Artificial intelligence in cancer research, diagnosis and therapy

Collaborative training of medical artificial intelligence models with non-uniform labels

Due to the rapid advancements in recent years, medical image analysis is largely dominated by deep learning (DL). However, building powerful and robust DL models requires training with large multi-party datasets. While multiple stakeholders have provided publicly available datasets, the ways in which these data are labeled vary widely. For Instance, an institution might provide a dataset of chest radiographs containing labels denoting the presence of pneumonia, while another institution might have a focus on determining the presence of metastases in the lung. Training a single AI model utilizing all these data is not feasible with conventional federated learning (FL). This prompts us to propose an extension to the widespread FL process, namely flexible federated learning (FFL) for collaborative training on such data. Using 695,000 chest radiographs from five institutions from across the globe-each with differing labels-we demonstrate that having heterogeneously labeled datasets, FFL-based training leads to significant performance increase compared to conventional FL training, where only the uniformly annotated images are utilized. We believe that our proposed algorithm could accelerate the process of bringing collaborative training methods from research and simulation phase to the real-world applications in healthcare.

Evolution-Informed Strategies for Combating Drug Resistance in Cancer

The ever-changing nature of cancer poses the most difficult challenge oncologists face today. Cancer's remarkable adaptability has inspired many to work toward understanding the evolutionary dynamics that underlie this disease in hopes of learning new ways to fight it. Eco-evolutionary dynamics of a tumor are not accounted for in most standard treatment regimens, but exploiting them would help us combat treatment-resistant effectively. Here, we outline several notable efforts to exploit these dynamics and circumvent drug resistance in cancer.

Deep-learning model AIBISI predicts bacterial infection across cancer types based on pathological images

Microorganisms play an important role in many physiological functions. Many studies have found that bacteria also regulate cancer susceptibility and tumor progression by affecting some metabolic or immune system signaling pathways. However, current bacterial detection methods are inaccurate or inefficient. Thus, we constructed a deep neural network (AIBISI) based on hematoxylin and eosin (H&E)-stained pathology slides to predict and visualize bacterial infection. Our model performance achieved as high as 0.81 of AUC (area under the ROC curve) within cancer type. We also built a pan-cancer model to predict bacterial infection across cancer types. To facilitate clinical usage, AIBISI visualized image areas affected by possible infection. Importantly, we successfully validated our model (AUC = 0.755) in pathological images from an independent patient cohort of stomach cancer (n = 32). To our best knowledge, this is the first artificial intelligence (AI)-based model to investigate bacterial infection in pathology images and has the potential to enable fast clinical decision related to pathogens in tumors.

Future of Artificial Intelligence Applications in Cancer Care: A Global Cross-Sectional Survey of Researchers

Cancer significantly contributes to global mortality, with 9.3 million annual deaths. To alleviate this burden, the utilization of artificial intelligence (AI) applications has been proposed in various domains of oncology. However, the potential applications of AI and the barriers to its widespread adoption remain unclear. This study aimed to address this gap by conducting a cross-sectional, global, web-based survey of over 1000 AI and cancer researchers. The results indicated that most respondents believed AI would positively impact cancer grading and classification, follow-up services, and diagnostic accuracy. Despite these benefits, several limitations were identified, including difficulties incorporating AI into clinical practice and the lack of standardization in cancer health data. These limitations pose significant challenges, particularly regarding testing, validation, certification, and auditing AI algorithms and systems. The results of this study provide valuable insights for informed decision-making for stakeholders involved in AI and cancer research and development, including individual researchers and research funding agencies.

Adversarial confound regression and uncertainty measurements to classify heterogeneous clinical MRI in Mass General Brigham

In this work, we introduce a novel deep learning architecture, MUCRAN (Multi-Confound Regression Adversarial Network), to train a deep learning model on clinical brain MRI while regressing demographic and technical confounding factors. We trained MUCRAN using 17,076 clinical T1 Axial brain MRIs collected from Massachusetts General Hospital before 2019 and demonstrated that MUCRAN could successfully regress major confounding factors in the vast clinical dataset. We also applied a method for quantifying uncertainty across an ensemble of these models to automatically exclude out-of-distribution data in AD detection. By combining MUCRAN and the uncertainty quantification method, we showed consistent and significant increases in the AD detection accuracy for newly collected MGH data (post-2019; 84.6% with MUCRAN vs. 72.5% without MUCRAN) and for data from other hospitals (90.3% from Brigham and Women's Hospital and 81.0% from other hospitals). MUCRAN offers a generalizable approach for deep-learning-based disease detection in heterogenous clinical data.

