Secure and Robust Machine Learning for Healthcare: A Survey

E-Cardiac Care: A Comprehensive Systematic Literature Review

The Internet of Things (IoT) is a complete ecosystem encompassing various communication technologies, sensors, hardware, and software. IoT cutting-edge technologies and Artificial Intelligence (AI) have enhanced the traditional healthcare system considerably. The conventional healthcare system faces many challenges, including avoidable long wait times, high costs, a conventional method of payment, unnecessary long travel to medical centers, and mandatory periodic doctor visits. A Smart healthcare system, Internet of Things (IoT), and AI are arguably the best-suited tailor-made solutions for all the flaws related to traditional healthcare systems. The primary goal of this study is to determine the impact of IoT, AI, various communication technologies, sensor networks, and disease detection/diagnosis in Cardiac healthcare through a systematic analysis of scholarly articles. Hence, a total of 104 fundamental studies are analyzed for the research questions purposefully defined for this systematic study. The review results show that deep learning emerges as a promising technology along with the combination of IoT in the domain of E-Cardiac care with enhanced accuracy and real-time clinical monitoring. This study also pins down the key benefits and significant challenges for E-Cardiology in the domains of IoT and AI. It further identifies the gaps and future research directions related to E-Cardiology, monitoring various Cardiac parameters, and diagnosis patterns.

Recent Advancements in Emerging Technologies for Healthcare Management Systems: A Survey

In recent times, the growth of the Internet of Things (IoT), artificial intelligence (AI), and Blockchain technologies have quickly gained pace as a new study niche in numerous collegiate and industrial sectors, notably in the healthcare sector. Recent advancements in healthcare delivery have given many patients access to advanced personalized healthcare, which has improved their well-being. The subsequent phase in healthcare is to seamlessly consolidate these emerging technologies such as IoT-assisted wearable sensor devices, AI, and Blockchain collectively. Surprisingly, owing to the rapid use of smart wearable sensors, IoT and AI-enabled technology are shifting healthcare from a conventional hub-based system to a more personalized healthcare management system (HMS). However, implementing smart sensors, advanced IoT, AI, and Blockchain technologies synchronously in HMS remains a significant challenge. Prominent and reoccurring issues such as scarcity of cost-effective and accurate smart medical sensors, unstandardized IoT system architectures, heterogeneity of connected wearable devices, the multidimensionality of data generated, and high demand for interoperability are vivid problems affecting the advancement of HMS. Hence, this survey paper presents a detailed evaluation of the application of these emerging technologies (Smart Sensor, IoT, AI, Blockchain) in HMS to better understand the progress thus far. Specifically, current studies and findings on the deployment of these emerging technologies in healthcare are investigated, as well as key enabling factors, noteworthy use cases, and successful deployments. This survey also examined essential issues that are frequently encountered by IoT-assisted wearable sensor systems, AI, and Blockchain, as well as the critical concerns that must be addressed to enhance the application of these emerging technologies in the HMS.

Explainable, trustworthy, and ethical machine learning for healthcare: A survey

With the advent of machine learning (ML) and deep learning (DL) empowered applications for critical applications like healthcare, the questions about liability, trust, and interpretability of their outputs are raising. The black-box nature of various DL models is a roadblock to clinical utilization. Therefore, to gain the trust of clinicians and patients, we need to provide explanations about the decisions of models. With the promise of enhancing the trust and transparency of black-box models, researchers are in the phase of maturing the field of eXplainable ML (XML). In this paper, we provided a comprehensive review of explainable and interpretable ML techniques for various healthcare applications. Along with highlighting security, safety, and robustness challenges that hinder the trustworthiness of ML, we also discussed the ethical issues arising because of the use of ML/DL for healthcare. We also describe how explainable and trustworthy ML can resolve all these ethical problems. Finally, we elaborate on the limitations of existing approaches and highlight various open research problems that require further development.

Mitigating urinary incontinence condition using machine learning

BACKGROUND

Urinary incontinence (UI) is the inability to completely control the process of releasing urine. UI presents a social, medical, and mental issue with financial consequences.

OBJECTIVE

This paper proposes a framework based on machine learning for predicting urination time, which can benefit people with various degrees of UI.

