Figure - available from: Frontiers in Oncology
This content is subject to copyright.
The relationship between the most common AI methods in medicine. SMV, Support Vector Machine; RF, Random forest algorithm; GBM, Gradient Boosting Machines; XGB, XGBoost.
Source publication
Purpose: Artificial intelligence (AI) has accelerated novel discoveries across multiple disciplines including medicine. Clinical medicine suffers from a lack of AI-based applications, potentially due to lack of awareness of AI methodology. Future collaboration between computer scientists and clinicians is critical to maximize the benefits of transf...
Similar publications
Purpose: Artificial intelligence (AI) has accelerated novel discoveries across multiple disciplines including medicine. Clinical medicine suffers from a lack of AI-based applications, potentially due to lack of awareness of AI methodology. Future collaboration between computer scientists and clinicians is critical to maximize the benefits of transf...
Citations
... Several AI equipped medical devices have already been used for clinical applications such as diagnostics imaging. Moreover, machine learning techniques have been developed for Precision Medicine by customization and optimization of the medical care for each individual and Precision Oncology is taking advantage of advancements in the machine learning for choosing treatment options [10][11][12]. Machine learning algorithms have also been used for Genomic Medicine to use genomic information of individuals as part of their clinical care [12,13]. ...
Lung cancer is the second most diagnosed cancer and the first cause of cancer related death for men and women in the United States. Early detection is essential as patient survival is not optimal and recurrence rate is high. Copy number (CN) changes in cancer populations have been broadly investigated to identify CN gains and deletions associated with the cancer. In this research, the similarities between cancer and paired peripheral blood samples are identified using maximal information coefficient (MIC) and the spatial locations with substantially high MIC scores in each chromosome are used for clustering analysis. The results showed that a sizable reduction of feature set can be obtained using only a subset of locations with high MIC values. The clustering performance was evaluated using both true rate and normalized mutual information (NMI). Clustering results using the reduced feature set outperformed the performance of clustering using entire feature set in several chromosomes that are highly associated with lung cancer with several identified oncogenes.
... However, the successful implementation of personalized medicine requires standardized and representative data and collaboration between AI experts and disease specialists. AI findings must also be validated through more extensive clinical trials for translation into clinical practice [109]. ...
... While these techniques show promising performance, the application of AI to glioma diagnosis and treatment is still in its initial stages. Further development is necessary to assess the potential and implementation of these techniques in daily clinical practice and their impact on patient outcomes [109]. ...
The twenty-first century has witnessed significant advancements in informatics, reshaping our understanding of data processing andaccessibility. Artificial intelligence (AI), encompassing techniques such as machine learning (ML), deep learning (DP), and neuralnetworks (NN), is poised to revolutionize medicine. AI holds the capability of analyzing vast amounts of data, extracting meaningfulinsights, and making accurate predictions, thereby empowering industries to make informed decisions, drive innovation, and enhanceefficiency. The landscape of medical AI has evolved significantly, demonstrating expert-level disease detection from medical imagesand promising breakthroughs across various industries. AI revolutionizes medical practice by leveraging advanced algorithms andmachine learning capabilities to improve diagnostics, treatment planning, and overall patient care. However, the deployment ofmedical AI systems in regular clinical practice still needs to be tapped, presenting complex ethical, technical, and human-centeredchallenges that must be addressed for successful implementation. While AI algorithms have shown efficacy in retrospective medicalinvestigations, their translation into practical medical settings has been limited, raising concerns about their usability and interactionwith healthcare professionals. Moreover, the representativeness of retrospective datasets in real-world medical practice is subject tofiltering and cleaning biases. Integrating AI into clinical medicine holds great promise for transforming healthcare delivery, improvingpatient care, and revolutionizing aspects such as diagnosis, treatment planning, drug discovery, personalized treatment, and medicalimaging. With advanced algorithms and machine learning capabilities, AI and robotics in Healthcare can analyze large volumes ofmedical data, extract meaningful insights, and provide accurate predictions, empowering healthcare professionals to make informeddecisions and optimize resource allocation. The availability of extensive clinical, genomics, and digital imaging data, coupled withinvestments from healthcare institutions and technology giants, underscores the potential of AI in healthcare. This review articleexplores AI's powerful potential to revolutionize healthcare delivery across multiple domains, emphasizing the need to overcomechallenges and harness its transformative capabilities in clinical practice.
