A review on multimodal machine learning in medical diagnostics.

Nowadays, the increasing number of medical diagnostic data and clinical data provide more complementary references for doctors to make diagnosis to patients. For example, with medical data, such as electrocardiography (ECG), machine learning algorithms can be used to identify and diagnose heart disease to reduce the workload of doctors. However, ECG data is always exposed to various kinds of noise and interference in reality, and medical diagnostics only based on one-dimensional ECG data is not trustable enough. By extracting new features from other types of medical data, we can implement enhanced recognition methods, called multimodal learning. Multimodal learning helps models to process data from a range of different sources, eliminate the requirement for training each single learning modality, and improve the robustness of models with the diversity of data. Growing number of articles in recent years have been devoted to investigating how to extract data from different sources and build accurate multimodal machine learning models, or deep learning models for medical diagnostics. This paper reviews and summarizes several recent papers that dealing with multimodal machine learning in disease detection, and identify topics for future research.

Single-cell and spatial transcriptome analyses revealed cell heterogeneity and immune environment alternations in metastatic axillary lymph nodes in breast cancer.

BACKGROUND: Tumor heterogeneity plays essential roles in developing cancer therapies, including therapies for breast cancer (BC). In addition, it is also very important to understand the relationships between tumor microenvironments and the systematic immune environment. METHODS: Here, we performed single-cell, VDJ sequencing and spatial transcriptome analyses on tumor and adjacent normal tissue as well as axillar lymph nodes (LNs) and peripheral blood mononuclear cells (PBMCs) from 8 BC patients. RESULTS: We found that myeloid cells exhibited environment-dependent plasticity, where a group of macrophages with both M1 and M2 signatures possessed high tumor specificity spatially and was associated with worse patient survival. Cytotoxic T cells in tumor sites evolved in a separate path from those in the circulatory system. T cell receptor (TCR) repertoires in metastatic LNs showed significant higher consistency with TCRs in tumor than those in nonmetastatic LNs and PBMCs, suggesting the existence of common neo-antigens across metastatic LNs and primary tumor cites. In addition, the immune environment in metastatic LNs had transformed into a tumor-like status, where pro-inflammatory macrophages and exhausted T cells were upregulated, accompanied by a decrease in B cells and neutrophils. Finally, cell interactions showed that cancer-associated fibroblasts (CAFs) contributed most to shaping the immune-suppressive microenvironment, while CD8+ cells were the most signal-responsive cells. CONCLUSIONS: This study revealed the cell structures of both micro- and macroenvironments, revealed how different cells diverged in related contexts as well as their prognostic capacities, and displayed a landscape of cell interactions with spatial information.

All-People-Test-Based Methods for COVID-19 Infectious Disease Dynamics Simulation Model: Towards Citywide COVID Testing.

The conversion rate between asymptomatic infections and reported/unreported symptomatic infections is a very sensitive parameter for model variables that spread COVID-19. This is important information for follow-up use in screening, prediction, prognostics, contact tracing, and drug development for the COVID-19 pandemic. The model described here suggests that there may not be enough researchers to solve all of these problems thoroughly and effectively, and it requires careful selection of what we are doing and rapid sharing of results and models and optimizing modeling simulations with value to reduce the impact of COVID-19. Exploring simulation modeling will help decision makers make the most informed decisions. In order to fight against the "Delta" virus, the establishment of a line of defense through all-people testing (APT) is not only an effective method summarized from past experience but also one of the best means to effectively cut the chain of epidemic transmission. The effect of large-scale testing has been fully verified in the international community. We developed a practical dynamic infectious disease model-SETPG (A + I) RD + APT by considering the effects of the all-people test (APT). The model is useful for studying effects of screening measures and providing a more realistic modelling with all-people-test strategies, which require everybody in a population to be tested for infection. In prior work, a total of 370 epidemic cases were collected. We collected three kinds of known cases: the cumulative number of daily incidences, daily cumulative recovery, and daily cumulative deaths in Hong Kong and the United States between 22 January 2020 and 13 November 2020 were simulated. In two essential strategies of the integrated SETPG (A + I) RD + APT model, comparing the cumulative number of screenings in derivative experiments based on daily detection capability and tracking system application rate, we evaluated the performance of the timespan required for the basic regeneration number (R0) and real-time regeneration number (R0t) to reach 1; the optimal policy of each experiment is available, and the screening effect is evaluated by screening performance indicators. with the binary encoding screening method, the number of screenings for the target population is 8667 in HK and 1,803,400 in the U.S., including 6067 asymptomatic cases in HK and 1,262,380 in the U.S. as well as 2599 cases of mild symptoms in HK and 541,020 in the U.S.; there were also 8.25 days of screening timespan in HK and 9.25 days of screening timespan required in the U.S. and a daily detectability of 625,000 cases in HK and 6,050,000 cases in the U.S. Using precise tracking technology, number of screenings for the target population is 6060 cases in HK and 1,766,420 cases in the U.S., including 4242 asymptomatic cases in HK and 1,236,494 cases in the U.S. as well as 1818 cases of mild symptoms in HK and 529,926 cases in the U.S. Total screening timespan (TS) is 8.25~9.25 days. According to the proposed infectious dynamics model that adapts to the all-people test, all of the epidemic cases were reported for fitting, and the result seemed more reasonable, and epidemic prediction became more accurate. It adapted to densely populated metropolises for APT on prevention.