METHOD

A total of 850 data points were self-recorded by 51 participants to investigate how different factors impact urination time. The participants were instructed to record input data (such as the time of consumption and the number of drinks) and output data (i.e., the time the individual urinated). Other factors, such as age and BMI, were also considered. The study was conducted in two phases: (1) data was prepared for modeling, including missing values, data encoding, and scaling; and (2) a classification model was designed with four output classes of the next urination time: <  = 30 min, 31-60 min, 61-90 min, > 90 min. The model was built in two steps: (1) feature selection and (2) model training and testing. Feature selection methods such as lasso regression, decision tree, random forest, and chi-square were used to select the best features, which were then used to train an extreme gradient boosting (XGB) algorithm model to predict the class of the next urination time.

RESULT

The feature selection steps resulted in nine features considered the most important features affecting UI. The accuracy, precision, recall, and F1 score of the XGB predictive model are 0.70, 0.73, 0.70, and 0.71, respectively.

CONCLUSION

This research is the first step in developing a machine learning model to predict when a person will need to urinate. A precise predictive instrument can enable healthcare providers and caregivers to assist people with various forms of UI in reliable, prompted voiding. The insights from this predictive model can allow future apps to go beyond current UI-related apps by predicting the time of urination using the most relevant factors that impact voiding frequency.

MaD GUI: An Open-Source Python Package for Annotation and Analysis of Time-Series Data

Developing machine learning algorithms for time-series data often requires manual annotation of the data. To do so, graphical user interfaces (GUIs) are an important component. Existing Python packages for annotation and analysis of time-series data have been developed without addressing adaptability, usability, and user experience. Therefore, we developed a generic open-source Python package focusing on adaptability, usability, and user experience. The developed package, Machine Learning and Data Analytics (MaD) GUI, enables developers to rapidly create a GUI for their specific use case. Furthermore, MaD GUI enables domain experts without programming knowledge to annotate time-series data and apply algorithms to it. We conducted a small-scale study with participants from three international universities to test the adaptability of MaD GUI by developers and to test the user interface by clinicians as representatives of domain experts. MaD GUI saves up to 75% of time in contrast to using a state-of-the-art package. In line with this, subjective ratings regarding usability and user experience show that MaD GUI is preferred over a state-of-the-art package by developers and clinicians. MaD GUI reduces the effort of developers in creating GUIs for time-series analysis and offers similar usability and user experience for clinicians as a state-of-the-art package.

Defending against Reconstruction Attacks through Differentially Private Federated Learning for Classification of Heterogeneous Chest X-ray Data

Privacy regulations and the physical distribution of heterogeneous data are often primary concerns for the development of deep learning models in a medical context. This paper evaluates the feasibility of differentially private federated learning for chest X-ray classification as a defense against data privacy attacks. To the best of our knowledge, we are the first to directly compare the impact of differentially private training on two different neural network architectures, DenseNet121 and ResNet50. Extending the federated learning environments previously analyzed in terms of privacy, we simulated a heterogeneous and imbalanced federated setting by distributing images from the public CheXpert and Mendeley chest X-ray datasets unevenly among 36 clients. Both non-private baseline models achieved an area under the receiver operating characteristic curve (AUC) of 0.94 on the binary classification task of detecting the presence of a medical finding. We demonstrate that both model architectures are vulnerable to privacy violation by applying image reconstruction attacks to local model updates from individual clients. The attack was particularly successful during later training stages. To mitigate the risk of a privacy breach, we integrated Rényi differential privacy with a Gaussian noise mechanism into local model training. We evaluate model performance and attack vulnerability for privacy budgets ε∈{1,3,6,10}. The DenseNet121 achieved the best utility-privacy trade-off with an AUC of 0.94 for ε=6. Model performance deteriorated slightly for individual clients compared to the non-private baseline. The ResNet50 only reached an AUC of 0.76 in the same privacy setting. Its performance was inferior to that of the DenseNet121 for all considered privacy constraints, suggesting that the DenseNet121 architecture is more robust to differentially private training.

