medical treatments have been developed using a standardized approach, where identical treatment protocols are administered to all patients with a particular disease or condition. Precision medicine represents a groundbreaking approach to healthcare that centers on customizing medical treatments and interventions to individual patients based on their unique environmental factors, lifestyles, and molecular profiles. This approach has been shown to enhance the success rates of clinical trials and expedite drug approvals. By harnessing vast amounts of data and sophisticated algorithms, artificial intelligence (AI) has the potential to transform precision medicine and drug discovery. AI can offer valuable insights into all facets of precision medicine, including expediting the development of new therapies, optimizing clinical trials, facilitating accurate diagnoses, guiding treatment decisions, and monitoring patients. In this review, we endeavor to explore the ways in which AI will impact the various aspects of precision medicine and drug discovery.

Chat generative pre-trained transformer (GPT) is a large language model (LLM) artificial intelligence (AI). Indeed, ChatGPT is a chatbot able to participate in a conversation by pretending to be a human. ChatGPT is able to write convincing academic texts which are hard to be distinguished from a human-written manuscript. In the medical context, ChatGPT demonstrated its ability to write abstracts and texts related to the given questions. It could answer medical questions whether they are asked by students or researchers. ChatGPT is able to enhance the knowledge of students by designing tests and answering personalized questions, consequently reducing the burden on teachers. This AI system can participate in healthcare programs by providing information for patients and acting as the connector between patients and healthcare providers. Also, it could serve as a translator and a text generator for patients who speak a different language or those who have speech difficulties. ChatGPT is also able to provide and categorize medical information necessary for healthcare providers and physicians. Nonetheless, the major concern is the level of reliability of generated data. In some cases, ChatGPT produced misleading information and fake citations which warned medical researchers. Worryingly, these false data could distract the process of treatments and or the projects of medical researchers. Regarding the inevitable necessity of AI utilization in the medical field, strict criteria should be enforced in order to improve the efficacy and reduce the safety of the application of any AI chatbot like ChatGPT.

Artificial intelligence (AI), machine learning, and deep learning are emerging technologies with the potential to revolutionize the diagnosis and treatment of various diseases, ranging from cancer to cardiovascular disorders. These advanced algorithms have the ability to learn patterns and associations, enabling them to make predictions and enhance therapeutic approaches. Among the conditions that can benefit from AI's capabilities are platelet disorders, which at least in some cases may lead to life-threatening excessive bleeding. The conventional methods to diagnose these disorders mainly rely on manual or automated blood cell counting and morphology analysis that are prone to errors. In recent years, researchers have turned to machine learning models to predict platelet disorders, including drug-induced immune thrombocytopenia (DITP), sepsis-associated thrombocytopenia (SAT), immune thrombocytopenic purpura (ITP), disseminated intravascular coagulation (DIC), as well as thrombocytosis. These studies have yielded promising results, demonstrating satisfactory efficacy and accuracy. Our analysis revealed that key predictive parameters include the patient's medical history, platelet counts, and coagulation factors. Notably, the support vector machine (SVM) algorithm exhibited the highest performance in predicting platelet disorders, achieving the highest accuracy score while analyzing a relatively lower number of parameters.

Anemia stands out as the most prevalent blood disorder globally. Various factors can contribute to its development, including insufficient production of red blood cells (RBCs) as well as degradation of RBCs. The functional impairment of RBCs in anemia can result in a wide spectrum of symptoms, ranging from fatigue and weakness to severe, life-threatening conditions. The primary method for detecting anemia is the commonly employed complete blood count (CBC) test. However, for certain cases and to distinguish between different types of anemia, more advanced tests become necessary. Artificial intelligence (AI) has emerged as a technology designed to replicate human intelligence and perform tasks that typically require human cognitive abilities. AI models possess the capability to comprehend patterns and associations, enabling them to recognize and analyze images. In the context of anemia, studies have demonstrated that AI algorithms can analyze images of various physical characteristics such as conjunctiva, palm, tongue, and fingernails. By estimating hemoglobin concentration, these algorithms can predict the presence of anemia. Furthermore, AI systems have also exhibited the ability to analyze clinical data, including laboratory tests and blood smears, to predict anemia and identify specific types. It is worth noting that previous studies in the context if AI applications in anemia have been conducted on relatively small populations. However, the accuracy achieved in these investigations has been satisfactory, suggesting that AI systems could potentially play a significant role in the future of anemia diagnosis and management.