Multi-Label Attribute Selection of Arrhythmia for Electrocardiogram Signals with Fusion Learning.

There are three primary challenges in the automatic diagnosis of arrhythmias by electrocardiogram (ECG): the significant variation among individual patients, the multiple pathologies in the ECG signal and the high cost in annotating clinical ECG with the corresponding labels. Traditional ECG processing approaches rely heavily on prior knowledge, such as those from feature extraction and waveform analysis. The preprocessing for prior knowledge incurs computational overhead. Furthermore, standard deep learning methods do not fully consider the dynamic temporal, spatial and multi-labeling characteristics of ECG data. In clinical ECG waveforms, it is common to see multi-labeling in which a patient is labeled with multiple classes of arrhythmias. However, multiclass approaches in current research mainly solve the multi-label machine learning problem, ignoring the correlation between diseases, resulting in information loss. In this paper, an arrhythmia detection and classification scheme called multi-label fusion deep learning is proposed. The objective is to build a unified system with automatic feature learning which supports effective multi-label classification. First, a multi-label ECG-based feature selection method is combined with a matrix decomposition and sparse learning theory. The optimal feature subset is selected as a preprocessing algorithm for ECG data. A multi-label classifier is then constructed by fusing CNN and RNN networks to fully exploit the interactions and features of the time and space dimensions. The experimental result demonstrates that the proposed method can achieve a state-of-the-art performance compared to other algorithms in multi-label database experiments.

An ambient air quality evaluation model based on improved evidence theory.

It is significant to evaluate the air quality scientifically for the management of air pollution. As an air quality comprehensive evaluation problem, its uncertainty can be effectively addressed by the Dempster-Shafer (D-S) evidence theory. However, there is not enough research on air quality comprehensive assessment using D-S theory. Aiming at the counterintuitive fusion results of the D-S combination rule in the field of comprehensive decision, an improved evidence theory with evidence weight and evidence decision credibility (here namely DCre-Weight method) is proposed, and it is used to comprehensively evaluate air quality. First, this method determines the weights of evidence by the entropy weight method and introduces the decision credibility by calculating the dispersion of different evidence decisions. An algorithm case shows that the credibility of fusion results is improved and the uncertainty is well expressed. It can make reasonable fusion results and solve the problems of D-S. Then, the air quality evaluation model based on improved evidence theory (here namely the DCreWeight model) is proposed. Finally, according to the hourly air pollution data in Xi'an from June 1, 2014, to May 1, 2016, comparisons are made with the D-S, other improved methods of evidence theory, and a recent fuzzy synthetic evaluation method to validate the effectiveness of the model. Under the national AQCI standard, the MAE and RMSE of the DCreWeight model are 1.02 and 1.17. Under the national AQI standard, the DCreWeight model has the minimal MAE, RMSE, and maximal index of agreement, which validated the superiority of the DCreWeight model. Therefore, the DCreWeight model can comprehensively evaluate air quality. It can provide a scientific basis for relevant departments to prevent and control air pollution.