Towards Secure and Intelligent Internet of Health Things: A Survey of Enabling Technologies and Applications

With the growth of computing and communication technologies, the information processing paradigm of the healthcare environment is evolving. The patient information is stored electronically, making it convenient to store and retrieve patient information remotely when needed. However, evolving the healthcare systems into smart healthcare environments comes with challenges and additional pressures. Internet of Things (IoT) connects things, such as computing devices, through wired or wireless mediums to form a network. There are numerous security vulnerabilities and risks in the existing IoT-based systems due to the lack of intrinsic security technologies. For example, patient medical data, data privacy, data sharing, and convenience are considered imperative for collecting and storing electronic health records (EHR). However, the traditional IoT-based EHR systems cannot deal with these paradigms because of inconsistent security policies and data access structures. Blockchain (BC) technology is a decentralized and distributed ledger that comes in handy in storing patient data and encountering data integrity and confidentiality challenges. Therefore, it is a viable solution for addressing existing IoT data security and privacy challenges. BC paves a tremendous path to revolutionize traditional IoT systems by enhancing data security, privacy, and transparency. The scientific community has shown a variety of healthcare applications based on artificial intelligence (AI) that improve health diagnosis and monitoring practices. Moreover, technology companies and startups are revolutionizing healthcare with AI and related technologies. This study illustrates the implication of integrated technologies based on BC, IoT, and AI to meet growing healthcare challenges. This research study examines the integration of BC technology with IoT and analyzes the advancements of these innovative paradigms in the healthcare sector. In addition, our research study presents a detailed survey on enabling technologies for the futuristic, intelligent, and secure internet of health things (IoHT). Furthermore, this study comprehensively studies the peculiarities of the IoHT environment and the security, performance, and progression of the enabling technologies. First, the research gaps are identified by mapping security and performance benefits inferred by the BC technologies. Secondly, practical issues related to the integration process of BC and IoT devices are discussed. Third, the healthcare applications integrating IoT, BC, and ML in healthcare environments are discussed. Finally, the research gaps, future directions, and limitations of the enabling technologies are discussed.

Machine Learning and Lean Six Sigma to Assess How COVID-19 Has Changed the Patient Management of the Complex Operative Unit of Neurology and Stroke Unit: A Single Center Study

Background: In health, it is important to promote the effectiveness, efficiency and adequacy of the services provided; these concepts become even more important in the era of the COVID-19 pandemic, where efforts to manage the disease have absorbed all hospital resources. The COVID-19 emergency led to a profound restructuring-in a very short time-of the Italian hospital system. Some factors that impose higher costs on hospitals are inappropriate hospitalization and length of stay (LOS). The length of stay (LOS) is a very useful parameter for the management of services within the hospital and is an index evaluated for the management of costs. Methods: This study analyzed how COVID-19 changed the activity of the Complex Operative Unit (COU) of the Neurology and Stroke Unit of the San Giovanni di Dio e Ruggi d'Aragona University Hospital of Salerno (Italy). The methodology used in this study was Lean Six Sigma. Problem solving in Lean Six Sigma is the DMAIC roadmap, characterized by five operational phases. To add even more value to the processing, a single clinical case, represented by stroke patients, was investigated to verify the specific impact of the pandemic. Results: The results obtained show a reduction in LOS for stroke patients and an increase in the value of the diagnosis related group relative weight. Conclusions: This work has shown how, thanks to the implementation of protocols for the management of the COU of the Neurology and Stroke Unit, the work of doctors has improved, and this is evident from the values of the parameters taken into consideration.

Machine Learning for Healthcare Wearable Devices: The Big Picture

Using artificial intelligence and machine learning techniques in healthcare applications has been actively researched over the last few years. It holds promising opportunities as it is used to track human activities and vital signs using wearable devices and assist in diseases' diagnosis, and it can play a great role in elderly care and patient's health monitoring and diagnostics. With the great technological advances in medical sensors and miniaturization of electronic chips in the recent five years, more applications are being researched and developed for wearable devices. Despite the remarkable growth of using smart watches and other wearable devices, a few of these massive research efforts for machine learning applications have found their way to market. In this study, a review of the different areas of the recent machine learning research for healthcare wearable devices is presented. Different challenges facing machine learning applications on wearable devices are discussed. Potential solutions from the literature are presented, and areas open for improvement and further research are highlighted.

A Survey of Artificial Intelligence Challenges: Analyzing the Definitions, Relationships, and Evolutions

In recent years, artificial intelligence has had a tremendous impact on every field, and several definitions of its different types have been provided. In the literature, most articles focus on the extraordinary capabilities of artificial intelligence. Recently, some challenges such as security, safety, fairness, robustness, and energy consumption have been reported during the development of intelligent systems. As the usage of intelligent systems increases, the number of new challenges increases. Obviously, during the evolution of artificial narrow intelligence to artificial super intelligence, the viewpoint on the challenges such as security will be changed. In addition, the recent development of human-level intelligence cannot appropriately happen without considering whole challenges in designing intelligent systems. Considering the mentioned situation, no study in the literature summarizes the challenges in designing artificial intelligence. In this paper, a review of the challenges is presented. Then, some important research questions about the future dynamism of challenges and their relationships are answered.

