Informatics in Medicine Unlocked最新文献

This article explores the transformative impact of Artificial Intelligence (AI) in oncology pharmacy. Oncology pharmacists, traditionally pivotal to cancer management, are now navigating a landscape revolutionized by AI advancements, including machine learning and predictive analytics. Their role has expanded beyond conventional boundaries to encompass data-driven decision-making, AI-guided clinical support, and comprehensive patient counseling on AI-based treatment protocols. This evolution necessitates an augmented skill set encompassing technological proficiency, data interpretation, and ethical considerations in patient care. Despite the promise of AI in personalizing treatment and enhancing patient outcomes, challenges persist, including data privacy concerns, integration complexities, and ethical quandaries. Oncology pharmacy is transitioning to a more patient-focused practice, driven by continuous innovation and adaptation to AI technologies. This shift underscores the critical role of oncology pharmacists in shaping an AI-integrated future in healthcare, pivotal for advancing cancer treatment and improving patient care.

Early detection of diabetic retinopathy (DR) is critical in preventing vision loss. However, building accurate Artificial intelligence (AI) models for multiple classes, including early-stage (Class-1) detection, is challenging due to limited and imbalanced medical datasets. The availability of such datasets is restricted due to ethical and privacy concerns. Traditional ensemble models also struggle with raw medical images, further complicating the issue as they require structured data. This study presents a novel deep learning-based ensemble model (EM) designed for multiple and specifically for precise early stage (Class 1) DR classification. The EM uses eight diverse Convolutional Neural Networks (CNNs) with carefully crafted strategies to enhance diversity. Data augmentation and generation techniques address imbalanced data through data diversity, while parameter and architectural diver-sity within CNNs-based EM maximize predictive performance. Evaluation on the publicly available Kaggle APTOS DR dataset demonstrates significant improvement over individual models and existing approaches. The proposed EM achieves multi-class accuracy (93.00 %), precision (93.00 %), sensitivity (98.00 %), and specificity (99.00 %). This research highlights the effectiveness of diversified CNNs ensembles in overcoming challenges posed by imbalanced and scarce data for multiple-class DR classification. This approach paves the way for developing robust and accurate AI-powered diagnostic tools for improved diabetic retinopathy screening.

Background:

Human user authentication can be implemented by token-, keyword-, or identity-based mechanisms for digital environment session entry (i.e., smartphones, platforms with log-in). Physiological signals, such as ECG, have shown discriminative properties for user identity recognition. Due to ECG hidden nature, it is resilient to public trait exposition, light/noise saturation, or eavesdropping in contrast to fingerprint, facial, voice, or password approaches. ECG might fill those gaps toward a cooperative authentication environment.

Methods:

This paper proposes a Deep Learning identification scenario in which the inclusion of sex recognition directs the input sample toward a sex-specialized identity classification model, simplifying the discrimination space for each model. The architecture proposed could be suitable for large populations. Our scheme worked with an ECG three-axis pseudo-orthogonal configuration in which each axis is transformed into a time-frequency space. Additionally, we combine each lead matrix in an RGB image, joining the contribution of each wavelet waveform.

Results:

Our results suggest that it is possible to identify people by using RGB wavelet representations, achieving a classification average of 99.97%. In addition, the inclusion of the sex category for our identification purpose does not significantly affect the classification performance, making it a feasible solution for systems with a larger population.

Conclusions:

With the features of our database, we have evidence that it is possible to recognize a person’s identity using an ECG sex recognition module through our proposed architecture.

Deep learning plays a crucial role in medical imaging analysis, particularly in tasks such as image classification and segmentation. However, learning from medical imaging datasets presents challenges, including scarcity of labeled examples, class imbalances, and inadequate representation of diverse patient populations. To address these challenges, there has been a growing interest in the use of deep generative models to create synthetic training data, with denoising diffusion probabilistic models (DDPMs) recently gaining attention for their ability to produce realistic and high-quality images. This study explores the potential of a DDPM to generate synthetic chest X-rays for multi-label classifier training. The results indicate that the use of a conditional DDPM has the potential to produce a realistic training set of synthetic chest X-rays. In addition, the study analyzes the impact on classification performance of addressing class imbalance. Balancing the synthetic training set increased the overall classification sensitivity from 0.02 to 0.59, but decreased the overall specificity from 0.99 to 0.71. Furthermore, we investigated the potential of unconditional pre-training to learn general representations, followed by conditional fine-tuning of the DDPM. The results indicate that this approach allows the amount of labeled training data to be reduced to 25% of the original set. Finally, we demonstrate that fidelity and classification metrics do not consistently exhibit the same trends. Integrating a DDPM into the classification pipeline underscores the benefits of having optimal control over the data and efficient use of available unlabeled data. Our research provides insights for making informed decisions about integrating generative models into medical image analysis.