A new SEAIRD pandemic prediction model with clinical and epidemiological data analysis on COVID-19 outbreak.

Measuring the spread of disease during a pandemic is critically important for accurately and promptly applying various lockdown strategies, so to prevent the collapse of the medical system. The latest pandemic of COVID-19 that hits the world death tolls and economy loss very hard, is more complex and contagious than its precedent diseases. The complexity comes mostly from the emergence of asymptomatic patients and relapse of the recovered patients which were not commonly seen during SARS outbreaks. These new characteristics pertaining to COVID-19 were only discovered lately, adding a level of uncertainty to the traditional SEIR models. The contribution of this paper is that for the COVID-19 epidemic, which is infectious in both the incubation period and the onset period, we use neural networks to learn from the actual data of the epidemic to obtain optimal parameters, thereby establishing a nonlinear, self-adaptive dynamic coefficient infectious disease prediction model. On the basis of prediction, we considered control measures and simulated the effects of different control measures and different strengths of the control measures. The epidemic control is predicted as a continuous change process, and the epidemic development and control are integrated to simulate and forecast. Decision-making departments make optimal choices. The improved model is applied to simulate the COVID-19 epidemic in the United States, and by comparing the prediction results with the traditional SEIR model, SEAIRD model and adaptive SEAIRD model, it is found that the adaptive SEAIRD model's prediction results of the U.S. COVID-19 epidemic data are in good agreement with the actual epidemic curve. For example, from the prediction effect of these 3 different models on accumulative confirmed cases, in terms of goodness of fit, adaptive SEAIRD model (0.99997) ≈ SEAIRD model (0.98548) > Classical SEIR model (0.66837); in terms of error value: adaptive SEAIRD model (198.6563) < < SEAIRD model(4739.8577) < < Classical SEIR model (22,652.796); The objective of this contribution is mainly on extending the current spread prediction model. It incorporates extra compartments accounting for the new features of COVID-19, and fine-tunes the new model with neural network, in a bid of achieving a higher level of prediction accuracy. Based on the SEIR model of disease transmission, an adaptive model called SEAIRD with internal source and isolation intervention is proposed. It simulates the effects of the changing behaviour of the SARS-CoV-2 in U.S. Neural network is applied to achieve a better fit in SEAIRD. Unlike the SEIR model, the adaptive SEAIRD model embraces multi-group dynamics which lead to different evolutionary trends during the epidemic. Through the risk assessment indicators of the adaptive SEAIRD model, it is convenient to measure the severity of the epidemic situation for consideration of different preventive measures. Future scenarios are projected from the trends of various indicators by running the adaptive SEAIRD model.

An ECG data sampling method for home-use IoT ECG monitor system optimization based on brick-up metaheuristic algorithm.

With the rise in the popularity of Internet of Things (IoT) in-home health monitoring, the demand of data processing and analysis increases at the server. This is especially true for ECG data which has to be collected and analyzed continuously in real time. The data transmission and storage capacity of a simple home-use IoT system is often limited. In order to provide a responsive and reasonably high-resolution analysis over the data, the ECG recorder sampling rate must be tuned to an acceptable level such as 50Hz (compared to between 100Hz and 500Hz in lab), a huge amount of time series are to be gathered and dealt with. Therefore, a suitable sampling method that helps shorten the ECG data transformation time and uploading time is very important for cost saving.. In this paper, how to down sample the ECG data is investigated; instead of traditional data sampling methods, the use of a novel Brick-up Metaheuristic Optimization Algorithm (BMOA) that automatically optimizes the sampling of ECG data is proposed. By its adaptive design in choosing the most appropriate components, BMOA can build in real-time a best metaheuristic optimization algorithm for each device user assuming no two ECG data series are exactly identical. This dynamic pre-processing approach ensures each time the most optimal part of the ECG data series is harvested for health analysis from the raw data, in different scenarios from different users. In this study various application scenarios using real ECG datasets are simulated. The experimentation is tested with one of the most commonly used ECG classification methods, Long Short-Term Memory Network. The result shows the ECG data sampling by BMOA is indeed adaptive, the classification efficiency is improved, and the data storage requirement is reduced.