Computational Biomaterials: Computational Simulations for Biomedicine

With the flourishing development of material simulation methods (quantum chemistry methods, molecular dynamics, Monte Carlo, phase field, etc.), extensive adoption of computing technologies (high-throughput, artificial intelligence, machine learning, etc.), and the invention of high-performance computing equipment, computational simulation tools have sparked the fundamental mechanism-level explorations to predict the diverse physicochemical properties and biological effects of biomaterials and investigate their enormous application potential for disease prevention, diagnostics, and therapeutics. Herein, the term "computational biomaterials" is proposed and the computational methods currently used to explore the inherent properties of biomaterials, such as optical, magnetic, electronic, and acoustic properties, and the elucidation of corresponding biological behaviors/effects in the biomedical field are summarized/discussed. The theoretical calculation of the physiochemical properties/biological performance of biomaterials applied in disease diagnosis, drug delivery, disease therapeutics, and specific paradigms such as biomimetic biomaterials is discussed. Additionally, the biosafety evaluation applications of theoretical simulations of biomaterials are presented. Finally, the challenges and future prospects of such computational simulations for biomaterials development are clarified. It is anticipated that these simulations would offer various methodologies for facilitating the development and future clinical translations/utilization of versatile biomaterials.

Automatic treatment outcome prediction with DeepInteg based on multimodal radiological images in rectal cancer

Neoadjuvant systemic treatment before surgery is a prevalent regimen in the patients with advanced-stage or high-risk tumor, which has shaped the treatment strategies and cancer survival in the past decades. However, some patients present with poor response to the neoadjuvant treatment. Therefore, it is of great significance to develop tools to help distinguish the patients that could achieve pathological complete response before surgery to avoid inappropriate treatment. Here, this study demonstrated a multi-task deep learning tool called DeepInteg. In the DeepInteg framework, the segmentation module was constructed based on the CE-Net with a context extractor to achieve end-to-end delineation of region of interest (ROI) from radiological images, then the features of segmented Magnetic Resonance Imaging (MRI) and Computed Tomography (CT) images of each case were fused and input to the classification module based on a convolution neural network for treatment outcome prediction. The dataset with 1700 MRI and CT slices collected from the prospectively randomized clinical trial (NCT01211210) on systemic treatment for rectal cancer was used to develop and systematically optimize DeepInteg. As a result, DeepInteg achieved automatic segmentation of tumoral ROI with Dices of 0.766 and 0.719 and mIoUs of 0.788 and 0.756 in CT and MRI images, respectively. In addition, DeepInteg achieved AUC of 0.833, accuracy of 0.826 and specificity of 0.856 in the prediction for pathological complete response after treatment, which showed better performance compared with the model based on CT or MRI alone. This study provide a robust framework to develop disease-specific tools for automatic delineation of ROI and clinical outcome prediction. The well-trained DeepInteg could be readily applied in clinic to predict pathological complete response after neoadjuvant therapy in rectal cancer patients.

Application of artificial intelligence to the public health education

With the global outbreak of coronavirus disease 2019 (COVID-19), public health has received unprecedented attention. The cultivation of emergency and compound professionals is the general trend through public health education. However, current public health education is limited to traditional teaching models that struggle to balance theory and practice. Fortunately, the development of artificial intelligence (AI) has entered the stage of intelligent cognition. The introduction of AI in education has opened a new era of computer-assisted education, which brought new possibilities for teaching and learning in public health education. AI-based on big data not only provides abundant resources for public health research and management but also brings convenience for students to obtain public health data and information, which is conducive to the construction of introductory professional courses for students. In this review, we elaborated on the current status and limitations of public health education, summarized the application of AI in public health practice, and further proposed a framework for how to integrate AI into public health education curriculum. With the rapid technological advancements, we believe that AI will revolutionize the education paradigm of public health and help respond to public health emergencies.