Sensitivity of Machine Learning Approaches to Fake and Untrusted Data in Healthcare Domain

Machine Learning models are susceptible to attacks, such as noise, privacy invasion, replay, false data injection, and evasion attacks, which affect their reliability and trustworthiness. Evasion attacks, performed to probe and identify potential ML-trained models’ vulnerabilities, and poisoning attacks, performed to obtain skewed models whose behavior could be driven when specific inputs are submitted, represent a severe and open issue to face in order to assure security and reliability to critical domains and systems that rely on ML-based or other AI solutions, such as healthcare and justice, for example. In this study, we aimed to perform a comprehensive analysis of the sensitivity of Artificial Intelligence approaches to corrupted data in order to evaluate their reliability and resilience. These systems need to be able to understand what is wrong, figure out how to overcome the resulting problems, and then leverage what they have learned to overcome those challenges and improve their robustness. The main research goal pursued was the evaluation of the sensitivity and responsiveness of Artificial Intelligence algorithms to poisoned signals by comparing several models solicited with both trusted and corrupted data. A case study from the healthcare domain was provided to support the pursued analyses. The results achieved with the experimental campaign were evaluated in terms of accuracy, specificity, sensitivity, F1-score, and ROC area.

Towards Machine Learning-Aided Lung Cancer Clinical Routines: Approaches and Open Challenges

Advancements in the development of computer-aided decision (CAD) systems for clinical routines provide unquestionable benefits in connecting human medical expertise with machine intelligence, to achieve better quality healthcare. Considering the large number of incidences and mortality numbers associated with lung cancer, there is a need for the most accurate clinical procedures; thus, the possibility of using artificial intelligence (AI) tools for decision support is becoming a closer reality. At any stage of the lung cancer clinical pathway, specific obstacles are identified and "motivate" the application of innovative AI solutions. This work provides a comprehensive review of the most recent research dedicated toward the development of CAD tools using computed tomography images for lung cancer-related tasks. We discuss the major challenges and provide critical perspectives on future directions. Although we focus on lung cancer in this review, we also provide a more clear definition of the path used to integrate AI in healthcare, emphasizing fundamental research points that are crucial for overcoming current barriers.

Machine learning based prognostic model and mobile application software platform for predicting infection susceptibility of COVID-19 using healthcare data

Introduction

Methods

Results

Conclusion

An Overview of Medical Electronic Hardware Security and Emerging Solutions

Electronic healthcare technology is widespread around the world and creates massive potential to improve clinical outcomes and transform care delivery. However, there are increasing concerns with respect to the cyber vulnerabilities of medical tools, malicious medical errors, and security attacks on healthcare data and devices. Increased connectivity to existing computer networks has exposed the medical devices/systems and their communicating data to new cybersecurity vulnerabilities. Adversaries leverage the state-of-the-art technologies, in particular artificial intelligence and computer vision-based techniques, in order to launch stronger and more detrimental attacks on the medical targets. The medical domain is an attractive area for cybercrimes for two fundamental reasons: (a) it is rich resource of valuable and sensitive data; and (b) its protection and defensive mechanisms are weak and ineffective. The attacks aim to steal health information from the patients, manipulate the medical information and queries, maliciously change the medical diagnosis, decisions, and prescriptions, etc. A successful attack in the medical domain causes serious damage to the patient’s health and even death. Therefore, cybersecurity is critical to patient safety and every aspect of the medical domain, while it has not been studied sufficiently. To tackle this problem, new human- and computer-based countermeasures are researched and proposed for medical attacks using the most effective software and hardware technologies, such as artificial intelligence and computer vision. This review provides insights to the novel and existing solutions in the literature that mitigate cyber risks, errors, damage, and threats in the medical domain. We have performed a scoping review analyzing the four major elements in this area (in order from a medical perspective): (1) medical errors; (2) security weaknesses of medical devices at software- and hardware-level; (3) artificial intelligence and/or computer vision in medical applications; and (4) cyber attacks and defenses in the medical domain. Meanwhile, artificial intelligence and computer vision are key topics in this review and their usage in all these four elements are discussed. The review outcome delivers the solutions through building and evaluating the connections among these elements in order to serve as a beneficial guideline for medical electronic hardware security.