Discriminable Multi-Label Attribute Selection for Pre-Course Student Performance Prediction.

The university curriculum is a systematic and organic study complex with some immediate associated steps; the initial learning of each semester's course is crucial, and significantly impacts the learning process of subsequent courses and further studies. However, the low teacher-student ratio makes it difficult for teachers to consistently follow up on the detail-oriented learning situation of individual students. The extant learning early warning system is committed to automatically detecting whether students have potential difficulties-or even the risk of failing, or non-pass reports-before starting the course. Previous related research has the following three problems: first of all, it mainly focused on e-learning platforms and relied on online activity data, which was not suitable for traditional teaching scenarios; secondly, most current methods can only proffer predictions when the course is in progress, or even approaching the end; thirdly, few studies have focused on the feature redundancy in these learning data. Aiming at the traditional classroom teaching scenario, this paper transforms the pre-class student performance prediction problem into a multi-label learning model, and uses the attribute reduction method to scientifically streamline the characteristic information of the courses taken and explore the important relationship between the characteristics of the previously learned courses and the attributes of the courses to be taken, in order to detect high-risk students in each course before the course begins. Extensive experiments were conducted on 10 real-world datasets, and the results proved that the proposed approach achieves better performance than most other advanced methods in multi-label classification evaluation metrics.

Convolutional neural network with group theory and random selection particle swarm optimizer for enhancing cancer image classification.

As an epitome of deep learning, convolutional neural network (CNN) has shown its advantages in solving many real-world problems. Successful CNN applications on medical prognosis and diagnosis have been achieved in recent years. Their common goal is to recognize the insights from the subtle details from medical images by building a suitable CNN model with maximum accuracy and minimum error. The CNN performance is extremely sensitive to the parameter tuning for any given network structure. To approach this concern, a novel self-tuning CNN model is proposed with a significant characteristic of having a metaheuristic-based optimizer. The most optimal set of parameters is often found via our proposed method, namely group theory and random selection-based particle swarm optimization (GTRS-PSO). The insights of symmetric essentials of model structure and parameter correlation are extracted, followed by the hierarchical partitioning of parameter space, and four operators on those partitions are designed for moving neighborhoods and formulating the swarm topology accordingly. The parameters are updated by a random selection strategy at each interval of partitions during the search process. Preliminary experiments over two radiology image datasets: breast cancer and lung cancer, are conducted for a comprehensive comparison of GTRS-PSO versus other optimization algorithms. The results show that CNN with GTRS-PSO optimizer can achieve the best performance for cancer image classifications, especially when there are symmetric components inside the data properties and model structures.

Artificial intelligence in the diagnosis of COVID-19: challenges and perspectives.

Artificial intelligence (AI) is being used to aid in various aspects of the COVID-19 crisis, including epidemiology, molecular research and drug development, medical diagnosis and treatment, and socioeconomics. The association of AI and COVID-19 can accelerate to rapidly diagnose positive patients. To learn the dynamics of a pandemic with relevance to AI, we search the literature using the different academic databases (PubMed, PubMed Central, Scopus, Google Scholar) and preprint servers (bioRxiv, medRxiv, arXiv). In the present review, we address the clinical applications of machine learning and deep learning, including clinical characteristics, electronic medical records, medical images (CT, X-ray, ultrasound images, etc.) in the COVID-19 diagnosis. The current challenges and future perspectives provided in this review can be used to direct an ideal deployment of AI technology in a pandemic.

Modelling dynamics of coronavirus disease 2019 spread for pandemic forecasting based on Simulink.