Differential Diagnosis of Hematologic and Solid Tumors Using Targeted Transcriptome and Artificial Intelligence

Diagnosis and classification of tumors is increasingly dependent on biomarkers. RNA expression profiling using next-generation sequencing provides reliable and reproducible information on the biology of cancer. This study investigated targeted transcriptome and artificial intelligence for differential diagnosis of hematologic and solid tumors. RNA samples from hematologic neoplasms (N = 2606), solid tumors (N = 2038), normal bone marrow (N = 782), and lymph node control (N = 24) were sequenced using next-generation sequencing using a targeted 1408-gene panel. Twenty subtypes of hematologic neoplasms and 24 subtypes of solid tumors were identified. Machine learning was used for diagnosis between two classes. Geometric mean naïve Bayesian classifier was used for differential diagnosis across 45 diagnostic entities with assigned rankings. Machine learning showed high accuracy in distinguishing between two diagnoses, with area under the curve varying between 1 and 0.841. Geometric mean naïve Bayesian algorithm was trained using 3045 samples and tested on 1415 samples, and showed correct first-choice diagnosis in 100%, 88%, 85%, 82%, 88%, 72%, and 72% of acute lymphoblastic leukemia, acute myeloid leukemia, diffuse large B-cell lymphoma, colorectal cancer, lung cancer, chronic lymphocytic leukemia, and follicular lymphoma cases, respectively. The data indicate that targeted transcriptome combined with artificial intelligence are highly useful for diagnosis and classification of various cancers. Mutation profiles and clinical information can improve these algorithms and minimize errors in diagnoses.

Exosomal microRNAs in cancer: Potential biomarkers and immunotherapeutic targets for immune checkpoint molecules

Exosomes are small extracellular vesicles with a lipid bilayer structure secreted from different cell types which can be found in various body fluids including blood, pleural fluid, saliva and urine. They carry different biomolecules including proteins, metabolites, and amino acids such as microRNAs which are small non-coding RNAs that regulate gene expression and promote cell-to-cell communication. One main function of the exosomal miRNAs (exomiRs) is their role in cancer pathogenesis. Alternation in exomiRs expression could indicate disease progression and can regulate cancer growth and facilitate drug response/resistance. It can also influence the tumour microenvironment by controlling important signaling that regulating immune checkpoint molecules leading to activation of T cell anti-tumour immunity. Therefore, they can be used as potential novel cancer biomarkers and innovative immunotherapeutic agents. This review highlights the use of exomiRs as potential reliable biomarkers for cancer diagnosis, treatment response and metastasis. Finally, discuses their potential as immunotherapeutic agents to regulate immune checkpoint molecules and promote T cell anti-tumour immunity.

Prediction of chemotherapy-related complications in pediatric oncology patients: artificial intelligence and machine learning implementations

Although the overall incidence of pediatric oncological diseases tends to increase over the years, it is among the rare diseases of the pediatric population. The diagnosis, treatment, and healthcare management of this group of diseases are important. Prevention of treatment-related complications is vital for patients, particularly in the pediatric population. Nowadays, the use of artificial intelligence and machine learning technologies in the management of oncological diseases is becoming increasingly important. With the advancement of software technologies, improvements have been made in the early diagnosis of risk groups in oncological diseases, in radiology, pathology, and imaging technologies, in cancer staging and management. In addition, these technologies can be used to predict the outcome in chemotherapy treatment of oncological diseases. In this context, this study identifies artificial intelligence and machine learning methods used in the prediction of complications due to chemotherapeutic agents used in childhood cancer treatment. For this purpose, the concepts of artificial intelligence and machine learning are explained in this review. A general framework for the use of machine learning in healthcare and pediatric oncology has been drawn and examples of studies conducted on this topic in pediatric oncology have been given. IMPACT: Artificial intelligence and machine learning are advanced tools that can be used to predict chemotherapy-related complications. Algorithms can assist clinicians' decision-making processes in the management of complications. Although studies are using these methods, there is a need to increase the number of studies on artificial intelligence applications in pediatric clinics.

Application of machine learning techniques for predicting survival in ovarian cancer

BACKGROUND

Ovarian cancer is the fifth leading cause of mortality among women in the United States. Ovarian cancer is also known as forgotten cancer or silent disease. The survival of ovarian cancer patients depends on several factors, including the treatment process and the prognosis.