... Besides CT scans, some new imaging modalities may also be beneficial in assessing immunotherapy. New MRI techniques, such as perfusion-weighted, apparent diffusion, MR spectroscopy, and chemical exchange saturation transfer (CEST) MRI, have shown promise in the field of immunotherapy [14,42]. Moreover, it has been shown that 18 F-FDG PET can detect irAE in patients with melanoma receiving immunotherapy even before the usual clinical presentations of irAE [43]. ...
Standard-of-care medical imaging techniques such as CT, MRI, and PET play a critical role in managing patients diagnosed with metastatic cutaneous melanoma. Advancements in artificial intelligence (AI) techniques, such as radiomics, machine learning, and deep learning, could revolutionize the use of medical imaging by enhancing individualized image-guided precision medicine approaches. In the present article, we will decipher how AI/radiomics could mine information from medical images, such as tumor volume, heterogeneity, and shape, to provide insights into cancer biology that can be leveraged by clinicians to improve patient care both in the clinic and in clinical trials. More specifically, we will detail the potential role of AI in enhancing detection/diagnosis, staging, treatment planning, treatment delivery, response assessment, treatment toxicity assessment, and monitoring of patients diagnosed with metastatic cutaneous melanoma. Finally, we will explore how these proof-of-concept results can be translated from bench to bedside by describing how the implementation of AI techniques can be standardized for routine adoption in clinical settings worldwide to predict outcomes with great accuracy, reproducibility, and generalizability in patients diagnosed with metastatic cutaneous melanoma.
... For example, the ability to generalize AI algorithms at an early point can enable creating a more efficient road map for AI-based tool implementation. Recent research on personalized AI approaches in oncology (such as personalized medicine tools explored for gliomas) discusses this implementation barrier where to date, the used AI has largely been trained on smaller populations, preventing applicability for groups that may be heterogeneous [64]. ...
Background
Physicians play a key role in integrating new clinical technology into care practices through user feedback and growth propositions to developers of the technology. As physicians are stakeholders involved through the technology iteration process, understanding their roles as users can provide nuanced insights into the workings of these technologies that are being explored. Therefore, understanding physicians’ perceptions can be critical toward clinical validation, implementation, and downstream adoption. Given the increasing prevalence of clinical decision support systems (CDSSs), there remains a need to gain an in-depth understanding of physicians’ perceptions and expectations toward their downstream implementation. This paper explores physicians’ perceptions of integrating CURATE.AI, a novel artificial intelligence (AI)–based and clinical stage personalized dosing CDSSs, into clinical practice.
Objective
This study aims to understand physicians’ perspectives of integrating CURATE.AI for clinical work and to gather insights on considerations of the implementation of AI-based CDSS tools.
Methods
A total of 12 participants completed semistructured interviews examining their knowledge, experience, attitudes, risks, and future course of the personalized combination therapy dosing platform, CURATE.AI. Interviews were audio recorded, transcribed verbatim, and coded manually. The data were thematically analyzed.
Results
Overall, 3 broad themes and 9 subthemes were identified through thematic analysis. The themes covered considerations that physicians perceived as significant across various stages of new technology development, including trial, clinical implementation, and mass adoption.
Conclusions
The study laid out the various ways physicians interpreted an AI-based personalized dosing CDSS, CURATE.AI, for their clinical practice. The research pointed out that physicians’ expectations during the different stages of technology exploration can be nuanced and layered with expectations of implementation that are relevant for technology developers and researchers.
... The accurate distinction of recurrence from pseudo-progression helps in optimizing chemotherapy protocols in post-surgical GBM patients [3]. Most described algorithms had accuracy levels above 80-90% [4]. These features have the additional advantage of significantly lowering the workload of healthcare staff. ...
Glioblastoma multiforme (GBM), an aggressive brain tumor with high recurrence rates and limited survival, presents a pressing need for accurate and timely diagnosis. The interpretation of MRI can be complex and subjective. Artificial Intelligence (AI) has emerged as a promising solution, leveraging its potential to revolutionize diagnostic imaging. Radiomics treats images as numerical data and extracts intricate features from images, including subtle patterns that elude human observation. By integrating radiomics with genetics through radiogenomics, AI aids in tumor classification, identifying specific mutations and genetic traits. Furthermore, AI's impact extends to treatment planning. GBM's heterogeneity and infiltrative growth complicate delineation for treatment purposes. AI-driven segmentation techniques provide accurate 2D and 3D delineations, optimizing surgical and radiotherapeutic planning. Predictive features like angiogenesis and tumor volumes enable AI models to anticipate postop complications and survival rates. It can also aid in distinguishing posttreatment radiation effects from tumor recurrence. Despite these merits, concerns linger. The quality of medical data, transparency of AI techniques, and ethical considerations require thorough addressing. Collaborative efforts between neurosurgeons, data scientists, ethicists, and regulatory bodies are imperative for AI's ethical development and implementation. Transparent communication and patient consent are vital, fostering trust and understanding in AI-augmented medical care. In conclusion, AI holds immense promise in diagnosing and managing aggressive brain tumors like GBM. Its ability to analyze complex radiological data, integrate genetics, and aid in treatment planning underscores its potential to transform patient care. However, carefully considering ethical, technical, and regulatory aspects is crucial for realizing AI's full potential in oncology.
