Receive a weekly summary and discussion of the top papers of the week by leading researchers in the field.

General General

Applying frontier approach to measure the financial efficiency of hospitals.

In Digital health

OBJECTIVES : The growth in global healthcare capacity has led to increased healthcare costs and a deterioration in the finances of universal health insurance. Hospitals must consider how to improve financial efficiency and service quality in order to survive and operate sustainably.

METHODS : This study applies data envelopment analysis (DEA) and stochastic frontier analysis (SFA) to measure the financial efficiency of hospitals and to identify the factors and business strategies to improve profitability.

RESULTS : The findings and recommendations show that (1) the DEA and SFA methods are similar and have reference values; (2) financial efficiency should be improved by reducing medical costs; (3) the quality of medical staff should be improved and manpower reduced; and (4) information, computerisation, and human intelligence in healthcare and management should be enhanced.

CONCLUSIONS : In terms of practical applications, this study recommends the promotion of smart healthcare to improve the efficiency and quality of healthcare services, as well as the introduction of artificial intelligence and big data analysis to optimise the use of healthcare manpower. Electronic medical records can be used to reduce the wastage of resources and labour costs, a medication management system can be established, and changes to the procurement system can be made to reduce inventory and improve the efficiency of medical equipment use. It is hoped that this study will provide reference materials and applications for healthcare organisations to improve their operational efficiency and strategies.

Wu Jih-Shong

2023

Financial efficiency, data envelopment analysis, health care, hospital, stochastic frontier analysis

General General

Trainable quantization for Speedy Spiking Neural Networks.

In Frontiers in neuroscience ; h5-index 72.0

Spiking neural networks are considered as the third generation of Artificial Neural Networks. SNNs perform computation using neurons and synapses that communicate using binary and asynchronous signals known as spikes. They have attracted significant research interest over the last years since their computing paradigm allows theoretically sparse and low-power operations. This hypothetical gain, used from the beginning of the neuromorphic research, was however limited by three main factors: the absence of an efficient learning rule competing with the one of classical deep learning, the lack of mature learning framework, and an important data processing latency finally generating energy overhead. While the first two limitations have recently been addressed in the literature, the major problem of latency is not solved yet. Indeed, information is not exchanged instantaneously between spiking neurons but gradually builds up over time as spikes are generated and propagated through the network. This paper focuses on quantization error, one of the main consequence of the SNN discrete representation of information. We argue that the quantization error is the main source of accuracy drop between ANN and SNN. In this article we propose an in-depth characterization of SNN quantization noise. We then propose a end-to-end direct learning approach based on a new trainable spiking neural model. This model allows adapting the threshold of neurons during training and implements efficient quantization strategies. This novel approach better explains the global behavior of SNNs and minimizes the quantization noise during training. The resulting SNN can be trained over a limited amount of timesteps, reducing latency, while beating state of the art accuracy and preserving high sparsity on the main datasets considered in the neuromorphic community.

Castagnetti Andrea, Pegatoquet Alain, Miramond Benoît

2023

Spiking Neural Networks, direct training, low latency, quantization error, sparsity

Public Health Public Health

Abnormal structural and functional network topological properties associated with left prefrontal, parietal, and occipital cortices significantly predict childhood TBI-related attention deficits: A semi-supervised deep learning study.

In Frontiers in neuroscience ; h5-index 72.0

INTRODUCTION : Traumatic brain injury (TBI) is a major public health concern in children. Children with TBI have elevated risk in developing attention deficits. Existing studies have found that structural and functional alterations in multiple brain regions were linked to TBI-related attention deficits in children. Most of these existing studies have utilized conventional parametric models for group comparisons, which have limited capacity in dealing with large-scale and high dimensional neuroimaging measures that have unknown nonlinear relationships. Nevertheless, none of these existing findings have been successfully implemented to clinical practice for guiding diagnoses and interventions of TBI-related attention problems. Machine learning techniques, especially deep learning techniques, are able to handle the multi-dimensional and nonlinear information to generate more robust predictions. Therefore, the current research proposed to construct a deep learning model, semi-supervised autoencoder, to investigate the topological alterations in both structural and functional brain networks in children with TBI and their predictive power for post-TBI attention deficits.

METHODS : Functional magnetic resonance imaging data during sustained attention processing task and diffusion tensor imaging data from 110 subjects (55 children with TBI and 55 group-matched controls) were used to construct the functional and structural brain networks, respectively. A total of 60 topological properties were selected as brain features for building the model.

RESULTS : The model was able to differentiate children with TBI and controls with an average accuracy of 82.86%. Functional and structural nodal topological properties associated with left frontal, inferior temporal, postcentral, and medial occipitotemporal regions served as the most important brain features for accurate classification of the two subject groups. Post hoc regression-based machine learning analyses in the whole study sample showed that among these most important neuroimaging features, those associated with left postcentral area, superior frontal region, and medial occipitotemporal regions had significant value for predicting the elevated inattentive and hyperactive/impulsive symptoms.