METHODS

The ovarian cancer patients' dataset is compiled from the Surveillance, Epidemiology, and End Results (SEER) database. With the help of a clinician, the dataset is curated, and the most relevant features are selected. Pearson's second coefficient of skewness test is used to evaluate the skewness of the dataset. Pearson correlation coefficient is also used to investigate the associations between features. Statistical test is utilized to evaluate the significance of the features. Six Machine Learning (ML) models, including K-Nearest Neighbors , Support Vector Machine (SVM), Decision Tree (DT), Random Forest (RF), Adaptive Boosting (AdaBoost), and Extreme Gradient Boosting (XGBoost), are implemented for survival prediction in both classification and regression approaches. An interpretable method, Shapley Additive Explanations (SHAP), is applied to clarify the decision-making process and determine the importance of each feature in prediction. Additionally, DTs of the RF model are displayed to show how the model predicts the survival intervals.

RESULTS

Our results show that RF (Accuracy = 88.72%, AUC = 82.38%) and XGBoost (Root Mean Squad Error (RMSE)) = 20.61%, R² = 0.4667) have the best performance for classification and regression approaches, respectively. Furthermore, using the SHAP method along with extracted DTs of the RF model, the most important features in the dataset are identified. Histologic type ICD-O-3, chemotherapy recode, year of diagnosis, age at diagnosis, tumor stage, and grade are the most important determinant factors in survival prediction.

CONCLUSION

To the best of our knowledge, our study is the first study that develops various ML models to predict ovarian cancer patients' survival on the SEER database in both classification and regression approaches. These ML algorithms also achieve more accurate results and outperform statistical methods. Furthermore, our study is the first study to use the SHAP method to increase confidence and transparency of the proposed models' prediction for clinicians. Moreover, our developed models, as an automated auxiliary tool, can help clinicians to have a better understanding of the estimated survival as well as important features that affect survival.

Development and validation of an artificial neural network model for non-invasive gastric cancer screening and diagnosis

Non-invasive and cost-effective diagnosis of gastric cancer is essential to improve outcomes. Aim of the study was to establish a neural network model based on patient demographic data and serum biomarker panels to aid gastric cancer diagnosis. A total of 295 patients hospitalized in Nanjing Drum Tower hospital diagnosed with gastric cancer based on tissue biopsy, and 423 healthy volunteers were included in the study. Demographical information and tumor biomarkers were obtained from Hospital Information System (HIS) as original data. Pearson's correlation analysis was applied on 574 individuals' data (training set, 229 patients and 345 healthy volunteers) to analyze the relationship between each variable and the final diagnostic result. And independent sample t test was used to detect the differences of the variables. Finally, a neural network model based on 14 relevant variables was constructed. The model was tested on the validation set (144 individuals including 66 patients and 78 healthy volunteers). The predictive ability of the proposed model was compared with other common machine learning models including logistic regression and random forest. Tumor markers contributing significantly to gastric cancer screening included CA199, CA125, AFP, and CA242 were identified, which might be considered as important inspection items for gastric cancer screening. The accuracy of the model on validation set was 86.8% and the F1-score was 85.0%, which were better than the performance of other models under the same condition. A non-invasive and low-cost artificial neural network model was developed and proved to be a valuable tool to assist gastric cancer diagnosis.

A Systems Biology and LASSO-Based Approach to Decipher the Transcriptome-Interactome Signature for Predicting Non-Small Cell Lung Cancer

The lack of precise molecular signatures limits the early diagnosis of non-small cell lung cancer (NSCLC). The present study used gene expression data and interaction networks to develop a highly accurate model with the least absolute shrinkage and selection operator (LASSO) for predicting NSCLC. The differentially expressed genes (DEGs) were identified in NSCLC compared with normal tissues using TCGA and GTEx data. A biological network was constructed using DEGs, and the top 20 upregulated and 20 downregulated hub genes were identified. These hub genes were used to identify signature genes with penalized logistic regression using the LASSO to predict NSCLC. Our model’s development involved the following steps: (i) the dataset was divided into 80% for training (TR) and 20% for testing (TD1); (ii) a LASSO logistic regression analysis was performed on the TR with 10-fold cross-validation and identified a combination of 17 genes as NSCLC predictors, which were used further for development of the LASSO model. The model’s performance was assessed on the TD1 dataset and achieved an accuracy and an area under the curve of the receiver operating characteristics (AUC-ROC) of 0.986 and 0.998, respectively. Furthermore, the performance of the LASSO model was evaluated using three independent NSCLC test datasets (GSE18842, GSE27262, GSE19804) and achieved high accuracy, with an AUC-ROC of >0.99, >0.99, and 0.95, respectively. Based on this study, a web application called NSCLCpred was developed to predict NSCLC.

