Autonomous Driving Architectures: Insights of Machine Learning and Deep Learning Algorithms

Mathematical Model-Driven Deep Learning Enables Personalized Adaptive Therapy

Standard-of-care treatment regimens have long been designed for maximal cell killing, yet these strategies often fail when applied to metastatic cancers due to the emergence of drug resistance. Adaptive treatment strategies have been developed as an alternative approach, dynamically adjusting treatment to suppress the growth of treatment-resistant populations and thereby delay, or even prevent, tumor progression. Promising clinical results in prostate cancer indicate the potential to optimize adaptive treatment protocols. Here, we applied deep reinforcement learning (DRL) to guide adaptive drug scheduling and demonstrated that these treatment schedules can outperform the current adaptive protocols in a mathematical model calibrated to prostate cancer dynamics, more than doubling the time to progression. The DRL strategies were robust to patient variability, including both tumor dynamics and clinical monitoring schedules. The DRL framework could produce interpretable, adaptive strategies based on a single tumor burden threshold, replicating and informing optimal treatment strategies. The DRL framework had no knowledge of the underlying mathematical tumor model, demonstrating the capability of DRL to help develop treatment strategies in novel or complex settings. Finally, a proposed five-step pathway, which combined mechanistic modeling with the DRL framework and integrated conventional tools to improve interpretability compared with traditional "black-box" DRL models, could allow translation of this approach to the clinic. Overall, the proposed framework generated personalized treatment schedules that consistently outperformed clinical standard-of-care protocols.

SIGNIFICANCE

Generation of interpretable and personalized adaptive treatment schedules using a deep reinforcement framework that interacts with a virtual patient model overcomes the limitations of standardized strategies caused by heterogeneous treatment responses.

Evaluating ChatGPT-4's Diagnostic Accuracy: Impact of Visual Data Integration

BACKGROUND

In the evolving field of health care, multimodal generative artificial intelligence (AI) systems, such as ChatGPT-4 with vision (ChatGPT-4V), represent a significant advancement, as they integrate visual data with text data. This integration has the potential to revolutionize clinical diagnostics by offering more comprehensive analysis capabilities. However, the impact on diagnostic accuracy of using image data to augment ChatGPT-4 remains unclear.

OBJECTIVE

This study aims to assess the impact of adding image data on ChatGPT-4's diagnostic accuracy and provide insights into how image data integration can enhance the accuracy of multimodal AI in medical diagnostics. Specifically, this study endeavored to compare the diagnostic accuracy between ChatGPT-4V, which processed both text and image data, and its counterpart, ChatGPT-4, which only uses text data.

METHODS

We identified a total of 557 case reports published in the American Journal of Case Reports from January 2022 to March 2023. After excluding cases that were nondiagnostic, pediatric, and lacking image data, we included 363 case descriptions with their final diagnoses and associated images. We compared the diagnostic accuracy of ChatGPT-4V and ChatGPT-4 without vision based on their ability to include the final diagnoses within differential diagnosis lists. Two independent physicians evaluated their accuracy, with a third resolving any discrepancies, ensuring a rigorous and objective analysis.

RESULTS

The integration of image data into ChatGPT-4V did not significantly enhance diagnostic accuracy, showing that final diagnoses were included in the top 10 differential diagnosis lists at a rate of 85.1% (n=309), comparable to the rate of 87.9% (n=319) for the text-only version (P=.33). Notably, ChatGPT-4V's performance in correctly identifying the top diagnosis was inferior, at 44.4% (n=161), compared with 55.9% (n=203) for the text-only version (P=.002, χ2 test). Additionally, ChatGPT-4's self-reports showed that image data accounted for 30% of the weight in developing the differential diagnosis lists in more than half of cases.

CONCLUSIONS

Our findings reveal that currently, ChatGPT-4V predominantly relies on textual data, limiting its ability to fully use the diagnostic potential of visual information. This study underscores the need for further development of multimodal generative AI systems to effectively integrate and use clinical image data. Enhancing the diagnostic performance of such AI systems through improved multimodal data integration could significantly benefit patient care by providing more accurate and comprehensive diagnostic insights. Future research should focus on overcoming these limitations, paving the way for the practical application of advanced AI in medicine.