In this paper, we demonstrate the application of MATLAB to develop a pandemic prediction system based on Simulink. The susceptible-exposed-asymptomatic but infectious-symptomatic and infectious (severe infected population + mild infected population)-recovered-deceased (SEAI(I1+I2)RD) physical model for unsupervised learning and two types of supervised learning, namely, fuzzy proportional-integral-derivative (PID) and wavelet neural-network PID learning, are used to build a predictive-control system model that enables self-learning artificial intelligence (AI)-based control. After parameter setting, the data entering the model are predicted, and the value of the data set at a future moment is calculated. PID controllers are added to ensure that the system does not diverge at the beginning of iterative learning. To adapt to complex system conditions and afford excellent control, a wavelet neural-network PID control strategy is developed that can be adjusted and corrected in real time, according to the output error.

White learning methodology: A case study of cancer-related disease factors analysis in real-time PACS environment.

BACKGROUND AND OBJECTIVE: Bayesian network is a probabilistic model of which the prediction accuracy may not be one of the highest in the machine learning family. Deep learning (DL) on the other hand possess of higher predictive power than many other models. How reliable the result is, how it is deduced, how interpretable the prediction by DL mean to users, remain obscure. DL functions like a black box. As a result, many medical practitioners are reductant to use deep learning as the only tool for critical machine learning application, such as aiding tool for cancer diagnosis. METHODS: In this paper, a framework of white learning is being proposed which takes advantages of both black box learning and white box learning. Usually, black box learning will give a high standard of accuracy and white box learning will provide an explainable direct acyclic graph. According to our design, there are 3 stages of White Learning, loosely coupled WL, semi coupled WL and tightly coupled WL based on degree of fusion of the white box learning and black box learning. In our design, a case of loosely coupled WL is tested on breast cancer dataset. This approach uses deep learning and an incremental version of Naïve Bayes network. White learning is largely defied as a systemic fusion of machine learning models which result in an explainable Bayes network which could find out the hidden relations between features and class and deep learning which would give a higher accuracy of prediction than other algorithms. We designed a series of experiments for this loosely coupled WL model. RESULTS: The simulation results show that using WL compared to standard black-box deep learning, the levels of accuracy and kappa statistics could be enhanced up to 50%. The performance of WL seems more stable too in extreme conditions such as noise and high dimensional data. The relations by Bayesian network of WL are more concise and stronger in affinity too. CONCLUSION: The experiments results deliver positive signals that WL is possible to output both high classification accuracy and explainable relations graph between features and class.

Social Group Optimization-Assisted Kapur's Entropy and Morphological Segmentation for Automated Detection of COVID-19 Infection from Computed Tomography Images.

The coronavirus disease (COVID-19) caused by a novel coronavirus, SARS-CoV-2, has been declared a global pandemic. Due to its infection rate and severity, it has emerged as one of the major global threats of the current generation. To support the current combat against the disease, this research aims to propose a machine learning-based pipeline to detect COVID-19 infection using lung computed tomography scan images (CTI). This implemented pipeline consists of a number of sub-procedures ranging from segmenting the COVID-19 infection to classifying the segmented regions. The initial part of the pipeline implements the segmentation of the COVID-19-affected CTI using social group optimization-based Kapur's entropy thresholding, followed by k-means clustering and morphology-based segmentation. The next part of the pipeline implements feature extraction, selection, and fusion to classify the infection. Principle component analysis-based serial fusion technique is used in fusing the features and the fused feature vector is then employed to train, test, and validate four different classifiers namely Random Forest, K-Nearest Neighbors (KNN), Support Vector Machine with Radial Basis Function, and Decision Tree. Experimental results using benchmark datasets show a high accuracy (> 91%) for the morphology-based segmentation task; for the classification task, the KNN offers the highest accuracy among the compared classifiers (> 87%). However, this should be noted that this method still awaits clinical validation, and therefore should not be used to clinically diagnose ongoing COVID-19 infection.

Parallel ensemble learning of convolutional neural networks and local binary patterns for face recognition.