The Application of Artificial Intelligence in Magnetic Hyperthermia Based Research

The development of nanomedicine involves complex nanomaterial research involving magnetic nanomaterials and their use in magnetic hyperthermia. The selection of the optimal treatment strategies is time-consuming, expensive, unpredictable, and not consistently effective. Delivering personalized therapy that obtains maximal efficiency and minimal side effects is highly important. Thus, Artificial Intelligence (AI) based algorithms provide the opportunity to overcome these crucial issues. In this paper, we briefly overview the significance of the combination of AI-based methods, particularly the Machine Learning (ML) technique, with magnetic hyperthermia. We considered recent publications, reports, protocols, and review papers from Scopus and Web of Science Core Collection databases, considering the PRISMA-S review methodology on applying magnetic nanocarriers in magnetic hyperthermia. An algorithmic performance comparison in terms of their types and accuracy, data availability taking into account their amount, types, and quality was also carried out. Literature shows AI support of these studies from the physicochemical evaluation of nanocarriers, drug development and release, resistance prediction, dosing optimization, the combination of drug selection, pharmacokinetic profile characterization, and outcome prediction to the heat generation estimation. The papers reviewed here clearly illustrate that AI-based solutions can be considered as an effective supporting tool in drug delivery, including optimization and behavior of nanocarriers, both in vitro and in vivo, as well as the delivery process. Moreover, the direction of future research, including the prediction of optimal experiments and data curation initiatives has been indicated.

A Novel, Simple, and Low-Cost Approach for Machine Learning Screening of Kidney Cancer: An Eight-Indicator Blood Test Panel with Predictive Value for Early Diagnosis

Clear cell renal cell carcinoma (ccRCC) accounts for more than 90% of all renal cancers. The five-year survival rate of early-stage (TNM 1) ccRCC reaches 96%, while the advanced-stage (TNM 4) is only 23%. Therefore, early screening of patients with renal cancer is essential for the treatment of renal cancer and the long-term survival of patients. In this study, blood samples of patients were collected and a pre-defined set of blood indicators were measured. A random forest (RF) model was established to predict based on each indicator in the blood, and was trained with all relevant indicators for comprehensive predictions. In our study, we found that there was a high statistical significance (p < 0.001) for all indicators of healthy individuals and early cancer patients, except for uric acid (UA). At the same time, ccRCC also presented great differences in most blood indicators between males and females. In addition, patients with ccRCC had a higher probability of developing a low ratio of albumin (ALB) to globulin (GLB) (AGR < 1.2). Eight key indicators were used to classify and predict renal cell carcinoma. The area under the receiver operating characteristic (ROC) curve (AUC) of the eight-indicator model was as high as 0.932, the sensitivity was 88.2%, and the specificity was 86.3%, which are acceptable in many applications, thus realising early screening for renal cancer by blood indicators in a simple blood-draw physical examination. Furthermore, the composite indicator prediction method described in our study can be applied to other clinical conditions or diseases, where multiple blood indicators may be key to enhancing the diagnostic potential of screening strategies.

Big data in basic and translational cancer research

Historically, the primary focus of cancer research has been molecular and clinical studies of a few essential pathways and genes. Recent years have seen the rapid accumulation of large-scale cancer omics data catalysed by breakthroughs in high-throughput technologies. This fast data growth has given rise to an evolving concept of 'big data' in cancer, whose analysis demands large computational resources and can potentially bring novel insights into essential questions. Indeed, the combination of big data, bioinformatics and artificial intelligence has led to notable advances in our basic understanding of cancer biology and to translational advancements. Further advances will require a concerted effort among data scientists, clinicians, biologists and policymakers. Here, we review the current state of the art and future challenges for harnessing big data to advance cancer research and treatment.

Machine learning approaches for prediction of early death among lung cancer patients with bone metastases using routine clinical characteristics: An analysis of 19,887 patients

Purpose

Bone is one of the most common sites for the spread of malignant tumors. Patients with bone metastases whose prognosis was shorter than 3 months (early death) were considered as surgical contraindications. However, the information currently available in the literature limits our capacity to assess the risk likelihood of 3 month mortality. As a result, the study's objective is to create an accurate prediction model utilizing machine-learning techniques to predict 3 month mortality specifically among lung cancer patients with bone metastases according to easily available clinical data.