Towards a Connected Mobile Cataract Screening System: A Future Approach

Advances in computing and AI technology have promoted the development of connected health systems, indirectly influencing approaches to cataract treatment. In addition, thanks to the development of methods for cataract detection and grading using different imaging modalities, ophthalmologists can make diagnoses with significant objectivity. This paper aims to review the development and limitations of published methods for cataract detection and grading using different imaging modalities. Over the years, the proposed methods have shown significant improvement and reasonable effort towards automated cataract detection and grading systems that utilise various imaging modalities, such as optical coherence tomography (OCT), fundus, and slit-lamp images. However, more robust and fully automated cataract detection and grading systems are still needed. In addition, imaging modalities such as fundus, slit-lamps, and OCT images require medical equipment that is expensive and not portable. Therefore, the use of digital images from a smartphone as the future of cataract screening tools could be a practical and helpful solution for ophthalmologists, especially in rural areas with limited healthcare facilities.

Implementing Machine Learning Algorithms to Classify Postures and Forecast Motions When Using a Dynamic Chair

Many modern jobs require long periods of sitting on a chair that may result in serious health complications. Dynamic chairs are proposed as alternatives to the traditional sitting chairs; however, previous studies have suggested that most users are not aware of their postures and do not take advantage of the increased range of motion offered by the dynamic chairs. Building a system that identifies users’ postures in real time, as well as forecasts the next few postures, can bring awareness to the sitting behavior of each user. In this study, machine learning algorithms have been implemented to automatically classify users’ postures and forecast their next motions. The random forest, gradient decision tree, and support vector machine algorithms were used to classify postures. The evaluation of the trained classifiers indicated that they could successfully identify users’ postures with an accuracy above 90%. The algorithm can provide users with an accurate report of their sitting habits. A 1D-convolutional-LSTM network has also been implemented to forecast users’ future postures based on their previous motions, the model can forecast a user’s motions with high accuracy (97%). The ability of the algorithm to forecast future postures could be used to suggest alternative postures as needed.

Appositeness of Optimized and Reliable Machine Learning for Healthcare: A Survey

Machine Learning (ML) has been categorized as a branch of Artificial Intelligence (AI) under the Computer Science domain wherein programmable machines imitate human learning behavior with the help of statistical methods and data. The Healthcare industry is one of the largest and busiest sectors in the world, functioning with an extensive amount of manual moderation at every stage. Most of the clinical documents concerning patient care are hand-written by experts, selective reports are machine-generated. This process elevates the chances of misdiagnosis thereby, imposing a risk to a patient's life. Recent technological adoptions for automating manual operations have witnessed extensive use of ML in its applications. The paper surveys the applicability of ML approaches in automating medical systems. The paper discusses most of the optimized statistical ML frameworks that encourage better service delivery in clinical aspects. The universal adoption of various Deep Learning (DL) and ML techniques as the underlying systems for a variety of wellness applications, is delineated by challenges and elevated by myriads of security. This work tries to recognize a variety of vulnerabilities occurring in medical procurement, admitting the concerns over its predictive performance from a privacy point of view. Finally providing possible risk delimiting facts and directions for active challenges in the future.

Does COVID-19 Clinical Status Associate with Outcome Severity? An Unsupervised Machine Learning Approach for Knowledge Extraction

Since the beginning of the COVID-19 pandemic, 195 million people have been infected and 4.2 million have died from the disease or its side effects. Physicians, healthcare scientists and medical staff continuously try to deal with overloaded hospital admissions, while in parallel, they try to identify meaningful correlations between the severity of infected patients with their symptoms, comorbidities and biomarkers. Artificial intelligence (AI) and machine learning (ML) have been used recently in many areas related to COVID-19 healthcare. The main goal is to manage effectively the wide variety of issues related to COVID-19 and its consequences. The existing applications of ML to COVID-19 healthcare are based on supervised classifications which require a labeled training dataset, serving as reference point for learning, as well as predefined classes. However, the existing knowledge about COVID-19 and its consequences is still not solid and the points of common agreement among different scientific communities are still unclear. Therefore, this study aimed to follow an unsupervised clustering approach, where prior knowledge is not required (tabula rasa). More specifically, 268 hospitalized patients at the First Propaedeutic Department of Internal Medicine of AHEPA University Hospital of Thessaloniki were assessed in terms of 40 clinical variables (numerical and categorical), leading to a high-dimensionality dataset. Dimensionality reduction was performed by applying a principal component analysis (PCA) on the numerical part of the dataset and a multiple correspondence analysis (MCA) on the categorical part of the dataset. Then, the Bayesian information criterion (BIC) was applied to Gaussian mixture models (GMM) in order to identify the optimal number of clusters under which the best grouping of patients occurs. The proposed methodology identified four clusters of patients with similar clinical characteristics. The analysis revealed a cluster of asymptomatic patients that resulted in death at a rate of 23.8%. This striking result forces us to reconsider the relationship between the severity of COVID-19 clinical symptoms and the patient's mortality.