BACKGROUND AND OBJECTIVE: Face recognition success rate is influenced by illumination, expression, posture change, and other factors, which is due to the low generalization ability of a single convolutional neural network. A new face recognition method based on parallel ensemble learning of convolutional neural networks (CNN) and local binary patterns (LBP) is proposed to solve this problem. It also helps to improve the low pedestrian detection rate caused by occlusion. METHODS: First, the LBP operator is employed to extract features of the face texture. After that, 10 convolutional neural networks with 5 different network structures are adopted to further extract features for training, to improve the network parameters and get classification result by using the Softmax function after the layer is fully connected. Finally, the method of parallel ensemble learning is used to generate the final result of face recognition using majority voting. RESULTS: By this method, the recognition rates in the ORL and Yale-B face datasets increase to 100% and 97.51%, respectively. In the experiments, the proposed approach is illustrated not only enhances its tolerance to illumination, expression, and posture but also improves the accuracy of face recognition and the poor generalization performance of the model, which is normally caused by the learning algorithm being trapped in a local minimum. Moreover, the proposed method is combined with a pedestrian detection model as a hybrid model for improving the detection rate, which shows in the result that the detection rate is improved by 11.2%. CONCLUSION: In summary, the proposed approach greatly outperforms other competitive methods.

Composite Monte Carlo decision making under high uncertainty of novel coronavirus epidemic using hybridized deep learning and fuzzy rule induction.

In the advent of the novel coronavirus epidemic since December 2019, governments and authorities have been struggling to make critical decisions under high uncertainty at their best efforts. In computer science, this represents a typical problem of machine learning over incomplete or limited data in early epidemic Composite Monte-Carlo (CMC) simulation is a forecasting method which extrapolates available data which are broken down from multiple correlated/casual micro-data sources into many possible future outcomes by drawing random samples from some probability distributions. For instance, the overall trend and propagation of the infested cases in China are influenced by the temporal-spatial data of the nearby cities around the Wuhan city (where the virus is originated from), in terms of the population density, travel mobility, medical resources such as hospital beds and the timeliness of quarantine control in each city etc. Hence a CMC is reliable only up to the closeness of the underlying statistical distribution of a CMC, that is supposed to represent the behaviour of the future events, and the correctness of the composite data relationships. In this paper, a case study of using CMC that is enhanced by deep learning network and fuzzy rule induction for gaining better stochastic insights about the epidemic development is experimented. Instead of applying simplistic and uniform assumptions for a MC which is a common practice, a deep learning-based CMC is used in conjunction of fuzzy rule induction techniques. As a result, decision makers are benefited from a better fitted MC outputs complemented by min-max rules that foretell about the extreme ranges of future possibilities with respect to the epidemic.

Mining Massive E-Health Data Streams for IoMT Enabled Healthcare Systems.

With the increasing popularity of the Internet-of-Medical-Things (IoMT) and smart devices, huge volumes of data streams have been generated. This study aims to address the concept drift, which is a major challenge in the processing of voluminous data streams. Concept drift refers to overtime change in data distribution. It may occur in the medical domain, for example the medical sensors measuring for general healthcare or rehabilitation, which may switch their roles for ICU emergency operations when required. Detecting concept drifts becomes trickier when the class distributions in data are skewed, which is often true for medical sensors e-health data. Reactive Drift Detection Method (RDDM) is an efficient method for detecting long concepts. However, RDDM has a high error rate, and it does not handle class imbalance. We propose an Enhanced Reactive Drift Detection Method (ERDDM), which systematically generates strategies to handle concept drift with class imbalance in data streams. We conducted experiments to compare ERDDM with three contemporary techniques in terms of prediction error, drift detection delay, latency, and ability to handle data imbalance. The experimentation was done in Massive Online Analysis (MOA) on 48 synthetic datasets customized to possess the capabilities of data streams. ERDDM can handle abrupt and gradual drifts and performs better than all benchmarks in almost all experiments.

Quantifying breast milk intake by term and preterm infants for input into paediatric physiologically based pharmacokinetic models.