Methods

This study enrolled 19,887 lung cancer patients with bone metastases between 2010 and 2018 from a large oncologic database in the United States. According to a ratio of 8:2, the entire patient cohort was randomly assigned to a training (n = 15881, 80%) and validation (n = 4,006, 20%) group. In the training group, prediction models were trained and optimized using six approaches, including logistic regression, XGBoosting machine, random forest, neural network, gradient boosting machine, and decision tree. There were 13 metrics, including the Brier score, calibration slope, intercept-in-large, area under the curve (AUC), and sensitivity, used to assess the model's prediction performance in the validation group. In each metric, the best prediction effectiveness was assigned six points, while the worst was given one point. The model with the highest sum score of the 13 measures was optimal. The model's explainability was performed using the local interpretable model-agnostic explanation (LIME) according to the optimal model. Predictor importance was assessed using H₂O automatic machine learning. Risk stratification was also evaluated based on the optimal threshold.

Results

Among all recruited patients, the 3 month mortality was 48.5%. Twelve variables, including age, primary site, histology, race, sex, tumor (T) stage, node (N) stage, brain metastasis, liver metastasis, cancer-directed surgery, radiation, and chemotherapy, were significantly associated with 3 month mortality based on multivariate analysis, and these variables were included for developing prediction models. With the highest sum score of all the measurements, the gradient boosting machine approach outperformed all the other models (62 points), followed by the XGBooting machine approach (59 points) and logistic regression (53). The area under the curve (AUC) was 0.820 (95% confident interval [CI]: 0.807-0.833), 0.820 (95% CI: 0.807-0.833), and 0.815 (95% CI: 0.801-0.828), respectively, calibration slope was 0.97, 0.95, and 0.96, respectively, and accuracy was all 0.772. Explainability of models was conducted to rank the predictors and visualize their contributions to an individual's mortality outcome. The top four important predictors in the population according to H₂O automatic machine learning were chemotherapy, followed by liver metastasis, radiation, and brain metastasis. Compared to patients in the low-risk group, patients in the high-risk group were more than three times the odds of dying within 3 months (P < 0.001).

Conclusions

Using machine learning techniques, this study offers a number of models, and the optimal model is found after thoroughly assessing and contrasting the prediction performance of each model. The optimal model can be a pragmatic risk prediction tool and is capable of identifying lung cancer patients with bone metastases who are at high risk for 3 month mortality, informing risk counseling, and aiding clinical treatment decision-making. It is better advised for patients in the high-risk group to have radiotherapy alone, the best supportive care, or minimally invasive procedures like cementoplasty.

A handheld intelligent single-molecule binary bioelectronic system for fast and reliable immunometric point-of-care testing

Molecular tests are highly reliable and sensitive but lack portability and are not simple to use; conversely, easy-to-use antigenic tests still lack high performance. BioScreen combines single-molecule sensitivity and outstanding reliability with ultraportability and simplicity of use. This digital platform is capable of artificial intelligence-based binary classification at the limit of identification of a single marker/virus in 0.1 ml. The diagnostic sensitivity, specificity, and accuracy reach 99.2% as validated through 240 assays, including a pilot clinical trial. The versatile immunometric system can detect the SARS-CoV-2 virus, spike S1, and immunoglobulin G antigen proteins in saliva, blood serum, and swab. BioScreen has a small footprint comprising a disposable cartridge and a handheld electronic reader connected to a smart device. The sample handling is minimal, and the assay time to result is 21 min. Reliable and sensitive self-testing with an ultraportable and easy-to-use diagnostic system operated directly by a patient holds the potential to revolutionize point-of-care testing and early diagnosis.