DISCUSSION : Findings of this study suggested that deep learning techniques may have the potential to help identifying robust neurobiological markers for post-TBI attention deficits; and the left superior frontal, postcentral, and medial occipitotemporal regions may serve as reliable targets for diagnosis and interventions of TBI-related attention problems in children.

Cao Meng, Wu Kai, Halperin Jeffery M, Li Xiaobo

2023

attention deficits, autoencoder, diffusion tensor imaging, functional magnetic resonance imaging, graph theory, pediatric, semi-supervised deep learning technique, traumatic brain injury

General General

An artificial intelligence lightweight blockchain security model for security and privacy in IIoT systems.

In Journal of cloud computing (Heidelberg, Germany)

The Industrial Internet of Things (IIoT) promises to deliver innovative business models across multiple domains by providing ubiquitous connectivity, intelligent data, predictive analytics, and decision-making systems for improved market performance. However, traditional IIoT architectures are highly susceptible to many security vulnerabilities and network intrusions, which bring challenges such as lack of privacy, integrity, trust, and centralization. This research aims to implement an Artificial Intelligence-based Lightweight Blockchain Security Model (AILBSM) to ensure privacy and security of IIoT systems. This novel model is meant to address issues that can occur with security and privacy when dealing with Cloud-based IIoT systems that handle data in the Cloud or on the Edge of Networks (on-device). The novel contribution of this paper is that it combines the advantages of both lightweight blockchain and Convivial Optimized Sprinter Neural Network (COSNN) based AI mechanisms with simplified and improved security operations. Here, the significant impact of attacks is reduced by transforming features into encoded data using an Authentic Intrinsic Analysis (AIA) model. Extensive experiments are conducted to validate this system using various attack datasets. In addition, the results of privacy protection and AI mechanisms are evaluated separately and compared using various indicators. By using the proposed AILBSM framework, the execution time is minimized to 0.6 seconds, the overall classification accuracy is improved to 99.8%, and detection performance is increased to 99.7%. Due to the inclusion of auto-encoder based transformation and blockchain authentication, the anomaly detection performance of the proposed model is highly improved, when compared to other techniques.

Selvarajan Shitharth, Srivastava Gautam, Khadidos Alaa O, Khadidos Adil O, Baza Mohamed, Alshehri Ali, Lin Jerry Chun-Wei

2023

Artificial intelligence, Blockchain, Cloud computing, Convivial Optimized Sprinter Neural Network, Fog computing, Security

General General

Brain inspired path planning algorithms for drones.

In Frontiers in neurorobotics

INTRODUCTION : With the development of artificial intelligence and brain science, brain-inspired navigation and path planning has attracted widespread attention.

METHODS : In this paper, we present a place cell based path planning algorithm that utilizes spiking neural network (SNN) to create efficient routes for drones. First, place cells are characterized by the leaky integrate-and-fire (LIF) neuron model. Then, the connection weights between neurons are trained by spike-timing-dependent plasticity (STDP) learning rules. Afterwards, a synaptic vector field is created to avoid obstacles and to find the shortest path.

RESULTS : Finally, simulation experiments both in a Python simulation environment and in an Unreal Engine environment are conducted to evaluate the validity of the algorithms.

DISCUSSION : Experiment results demonstrate the validity, its robustness and the computational speed of the proposed model.

Chao Yixun, Augenstein Philipp, Roennau Arne, Dillmann Ruediger, Xiong Zhi

2023

Airsim, navigation, path planning, place cells, spiking neural network

oncology Oncology

Discovering cryptic splice mutations in cancers via a deep neural network framework.

In NAR cancer

Somatic mutations can disrupt splicing regulatory elements and have dramatic effects on cancer genes, yet the functional consequences of mutations located in extended splice regions is difficult to predict. Here, we use a deep neural network (SpliceAI) to characterize the landscape of splice-altering mutations in cancer. In our in-house series of 401 liver cancers, SpliceAI uncovers 1244 cryptic splice mutations, located outside essential splice sites, that validate at a high rate (66%) in matched RNA-seq data. We then extend the analysis to a large pan-cancer cohort of 17 714 tumors, revealing >100 000 cryptic splice mutations. Taking into account these mutations increases the power of driver gene discovery, revealing 126 new candidate driver genes. It also reveals new driver mutations in known cancer genes, doubling the frequency of splice alterations in tumor suppressor genes. Mutational signature analysis suggests mutational processes that could give rise preferentially to splice mutations in each cancer type, with an enrichment of signatures related to clock-like processes and DNA repair deficiency. Altogether, this work sheds light on the causes and impact of cryptic splice mutations in cancer, and highlights the power of deep learning approaches to better annotate the functional consequences of mutations in oncology.

Teboul Raphaël, Grabias Michalina, Zucman-Rossi Jessica, Letouzé Eric

2023-Jun