... Moreover, the applications of artificial intelligence (AI) in health care have helped advance the qualitative interpretation of cancer imaging, including volumetric delineation of tumors, extrapolation of the tumor genotype and biological course from its radiographic phenotype, prediction of clinical outcome, and assessment of the impact of disease and treatment (18). Many AI approaches have been created to help with glioma management concentrating on clinical and radiological data from CT and MRI (28). First steps have also been taken with regard to PET as an imaging tool for ML-based analysis of gliomas. ...
Introduction
Amino-acid positron emission tomography (PET) is a validated metabolic imaging approach for the diagnostic work-up of gliomas. This study aimed to evaluate sex-specific radiomic characteristics of L-[S-methyl- ¹¹ Cmethionine (MET)-PET images of glioma patients in consideration of the prognostically relevant biomarker isocitrate dehydrogenase (IDH) mutation status.
Methods
MET-PET of 35 astrocytic gliomas (13 females, mean age 41 ± 13 yrs. and 22 males, mean age 46 ± 17 yrs.) and known IDH mutation status were included. All patients underwent radiomic analysis following imaging biomarker standardization initiative (IBSI)-conform guidelines both from standardized uptake value (SUV) and tumor-to-background ratio (TBR) PET values. Aligned Monte Carlo (MC) 100-fold split was utilized for SUV and TBR dataset pairs for both sex and IDH-specific analysis. Borderline and outlier scores were calculated for both sex and IDH-specific MC folds. Feature ranking was performed by R-squared ranking and Mann-Whitney U-test together with Bonferroni correction. Correlation of SUV and TBR radiomics in relation to IDH mutational status in male and female patients were also investigated.
Results
There were no significant features in either SUV or TBR radiomics to distinguish female and male patients. In contrast, intensity histogram coefficient of variation (ih.cov) and intensity skewness (stat.skew) were identified as significant to predict IDH +/-. In addition, IDH+ females had significant ih.cov deviation (0.031) and mean stat.skew (-0.327) differences compared to IDH+ male patients (0.068 and -0.123, respectively) with two-times higher standard deviations of the normal brain background MET uptake as well.
Discussion
We demonstrated that female and male glioma patients have significantly different radiomic profiles in MET PET imaging data. Future IDH prediction models shall not be built on mixed female-male cohorts, but shall rely on sex-specific cohorts and radiomic imaging biomarkers.
... The exclusion of image features that are too sensitive to variation has been another suggested solution towards increased standardization [9]. For generalizability, authors emphasized the need for more and better-performed external validation, using multicentric imaging datasets obtained under real-world conditions and representative of the target patient group [4,9,11,22,28,46,72,[76][77][78]. Transfer learning, crowd-sourced, and open-access image repositories, and mathematically generated datasets are alternatives if data scarcity cannot be solved [41,71,[79][80][81]. ...
... First, most ML studies fail to compare their algorithms to current gold standards and instead retain a technical, proof-of-concept focus [9,30]. Others argued that the performance of most ML algorithms is not assessed based on their impact on disease outcomes, quality of care, or cost-effectiveness, with most studies adopting rather non-transparent workflows that do not resemble real-word settings [24,36,38,42,50,76,87,92]. Thus, it remains unknown how many of these tools perform under complex and unpredictable conditions, or how they affect the broader planning and provision of care [40,42,59]. ...
Machine learning has become a key driver of the digital health revolution. That comes with a fair share of high hopes and hype. We conducted a scoping review on machine learning in medical imaging, providing a comprehensive outlook of the field’s potential, limitations, and future directions. Most reported strengths and promises included: improved (a) analytic power, (b) efficiency (c) decision making, and (d) equity. Most reported challenges included: (a) structural barriers and imaging heterogeneity, (b) scarcity of well-annotated, representative and interconnected imaging datasets (c) validity and performance limitations, including bias and equity issues, and (d) the still missing clinical integration. The boundaries between strengths and challenges, with cross-cutting ethical and regulatory implications, remain blurred. The literature emphasizes explainability and trustworthiness, with a largely missing discussion about the specific technical and regulatory challenges surrounding these concepts. Future trends are expected to shift towards multi-source models, combining imaging with an array of other data, in a more open access, and explainable manner.