Construction and Research of Constructive English Teaching Model Applying Multimodal Neural Network Algorithm

This article draws on previous research on constructive English teaching models and uses multimodal neural network algorithm theory and constructive English teaching as the theoretical basis, experimental research method, questionnaire survey method, and evaluation method. In this article, we propose a multimodal neural network consisting of a multiscale FCN module and an LSTM module. The network focuses on both the multiscale geometric spatial features and the numerical time-dependent features of the time series curves, and with the comprehensive knowledge of their characteristics, it can better distinguish the classes to which the series belong. A large-scale perceptual field is achieved by null convolution in the model to ensure that the training pressure does not increase significantly. A series of experiments on the UCR dataset verifies the effectiveness and superiority of the model. Simulation experiments were conducted to build the proposed constructive English teaching model based on a multimodal neural network algorithm, and a test environment was built for use case testing. The experimental results showed that the algorithm can be better applied to constructive English teaching and has better adaptability and accuracy in various scenarios. At the end of the experiment, a posttest of grammar level was conducted in two classes to test whether the constructive English teaching model based on the multimodal neural network model could help students improve their English grammar skills. The results of the data analysis showed that the mean score of the experimental class was significantly higher than that of the control class, and the experimental class showed a more significant improvement, indicating that this new constructive English teaching model was beneficial to improving students' English grammar skills. The interaction strategy proposed under the constructive English teaching model can effectively improve the interaction between teachers and students. This positive feedback effect can provide front-line teachers with corresponding teaching references.

Challenges and the Evolving Landscape of Assessing Blood-Based PD-L1 Expression as a Biomarker for Anti-PD-(L)1 Immunotherapy

While promising, PD-L1 expression on tumor tissues as assessed by immunohistochemistry has been shown to be an imperfect biomarker that only applies to a limited number of cancers, whereas many patients with PD-L1-negative tumors still respond to anti-PD-(L)1 immunotherapy. Recent studies using patient blood samples to assess immunotherapeutic responsiveness suggests a promising approach to the identification of novel and/or improved biomarkers for anti-PD-(L)1 immunotherapy. In this review, we discuss the advances in our evolving understanding of the regulation and function of PD-L1 expression, which is the foundation for developing blood-based PD-L1 as a biomarker for anti-PD-(L)1 immunotherapy. We further discuss current knowledge and clinical study results for biomarker identification using PD-L1 expression on tumor and immune cells, exosomes, and soluble forms of PD-L1 in the peripheral blood. Finally, we discuss key challenges for the successful development of the potential use of blood-based PD-L1 as a biomarker for anti-PD-(L)1 immunotherapy.

Swarm learning for decentralized artificial intelligence in cancer histopathology

Artificial intelligence (AI) can predict the presence of molecular alterations directly from routine histopathology slides. However, training robust AI systems requires large datasets for which data collection faces practical, ethical and legal obstacles. These obstacles could be overcome with swarm learning (SL), in which partners jointly train AI models while avoiding data transfer and monopolistic data governance. Here, we demonstrate the successful use of SL in large, multicentric datasets of gigapixel histopathology images from over 5,000 patients. We show that AI models trained using SL can predict BRAF mutational status and microsatellite instability directly from hematoxylin and eosin (H&E)-stained pathology slides of colorectal cancer. We trained AI models on three patient cohorts from Northern Ireland, Germany and the United States, and validated the prediction performance in two independent datasets from the United Kingdom. Our data show that SL-trained AI models outperform most locally trained models, and perform on par with models that are trained on the merged datasets. In addition, we show that SL-based AI models are data efficient. In the future, SL can be used to train distributed AI models for any histopathology image analysis task, eliminating the need for data transfer.

A decentralized, privacy-preserving machine learning framework used to train a clinically relevant AI system identifies actionable molecular alterations in patients with colorectal cancer by use of routine histopathology slides collected in real-world settings.

The future of early cancer detection

A proactive approach to detecting cancer at an early stage can make treatments more effective, with fewer side effects and improved long-term survival. However, as detection methods become increasingly sensitive, it can be difficult to distinguish inconsequential changes from lesions that will lead to life-threatening cancer. Progress relies on a detailed understanding of individualized risk, clear delineation of cancer development stages, a range of testing methods with optimal performance characteristics, and robust evaluation of the implications for individuals and society. In the future, advances in sensors, contrast agents, molecular methods, and artificial intelligence will help detect cancer-specific signals in real time. To reduce the burden of cancer on society, risk-based detection and prevention needs to be cost effective and widely accessible.