Predicting Drug-Protein Interactions through Branch-Chain Mining and multi-dimensional attention network

Identifying drug-protein interactions (DPIs) is crucial in drug discovery and repurposing. Computational methods for precise DPI identification can expedite development timelines and reduce expenses compared with conventional experimental methods. Lately, deep learning techniques have been employed for predicting DPIs, enhancing these processes. Nevertheless, the limitations observed in prior studies, where many extract features from complete drug and protein entities, overlooking the crucial theoretical foundation that pharmacological responses are often correlated with specific substructures, can lead to poor predictive performance. Furthermore, certain substructure-focused research confines its exploration to a solitary fragment category, such as a functional group. In this study, addressing these constraints, we present an end-to-end framework termed BCMMDA for predicting DPIs. The framework considers various substructure types, including branch chains, common substructures, and specific fragments. We designed a specific feature learning module by combining our proposed multi-dimensional attention mechanism with convolutional neural networks (CNNs). Deep CNNs assist in capturing the synergistic effects among these fragment sets, enabling the extraction of relevant features of drugs and proteins. Meanwhile, the multi-dimensional attention mechanism refines the relationship between drug and protein features by assigning attention vectors to each drug compound and amino acid. This mechanism empowers the model to further concentrate on pivotal substructures and elements, thereby improving its ability to identify essential interactions in DPI prediction. We evaluated the performance of BCMMDA on four well-known benchmark datasets. The results indicated that BCMMDA outperformed state-of-the-art baseline models, demonstrating significant improvement in performance.

Machine learning for small interfering RNAs: a concise review of recent developments

The advent of machine learning and its subsequent integration into small interfering RNA (siRNA) research heralds a new epoch in the field of RNA interference (RNAi). This review emphasizes the urgency and relevance of assimilating the plethora of contributions and advancements in this domain, particularly focusing on the period of 2019-2023. Given the rapid progression of deep learning technologies, our synthesis of recent research is paramount to staying apprised of the state-of-the-art methods being utilized. It not only offers a comprehensive insight into the confluence of machine learning and siRNA but also serves as a beacon, guiding future explorations in this intersectional research field. Our rigorous examination of studies promises a discerning perspective on the contemporary landscape of machine learning applications in siRNA design and function. This review is an effort to foster further discourse and propel academic inquiry in this multifaceted domain.

Road User Position and Speed Estimation via Deep Learning from Calibrated Fisheye Videos

In this paper, we present a deep learning processing flow aimed at Advanced Driving Assistance Systems (ADASs) for urban road users. We use a fine analysis of the optical setup of a fisheye camera and present a detailed procedure to obtain Global Navigation Satellite System (GNSS) coordinates along with the speed of the moving objects. The camera to world transform incorporates the lens distortion function. YOLOv4, re-trained with ortho-photographic fisheye images, provides road user detection. All the information extracted from the image by our system represents a small payload and can easily be broadcast to the road users. The results show that our system is able to properly classify and localize the detected objects in real time, even in low-light-illumination conditions. For an effective observation area of 20 m × 50 m, the error of the localization is in the order of one meter. Although an estimation of the velocities of the detected objects is carried out by offline processing with the FlowNet2 algorithm, the accuracy is quite good, with an error below one meter per second for urban speed range (0 to 15 m/s). Moreover, the almost ortho-photographic configuration of the imaging system ensures that the anonymity of all street users is guaranteed.

A machine learning approach for predicting high risk hospitalized patients with COVID-19 SARS-Cov-2

BACKGROUND

This study aimed to explore whether explainable Artificial Intelligence methods can be fruitfully used to improve the medical management of patients suffering from complex diseases, and in particular to predict the death risk in hospitalized patients with SARS-Cov-2 based on admission data.

METHODS

This work is based on an observational ambispective study that comprised patients older than 18 years with a positive SARS-Cov-2 diagnosis that were admitted to the hospital Azienda Ospedaliera "SS Antonio e Biagio e Cesare Arrigo", Alessandria, Italy from February, 24 2020 to May, 31 2021, and that completed the disease treatment inside this structure. The patients'medical history, demographic, epidemiologic and clinical data were collected from the electronic medical records system and paper based medical records, entered and managed by the Clinical Study Coordinators using the REDCap electronic data capture tool patient chart. The dataset was used to train and to evaluate predictive ML models.

RESULTS

We overall trained, analysed and evaluated 19 predictive models (both supervised and unsupervised) on data from 824 patients described by 43 features. We focused our attention on models that provide an explanation that is understandable and directly usable by domain experts, and compared the results against other classical machine learning approaches. Among the former, JRIP showed the best performance in 10-fold cross validation, and the best average performance in a further validation test using a different patient dataset from the beginning of the third COVID-19 wave. Moreover, JRIP showed comparable performances with other approaches that do not provide a clear and/or understandable explanation.

CONCLUSIONS

The ML supervised models showed to correctly discern between low-risk and high-risk patients, even when the medical disease context is complex and the list of features is limited to information available at admission time. Furthermore, the models demonstrated to reasonably perform on a dataset from the third COVID-19 wave that was not used in the training phase. Overall, these results are remarkable: (i) from a medical point of view, these models evaluate good predictions despite the possible differences entitled with different care protocols and the possible influence of other viral variants (i.e. delta variant); (ii) from the organizational point of view, they could be used to optimize the management of health-care path at the admission time.

How Do Autonomous Vehicles Decide?