To guarantees patient survival and reduce the consumption of pharmaceutical and medical resources, an accurate diagnosis and assessment of COVID-19 severity are crucial. Since the outbreak of the pandemic, researchers have evaluated, identified, and predicted the severity of COVID-19 using a range of AI techniques. Due to the lack of a systematic review in the field of analysis of these studies, the present research rigorously reviewed all the pertinent literature.

Between December 1, 2019, and January 1, 2022, 762 articles were found by searching the PubMed, Scopus, Web of Science, and Scholar databases using the search method. 34 papers were chosen from this group as the research community's representatives using inclusion and exclusion criteria.

By looking at the machine learning approach used in this research, it can be seen that XGBoost and SVM algorithms were more prevalent and effective in identifying the severity of the condition, according to the results of the data analysis used in this study. A set of impressive features, including clinical, demographic, laboratory, and serology data, was used to calculate the severity of COVID-19 using ML algorithms. By calculating the performance metric, it can be concluded that the ML methods had high sensitivity and specificity in determining the severity of COVID-19.

Deep learning methods, as cutting-edge methods, have a significant tangible capacity for providing an accurate and efficient intelligent system for detecting and estimating the severity of COVID-19. It is recommended that in the future or other variants of COVID-19 epidemics, AI-based systems in conjunction with IoT, cloud storage, and 5G technologies be used to remove geographical problems in the rapid estimation of disease severity, immediate epidemic control before the pandemic, epidemic management, and lower treatment costs

Malaria remains a significant global health problem, with a high incidence of cases and a substantial number of deaths yearly. Early identification and accurate diagnosis play a crucial role in effective malaria treatment. However, underdiagnosis presents a significant challenge in reducing mortality rates, and traditional laboratory diagnosis methods have limitations in terms of time consumption and error susceptibility. To overcome these challenges, researchers have increasingly utilized Machine Learning techniques, specifically neural networks, which provide faster, cost-effective, and highly accurate diagnostic capabilities.

This study aimed to compare the performance of a traditional neural network (NN) with a convolutional neural network (CNN) in the diagnosis and classification of different types of malaria using blood smear images. We curated a comprehensive malaria dataset comprising 1,920 images obtained from 84 patients suspected of having various malaria strains. The dataset consisted of 624 images of Falciparum, 548 images of Vivax, 588 images of Ovale, and 160 images from suspected healthy individuals, obtained from local hospitals in Iran. To ensure precise analysis, we developed a unique segmentation model that effectively eliminated therapeutically beneficial cells from the image context, enabling accurate analysis using artificial intelligence algorithms.

The evaluation of the traditional NN and the proposed 6-layer CNN model for image classification yielded average accuracies of 95.11% and 99.59%, respectively. These results demonstrate that the CNN, as a primary algorithm of deep neural networks (DNN), outperforms the traditional NN in analyzing different classes of malaria images. The CNN model demonstrated superior diagnostic performance, delivering enhanced accuracy and reliability in the classifying of malaria cases.

This research underscores the potential of ML technologies, specifically CNNs, in improving malaria diagnosis and classification. By leveraging advanced image analysis techniques, including the developed segmentation model, CNN showcased remarkable proficiency in accurately identifying and classifying various malaria parasites from blood smear images. The adoption of machine learning-based approaches holds promise for more effective management and treatment of malaria, addressing the challenges of underdiagnosis and improving patient outcomes.

Celiac disease (CD) is an autoimmune digestive condition that is distinguished by inflammation of the small intestine as a result of gluten ingestion. Its worldwide prevalence is approximately 1%. Despite progress in understanding CD, challenges in pathogenesis, diagnosis, treatment, and management persist. Genetic and environmental factors, such as HLA and non-HLA genes, gluten, gut microbiota imbalance, and immune responses involving CD4+ T cells, influence CD. Diagnostic challenges arise due to diverse clinical presentations and overlap with other gastrointestinal disorders. Following a gluten-free diet (GFD) strictly is the primary treatment for CD, but this diet presents social, psychological, and financial hurdles. Artificial intelligence (AI) has emerged as a potent instrument in CD management. Techniques like machine learning (ML), deep learning (DL), natural language processing (NLP), and computer-aided algorithms have shown promise in CD diagnosis by improving microbiome analysis, disease prediction, interpretation of medical records and endoscopy images. AI-based decision-support systems can aid in diagnosis. AI-driven personalized nutrition and gluten contamination monitoring techniques offer potential improvements for treatment. Overall, AI has potential in addressing CD challenges and enhancing patient outcomes.