Budget constrained machine learning for early prediction of adverse outcomes for COVID-19 patients

The combination of machine learning (ML) and electronic health records (EHR) data may be able to improve outcomes of hospitalized COVID-19 patients through improved risk stratification and patient outcome prediction. However, in resource constrained environments the clinical utility of such data-driven predictive tools may be limited by the cost or unavailability of certain laboratory tests. We leveraged EHR data to develop an ML-based tool for predicting adverse outcomes that optimizes clinical utility under a given cost structure. We further gained insights into the decision-making process of the ML models through an explainable AI tool. This cohort study was performed using deidentified EHR data from COVID-19 patients from ProMedica Health System in northwest Ohio and southeastern Michigan. We tested the performance of various ML approaches for predicting either increasing ventilatory support or mortality. We performed post hoc analysis to obtain optimal feature sets under various budget constraints. We demonstrate that it is possible to achieve a significant reduction in cost at the expense of a small reduction in predictive performance. For example, when predicting ventilation, it is possible to achieve a 43% reduction in cost with only a 3% reduction in performance. Similarly, when predicting mortality, it is possible to achieve a 50% reduction in cost with only a 1% reduction in performance. This study presents a quick, accurate, and cost-effective method to evaluate risk of deterioration for patients with SARS-CoV-2 infection at the time of clinical evaluation.

The potential and challenges of Health 4.0 to face COVID-19 pandemic: a rapid review

The COVID-19 pandemic has generated the need to evolve health services to reduce the risk of contagion and promote a collaborative environment even remotely. Advances in Industry 4.0, including the internet of things, mobile networks, cloud computing, and artificial intelligence make Health 4.0 possible to connect patients with healthcare professionals. Hence, the focus of this work is analyzing the potentiality, and challenges of state-of-the-art Health 4.0 applications to face the COVID-19 pandemic including augmented environments, diagnosis of the virus, forecasts, medical robotics, and remote clinical services. It is concluded that Health 4.0 can be applied in the prevention of contagion, improve diagnosis, promote virtual learning environments, and offer remote services. However, there are still ethical, technical, security, and legal challenges to be addressed. Additionally, more imaging datasets for COVID-19 detection need to be made available to the scientific community. Working in the areas of opportunity will help to address the new normal. Likewise, Health 4.0 can be applied not only in the COVID-19 pandemic, but also in future global viruses and natural disasters.

Key Technology Considerations in Developing and Deploying Machine Learning Models in Clinical Radiology Practice

The use of machine learning to develop intelligent software tools for the interpretation of radiology images has gained widespread attention in recent years. The development, deployment, and eventual adoption of these models in clinical practice, however, remains fraught with challenges. In this paper, we propose a list of key considerations that machine learning researchers must recognize and address to make their models accurate, robust, and usable in practice. We discuss insufficient training data, decentralized data sets, high cost of annotations, ambiguous ground truth, imbalance in class representation, asymmetric misclassification costs, relevant performance metrics, generalization of models to unseen data sets, model decay, adversarial attacks, explainability, fairness and bias, and clinical validation. We describe each consideration and identify the techniques used to address it. Although these techniques have been discussed in prior research, by freshly examining them in the context of medical imaging and compiling them in the form of a laundry list, we hope to make them more accessible to researchers, software developers, radiologists, and other stakeholders.