Wireless capsule endoscopy (WCE) has emerged as a valuable non-invasive technique for visualizing the entire gastrointestinal (GI) tract. However, manual evaluation of WCE videos is a time-consuming and costly process. In this study, we present a novel diagnostic assistant system that employs deep convolutional neural networks (DCNNs) to accelerate the evaluation process. Our primary objective is to achieve a high negative predictive value (NPV), which is essential for the efficient identification of normal frames. Six distinct DCNN models were developed and implemented with this objective in mind. The models were trained on a limited dataset encompassing common GI pathologies that reflect real clinical scenarios. Each DCNN architecture comprises a convolutional part derived from renowned pre-trained networks and a custom-designed classifier block optimized for high NPV and classification accuracy. Following a comprehensive assessment utilizing the 5-fold cross-validation approach, the VG_BFCG model was identified as the most effective, exhibiting an average test accuracy of 0.946 and an NPV of 0.983. Moreover, in the event of encountering novel pathologies not present in the training data, our models exhibited robustness in NPV, which is of great importance for practical applications. For example, the DN_BFCG model demonstrated consistent performance, with an NPV exceeding 0.99 across a range of new pathologies. This validates the reliability of our models in clinical settings. Our findings suggest that our developed DCNN architectures have the potential to enhance the efficiency and accuracy of WCE video analysis, which could transform the landscape of gastroenterological diagnostics.

Measles infection is a significant global public health concern, with one patient able to infect 12–18 people in a susceptible population. Mathematical modeling helps understand the factors influencing measles outbreaks, including vaccination levels, population density and movement patterns of the people who comprise it. Agent-based modeling, particularly useful in organized populations like hospitals or academic buildings, can predict the dynamics of infectious disease outbreaks. The aim of this work is to create an agent-based model of measles infection, which would predict the effectiveness of various anti-epidemic measures in small-group settings such as academic buildings. In this article, the effects of vaccination and isolation on the measles epidemic process were studied. The modeling found that combinations of vaccination and isolation measures are most effective, and these anti-epidemic measures allow to reduce the number of susceptible people that were infected from 199/199 (100 %) in the absence of measures to 73–80/199 (36.7–40.2 %).

Background

Objectives

Methods

Results

Conclusion

Breast cancer is a prevalent disease that has a potential influence on the lives of countless women globally. Early diagnosis and intervention are crucial for successful treatment and better patient outcomes. Machine learning algorithms have shown promising results in developing accurate and dependable prediction models for breast cancer. In this research, we conduct an extensive overview of various machine learning (ML) techniques employed to develop breast cancer prediction models using diverse datasets. Our study explores the literature on several ML algorithms utilized for breast cancer prediction. We also examine the types of datasets used for training and testing these models, including clinical data, mammography images, and genetic data. Additionally, we evaluate the benefits and limitations of each machine learning algorithm and dataset and offer recommendations for future research. Our aim is to provide a comprehensive understanding of the current state-of-the-art in breast cancer prediction models using ML and to promote the development of precise and effective models to detect breast cancer at an early stage.

Alzheimer's disease (AD) is a progressive neurological disease considered the most common form of late-stage dementia. Usually, AD leads to a reduction in brain volume, impacting various functions. This article comprehensively analyzes the AD context in fivefold main topics. Firstly, it reviews the main imaging techniques used in diagnosing AD disease. Secondly, it explores the most proposed deep learning (DL) algorithms for detecting the disease. Thirdly, the article investigates the commonly used datasets to develop DL techniques. Fourthly, we conducted a systematic review and selected 45 papers published in highly ranked publishers (Science Direct, IEEE, Springer, and MDPI). We analyzed them thoroughly by delving into the stages of AD diagnosis and emphasizing the role of preprocessing techniques. Lastly, the paper addresses the remaining practical implications and challenges in the AD context. Building on the analysis, this survey contributes to covering several aspects related to AD disease that have not been studied thoroughly.

Background

Investigating the causes and impact of essential medicines and supplies shortages in the supply chain of the MOH in Saudi Arabia could be the initial step in setting innovative strategies for mitigating this issue. This study aimed to identify the key factors contributing to essential medicines and supplies shortages in the supply chain of the MOH in Saudi Arabia and assess their impact on healthcare delivery.

Methods

A structured questionnaire was designed to collect relevant data on the causes and impact of essential medicines and supplies shortages. A representative sample of healthcare professionals, from various healthcare MOH facilities in Saudi Arabia. The Statistical Package for the Social Sciences (SPSS) software version 26 was used for the data analysis.

Results

A total of 379 respondents participated in the study, 73.7% were males, 51.2% were aged 36–45 years, 23.5% were supply chain professionals, and 32.9% reported an experience of >15 years. 90.0% of the participants reported that they personally have experienced shortages of essential medicines and supplies in the MOH supply chain in KSA. Inadequate planning, forecasting, and procurement were identified as the most significant contributing factors for shortages by about half (48.5%). At least two-thirds of the participants agreed with all strategies adopted for mitigating the issue of shortages.

Conclusions

The impact of shortages on patients and healthcare professionals was found to be substantial. The study also identified several key strategies to reduce shortages that received strong support from the participants.