Despite the many benefits of breast milk, mothers taking medication are often uncertain about the risks of drug exposure to their infants and decide not to breastfeed. Physiologically based pharmacokinetic models can contribute to drug-in-milk safety assessments by predicting the infant exposure and subsequently, risk for toxic effects that would result from continuous breastfeeding. This review aimed to quantify breast milk intake feeding parameters in term and preterm infants using literature data for input into paediatric physiologically based pharmacokinetic models designed for drug-in-milk risk assessment. Ovid MEDLINE and Embase were searched up to July 2, 2019. Key study reference lists and grey literature were reviewed. Title, abstract and full text were screened in nonduplicate. Daily weight-normalized human milk intake (WHMI) and feeding frequency by age were extracted. The review process retrieved 52 studies. A nonlinear regression equation was constructed to describe the WHMI of exclusively breastfed term infants from birth to 1 year of age. In all cases, preterm infants fed with similar feeding parameters to term infants on a weight-normalized basis. Maximum WHMI was 152.6 ml/kg/day at 19.7 days, and weighted mean feeding frequency was 7.7 feeds/day. Existing methods for approximating breast milk intake were refined by using a comprehensive set of literature data to describe WHMI and feeding frequency. Milk feeding parameters were quantified for preterm infants, a vulnerable population at risk for high drug exposure and toxic effects. A high-risk period of exposure at 2-4 weeks of age was identified and can inform future drug-in-milk risk assessments.

Artificial intelligence in cancer diagnosis and prognosis: Opportunities and challenges.

Cancer is an aggressive disease with a low median survival rate. Ironically, the treatment process is long and very costly due to its high recurrence and mortality rates. Accurate early diagnosis and prognosis prediction of cancer are essential to enhance the patient's survival rate. Developments in statistics and computer engineering over the years have encouraged many scientists to apply computational methods such as multivariate statistical analysis to analyze the prognosis of the disease, and the accuracy of such analyses is significantly higher than that of empirical predictions. Furthermore, as artificial intelligence (AI), especially machine learning and deep learning, has found popular applications in clinical cancer research in recent years, cancer prediction performance has reached new heights. This article reviews the literature on the application of AI to cancer diagnosis and prognosis, and summarizes its advantages. We explore how AI assists cancer diagnosis and prognosis, specifically with regard to its unprecedented accuracy, which is even higher than that of general statistical applications in oncology. We also demonstrate ways in which these methods are advancing the field. Finally, opportunities and challenges in the clinical implementation of AI are discussed. Hence, this article provides a new perspective on how AI technology can help improve cancer diagnosis and prognosis, and continue improving human health in the future.

Development of interventions for an intelligent and individualized mobile health care system to promote healthy diet and physical activity: using an intervention mapping framework.

BACKGROUND: The mortality of coronary heart disease can be largely reduced by modifying unhealthy lifestyles. However, the long-term effectiveness of interventions for modifying unhealthy diet and physical inactivity of patients with coronary heart disease remain unsatisfactory worldwide. This study aims to systematically design a set of theory-based and evidence-based, individualized, and intelligent interventions for promoting the adoption and maintenance of a healthy diet and physical activity level in patients with coronary heart disease. METHODS: The interventions will be delivered by a mobile health care system called Individualized, Intelligent and Integrated Cardiovascular Application for Risk Elimination. Three steps of the intervention mapping framework were used to systematically develop the interventions. Step 1: needs assessment, which was carried out by a literature review, in-depth interviews and focus group discussions. Step 2: development of objective matrix for diet and physical activity changes, based on the intersection of objectives and determinants from the Contemplation-Action-Maintenance behavior change model. Step 3: formulation of evidence-based methods and strategies, and practical applications, through a systematic review of existing literature, research team discussions, and consultation with multidisciplinary expert panels. RESULTS: Three needs relevant to content of the intervention, one need relevant to presentation modes of the intervention, and four needs relevant to functional features of the application were identified. The objective matrix includes three performance objectives, and 24 proximal performance objectives. The evidence-based and theory-based interventions include 31 strategies, 61 evidence-based methods, and 393 practical applications. CONCLUSIONS: This article describes the development of theory-based and evidence-based interventions of the mobile health care system for promoting the adoption and maintenance of a healthy diet and physical activity level in a structured format. The results will provide a theoretical and methodological basis to explore the application of intervention mapping in developing effective behavioral mobile health interventions for patients with coronary heart disease. TRIAL REGISTRATION: Chinese Clinical Trial Registry: ChiCTR-INR-16010242. Registered 24 December 2016. http://www.chictr.org.cn/index.aspx.