Machine learning as the new approach in understanding biomarkers of suicidal behavior

In psychiatry, compared to other medical fields, the identification of biological markers that would complement current clinical interview, and enable more objective and faster clinical diagnosis, implement accurate monitoring of treatment response and remission, is grave. Current technological development enables analyses of various biological marks in high throughput scale at reasonable costs, and therefore 'omic' studies are entering the psychiatry research. However, big data demands a whole new plethora of skills in data processing, before clinically useful information can be extracted. So far the classical approach to data analysis did not really contribute to identification of biomarkers in psychiatry, but the extensive amounts of data might get to a higher level, if artificial intelligence in the shape of machine learning algorithms would be applied. Not many studies on machine learning in psychiatry have been published, but we can already see from that handful of studies that the potential to build a screening portfolio of biomarkers for different psychopathologies, including suicide, exists.

Interpretability of Machine Learning Solutions in Public Healthcare: The CRISP-ML Approach

Public healthcare has a history of cautious adoption for artificial intelligence (AI) systems. The rapid growth of data collection and linking capabilities combined with the increasing diversity of the data-driven AI techniques, including machine learning (ML), has brought both ubiquitous opportunities for data analytics projects and increased demands for the regulation and accountability of the outcomes of these projects. As a result, the area of interpretability and explainability of ML is gaining significant research momentum. While there has been some progress in the development of ML methods, the methodological side has shown limited progress. This limits the practicality of using ML in the health domain: the issues with explaining the outcomes of ML algorithms to medical practitioners and policy makers in public health has been a recognized obstacle to the broader adoption of data science approaches in this domain. This study builds on the earlier work which introduced CRISP-ML, a methodology that determines the interpretability level required by stakeholders for a successful real-world solution and then helps in achieving it. CRISP-ML was built on the strengths of CRISP-DM, addressing the gaps in handling interpretability. Its application in the Public Healthcare sector follows its successful deployment in a number of recent real-world projects across several industries and fields, including credit risk, insurance, utilities, and sport. This study elaborates on the CRISP-ML methodology on the determination, measurement, and achievement of the necessary level of interpretability of ML solutions in the Public Healthcare sector. It demonstrates how CRISP-ML addressed the problems with data diversity, the unstructured nature of data, and relatively low linkage between diverse data sets in the healthcare domain. The characteristics of the case study, used in the study, are typical for healthcare data, and CRISP-ML managed to deliver on these issues, ensuring the required level of interpretability of the ML solutions discussed in the project. The approach used ensured that interpretability requirements were met, taking into account public healthcare specifics, regulatory requirements, project stakeholders, project objectives, and data characteristics. The study concludes with the three main directions for the development of the presented cross-industry standard process.

Novel artificial intelligence-driven software significantly shortens the time required for annotation in computer vision projects

Background and study aims The contribution of artificial intelligence (AI) to endoscopy is rapidly expanding. Accurate labelling of source data (video frames) remains the rate-limiting step for such projects and is a painstaking, cost-inefficient, time-consuming process. A novel software platform, Cord Vision (CdV) allows automated annotation based on “embedded intelligence.” The user manually labels a representative proportion of frames in a section of video (typically 5 %), to create ‘micro-modelsʼ which allow accurate propagation of the label throughout the remaining video frames. This could drastically reduce the time required for annotation.

Methods We conducted a comparative study with an open-source labelling platform (CVAT) to determine speed and accuracy of labelling.

Results Across 5 users, CdV resulted in a significant increase in labelling performance (P < 0.001) compared to CVAT for bounding box placement.

Conclusions This advance represents a valuable first step in AI-image analysis projects.

Securing Machine Learning in the Cloud: A Systematic Review of Cloud Machine Learning Security

With the advances in machine learning (ML) and deep learning (DL) techniques, and the potency of cloud computing in offering services efficiently and cost-effectively, Machine Learning as a Service (MLaaS) cloud platforms have become popular. In addition, there is increasing adoption of third-party cloud services for outsourcing training of DL models, which requires substantial costly computational resources (e.g., high-performance graphics processing units (GPUs)). Such widespread usage of cloud-hosted ML/DL services opens a wide range of attack surfaces for adversaries to exploit the ML/DL system to achieve malicious goals. In this article, we conduct a systematic evaluation of literature of cloud-hosted ML/DL models along both the important dimensions—attacks and defenses—related to their security. Our systematic review identified a total of 31 related articles out of which 19 focused on attack, six focused on defense, and six focused on both attack and defense. Our evaluation reveals that there is an increasing interest from the research community on the perspective of attacking and defending different attacks on Machine Learning as a Service platforms. In addition, we identify the limitations and pitfalls of the analyzed articles and highlight open research issues that require further investigation.