The advancement in sensor technologies, mobile network technologies, and artificial intelligence has pushed the boundaries of different verticals, e.g., eHealth and autonomous driving. Statistics show that more than one million people are killed in traffic accidents yearly, where the vast majority of the accidents are caused by human negligence. Higher-level autonomous driving has great potential to enhance road safety and traffic efficiency. One of the most crucial links to building an autonomous system is the task of decision-making. The ability of a vehicle to make robust decisions on its own by anticipating and evaluating future outcomes is what makes it intelligent. Planning and decision-making technology in autonomous driving becomes even more challenging, due to the diversity of the dynamic environments the vehicle operates in, the uncertainty in the sensor information, and the complex interaction with other road participants. A significant amount of research has been carried out toward deploying autonomous vehicles to solve plenty of issues, however, how to deal with the high-level decision-making in a complex, uncertain, and urban environment is a comparatively less explored area. This paper provides an analysis of decision-making solutions approaches for autonomous driving. Various categories of approaches are analyzed with a comparison to classical decision-making approaches. Following, a crucial range of research gaps and open challenges have been highlighted that need to be addressed before higher-level autonomous vehicles hit the roads. We believe this survey will contribute to the research of decision-making methods for autonomous vehicles in the future by equipping the researchers with an overview of decision-making technology, its potential solution approaches, and challenges.

A review on AI Safety in highly automated driving

Remarkable progress in the fields of machine learning (ML) and artificial intelligence (AI) has led to an increased number of applications of (data-driven) AI systems for the partial or complete control of safety-critical systems. Recently, ML solutions have been particularly popular. Such approaches are often met with concerns regarding their correct and safe execution, which is often caused by missing knowledge or intransparency of their exact functionality. The investigation and derivation of methods for the safety assessment of AI systems are thus of great importance. Among others, these issues are addressed in the field of AI Safety. The aim of this work is to provide an overview of this field by means of a systematic literature review with special focus on the area of highly automated driving, as well as to present a selection of approaches and methods for the safety assessment of AI systems. Particularly, validation, verification, and testing are considered in light of this context. In the review process, two distinguished classes of approaches have been identified: On the one hand established methods, either referring to already published standards or well-established concepts from multiple research areas outside ML and AI. On the other hand newly developed approaches, including methods tailored to the scope of ML and AI which gained importance only in recent years.

A Review on Autonomous Vehicles: Progress, Methods and Challenges

Vehicular technology has recently gained increasing popularity, and autonomous driving is a hot topic. To achieve safe and reliable intelligent transportation systems, accurate positioning technologies need to be built to factor in the different types of uncertainties such as pedestrian behavior, random objects, and types of roads and their settings. In this work, we look into the other domains and technologies required to build an autonomous vehicle and conduct a relevant literature analysis. In this work, we look into the current state of research and development in environment detection, pedestrian detection, path planning, motion control, and vehicle cybersecurity for autonomous vehicles. We aim to study the different proposed technologies and compare their approaches. For a car to become fully autonomous, these technologies need to be accurate enough to gain public trust and show immense accuracy in their approach to solving these problems. Public trust and perception of auto vehicles are also explored in this paper. By discussing the opportunities as well as the obstacles of autonomous driving technology, we aim to shed light on future possibilities.

Vulnerable Road Users and Connected Autonomous Vehicles Interaction: A Survey

There is a group of users within the vehicular traffic ecosystem known as Vulnerable Road Users (VRUs). VRUs include pedestrians, cyclists, motorcyclists, among others. On the other hand, connected autonomous vehicles (CAVs) are a set of technologies that combines, on the one hand, communication technologies to stay always ubiquitous connected, and on the other hand, automated technologies to assist or replace the human driver during the driving process. Autonomous vehicles are being visualized as a viable alternative to solve road accidents providing a general safe environment for all the users on the road specifically to the most vulnerable. One of the problems facing autonomous vehicles is to generate mechanisms that facilitate their integration not only within the mobility environment, but also into the road society in a safe and efficient way. In this paper, we analyze and discuss how this integration can take place, reviewing the work that has been developed in recent years in each of the stages of the vehicle-human interaction, analyzing the challenges of vulnerable users and proposing solutions that contribute to solving these challenges.

Exploration of Financial Market Credit Scoring and Risk Management and Prediction Using Deep Learning and Bionic Algorithm

The purpose is to effectively manage the financial market, comprehensive assess personal credit, reduce the risk of financial enterprises. Given the systemic risk problem caused by the lack of credit scoring in the existing financial market, a credit scoring model is put forward based on the deep learning network. The proposed model uses RNN (Recurrent Neural Network) and BRNN (Bidirectional Recurrent Neural Network) to avoid the limitations of shallow models. Afterward, to optimize path analysis, bionic optimization algorithms are introduced, and an integrated deep learning model is proposed. Finally, a financial credit risk management system using the integrated deep learning model is proposed. The probability of default or overdue customers is predicted through verification on three real credit data sets, thus realizing the credit risk management for credit customers.