Lessons for Oncology From the COVID-19 Pandemic: Operationalizing and Scaling Virtual Cancer Care in Health Systems

ABSTRACT

After several decades of slow expansion, the use of virtual care in oncology rapidly expanded during the COVID-19 pandemic. Data from cancer centers across the country show that most patients and providers were satisfied with components of virtual care, and virtual care may be able to improve access to care. However, the rapid implementation of programs during the pandemic worsened disparities in access to virtual care. Health systems must develop strategies to monitor quality, support patients and providers, promote health equity, and overcome regulatory challenges to successfully deliver care in hybrid systems that combine in-person and virtual care.

Her-2 directed systemic delivery of fatty acid synthase (FASN) siRNA with novel liposomal carrier systems in the breast cancer mouse model

Despite the current advancements in the gene silencing therapy in vitro, the systemic delivery of siRNA still remains a challenging task for its transition into clinics. We have previously developed the Her2-targeted fatty acid synthase (FASN) siRNA-encapsulating immunoliposomes (ILs) with a great stability in the presence of serum. We report here the therapeutic potential of the lipid-based novel formulations in the breast cancer mouse model. The growth inhibitory and gene silencing effects of various formulations were determined by measuring the size of the tumor, cell proliferation, apoptotic index and immunoassays against Her2-over expressed tumor xenografts in nude mice. The pegylated DSPC/Chol and DOPE/CHEMS immunoliposomes containing FASN-siRNA significantly decreased the tumor growth relative to non-targeted liposomes. They induced the 1.5-fold increase in cellular apoptosis and several fold decrease in proliferation as compared to non-targeted liposomal formulations of FASN-siRNA. Moreover, FASN-siRNA-ILs produced several fold increase in the ratios of p53/p21 and Bax/Bcl-2. The gene silencing effects of targeted FASN-liposomes were found significantly superior, resulting in 30%-40% downregulation in FASN as compared to non-targeted similar formulations. Both types of FASN immunoliposomes provided a highly efficient approach for targeted delivery in Her-2-expressed breast cancer and thus offered a promising anticancer strategy in the clinical therapy.

Application Status and Prospects of Artificial Intelligence in Peptic Ulcers

Peptic ulcer (PU) is a common and frequently occurring disease. Although PU seriously threatens the lives and health of global residents, the applications of artificial intelligence (AI) have strongly promoted diversification and modernization in the diagnosis and treatment of PU. This minireview elaborates on the research progress of AI in the field of PU, from PU's pathogenic factor Helicobacter pylori (Hp) infection, diagnosis and differential diagnosis, to its management and complications (bleeding, obstruction, perforation and canceration). Finally, the challenges and prospects of AI application in PU are prospected and expounded. With the in-depth understanding of modern medical technology, AI remains a promising option in the management of PU patients and plays a more indispensable role. How to realize the robustness, versatility and diversity of multifunctional AI systems in PU and conduct multicenter prospective clinical research as soon as possible are the top priorities in the future.

Application of Artificial Intelligence to Overcome Clinical Information Overload in Urologic Cancer

OBJECTIVE

To describe the use of artificial intelligence (AI) in medical literature and trial data extraction, and its applications in uro-oncology. This bridging review, which consolidates information from the diverse applications of AI, highlights how AI users can investigate more sophisticated queries than with traditional methods, leading to synthesis of raw data and complex outputs into more actionable and personalized results, particularly in the field of uro-oncology.

METHODS

Literature and clinical trial searches were performed in PubMed, Dimensions, Embase and Google (1999-2020). The searches focused on the use of AI and its various forms to facilitate literature searches, clinical guidelines development, and clinical trial data extraction in uro-oncology. To illustrate how AI can be applied toaddress questions about optimizing therapeutic decision making and individualizing treatment regimens, the Dimensions-linked information platform was searched for "prostate cancer" keywords (76 publications were identified; 48 were included).

RESULTS

AI offers the promise of transforming raw data and complex outputs into actionable insights. Literature and clinical trial searches can be automated, enabling clinicians to develop and analyze publications expeditiously on complex issues such as therapeutic sequencing and to obtain updates on documents that evolve at the pace and scope of the landscape. An AI-based platform inclusive of 12 trial databases and >100 scientific literature sources enabled the creation of an interactive visualization.

CONCLUSION

As the literature and clinical trial landscape continues to grow in complexity and with increasing speed, the ability to pull the right information at the right time from different search engines and resources while excluding social media bias becomes more challenging. This review demonstrates that by applying natural language processing and machine learning algorithms, validated and optimized AI leads to a speedier, more personalized, efficient and focused search compared with traditional methods.