... Cancer gene expression has been a prominent focus of ML in addition to MRI/CT imaging analysis, cancer susceptibility testing, radiation resistance, mortality risk percentages, and tumor grade [10,[20][21][22][23]. The ML techniques commonly utilized within cancer research include ANN, K-nearest neighbors (KNN), Bayesian network (BN), Naïve Bayes (NB), support vector machine (SVM), and decision trees (DT). ...
Glioblastoma (GBM) is a common and deadly brain tumor with late diagnoses and poor prognoses. Machine learning (ML) is an emerging tool that can create highly accurate diagnostic and prognostic prediction models. The aim of this paper is to systematically search the literature of ML for GBM metabolism and assess recent advancements. A literature search was performed using pre-determined search terms. Articles describing use of a ML algorithm for GBM metabolism were included. Ten studies met the inclusion criteria for analysis. They were diagnostic (n=3, 30%), prognostic (n=6, 60%), or both (n=1, 10%), respectively. Most studies analyzed data from multiple databases, while 50% (n=5) included additional original samples. At least 2,536 data samples were run through a ML algorithm. 27 ML algorithms were recorded with a mean 2.8 algorithms per study. Algorithms were supervised (n=22, 79%) or unsupervised (n=6, 21%), and continuous (n=21, 75%) or categorical (n=7, 25%). The mean reported accuracy and AUC of ROC was 95.63% and 0.779, respectively. 106 metabolic markers were identified, but only EMP3 was reported in multiple studies. Many studies have identified potential biomarkers for GBM diagnosis and prognostication. These algorithms show promise; although, a consensus on even a handful of biomarkers has not been made.
... Emerging AI approaches, such as neural networks, deep learning, and CNN, help to retrieve important clinical data. These clinical data can be used for treatment planning and post-treatment monitoring [159]. By developing a fast and stable convergence method, it is possible to reduce the amount of time and resources needed to tune the momentum hyperparameters in popular CNN optimizers. ...
Brain tumors are a widespread and serious neurological phenomenon that can be life- threatening. The computing field has allowed for the development of artificial intelligence (AI), which can mimic the neural network of the human brain. One use of this technology has been to help researchers capture hidden, high-dimensional images of brain tumors. These images can provide new insights into the nature of brain tumors and help to improve treatment options. AI and precision medicine (PM) are converging to revolutionize healthcare. AI has the potential to improve cancer imaging interpretation in several ways, including more accurate tumor genotyping, more precise delineation of tumor volume, and better prediction of clinical outcomes. AI-assisted brain surgery can be an effective and safe option for treating brain tumors. This review discusses various AI and PM techniques that can be used in brain tumor treatment. These new techniques for the treatment of brain tumors, i.e., genomic profiling, microRNA panels, quantitative imaging, and radiomics, hold great promise for the future. However, there are challenges that must be overcome for these technologies to reach their full potential and improve healthcare.
... ML algorithms are generally classified as supervised, where data are accompanied by relevant labels that a model 'learns' to predict, or unsupervised, where no labels are provided with the data and the algorithm attempts to discern patterns within the data. Many ML algorithms, including support vector machines, neural networks and random forest, have found utility in radiomics [42]. Neural networks are a set of ML methods where data are fed through a set of interconnected 'layers' of linear operations to produce predictions. ...
Radiomics is a field of medical imaging analysis that focuses on the extraction of many quantitative imaging features related to shape, intensity and texture. These features are incorporated into models designed to predict important clinical or biological endpoints for patients. Attention for radiomics research has recently grown dramatically due to the increased use of imaging and the availability of large, publicly available imaging datasets. Glioblastoma multiforme (GBM) patients stand to benefit from this emerging research field as radiomics has the potential to assess the biological heterogeneity of the tumour, which contributes significantly to the inefficacy of current standard of care therapy. Radiomics models still require further development before they are implemented clinically in GBM patient management. Challenges relating to the standardisation of the radiomics process and the validation of radiomic models impede the progress of research towards clinical implementation. In this manuscript, we review the current state of radiomics in GBM, and we highlight the barriers to clinical implementation and discuss future validation studies needed to advance radiomics models towards clinical application.
