BioMedInformatics, Volume 4, Issue 3 (September 2024) – 11 articles

When women receive a diagnosis of a gynecologic malignancy, they can have questions about their diagnosis or treatment that can result in voice queries to virtual assistants for more information. Recent advancement in artificial intelligence (AI) has transformed the landscape of medical information accessibility. The Google virtual assistant (VA) outperformed Siri, Alexa and Cortana in voice queries presented prior to the explosive implementation of AI in early 2023. The efforts presented here focus on determining if advances in AI in the last 12 months have improved the accuracy of Google VA responses related to gynecologic oncology. Previous questions were utilized to form a common basis for queries prior to 2023 and responses in 2024. Correct answers were obtained from the UpToDate medical resource. Responses related to gynecologic oncology were obtained using Google VA, as well as the generative AI chatbots Google Bard/Gemini and Microsoft Bing-Copilot. The AI narrative responses varied in length and positioning of answers within the response. Google Bard/Gemini achieved an 87.5% accuracy rate, while Microsoft Bing-Copilot reached 83.3%. In contrast, the Google VA’s accuracy in audible responses improved from 18% prior to 2023 to 63% in 2024. While the accuracy of the Google VA has improved in the last year, it underperformed Google Bard/Gemini and Microsoft Bing-Copilot so there is considerable room for further improved accuracy. Full article

In this scoping review, we delve into the transformative potential of artificial intelligence (AI) in addressing challenges inherent in whole-genome sequencing (WGS) analysis, with a specific focus on its implications in oncology. Unveiling the limitations of existing sequencing technologies, the review illuminates how AI-powered methods emerge as innovative solutions to surmount these obstacles. The evolution of DNA sequencing technologies, progressing from Sanger sequencing to next-generation sequencing, sets the backdrop for AI’s emergence as a potent ally in processing and analyzing the voluminous genomic data generated. Particularly, deep learning methods play a pivotal role in extracting knowledge and discerning patterns from the vast landscape of genomic information. In the context of oncology, AI-powered methods exhibit considerable potential across diverse facets of WGS analysis, including variant calling, structural variation identification, and pharmacogenomic analysis. This review underscores the significance of multimodal approaches in diagnoses and therapies, highlighting the importance of ongoing research and development in AI-powered WGS techniques. Integrating AI into the analytical framework empowers scientists and clinicians to unravel the intricate interplay of genomics within the realm of multi-omics research, paving the way for more successful personalized and targeted treatments. Full article

Background: Intracranial neoplasm, often referred to as a brain tumor, is an abnormal growth or mass of tissues in the brain. The complexity of the brain and the associated diagnostic delays cause significant stress for patients. This study aims to enhance the efficiency of MRI analysis for brain tumors using deep transfer learning. Methods: We developed and evaluated the performance of five pre-trained deep learning models—ResNet50, Xception, EfficientNetV2-S, ResNet152V2, and VGG16—using a publicly available MRI scan dataset to classify images as glioma, meningioma, pituitary, or no tumor. Various classification metrics were used for evaluation. Results: Our findings indicate that these models can improve the accuracy of MRI analysis for brain tumor classification, with the Xception model achieving the highest performance with a test F1 score of 0.9817, followed by EfficientNetV2-S with a test F1 score of 0.9629. Conclusions: Implementing pre-trained deep learning models can enhance MRI accuracy for detecting brain tumors. Full article

Background: Malignant breast cancer is the most common cancer affecting women worldwide. The COVID-19 pandemic appears to have slowed the diagnostic process, leading to an enhanced use of invasive approaches such as mastectomy. The increased use of a surgical procedure pushes towards an objective analysis of patient flow with measurable quality indicators such as length of stay (LOS) in order to optimize it. Methods: In this work, different regression and classification models were implemented to analyze the total LOS as a function of a set of independent variables (age, gender, pre-op LOS, discharge ward, year of discharge, type of procedure, presence of hypertension, diabetes, cardiovascular disease, respiratory disease, secondary tumors, and surgery with complications) extracted from the discharge records of patients undergoing mastectomy at the ‘San Giovanni di Dio e Ruggi d’Aragona’ University Hospital of Salerno (Italy) in the years 2011–2021. In addition, the impact of COVID-19 was assessed by statistically comparing data from patients discharged in 2018–2019 with those discharged in 2020–2021. Results: The results obtained generally show the good performance of the regression models in characterizing the particular case studies. Among the models, the best at predicting the LOS from the set of variables described above was polynomial regression, with an R² value above 0.689. The classification algorithms that operated on a LOS divided into 3 arbitrary classes also proved to be good tools, reaching 79% accuracy with the voting classifier. Among the independent variables, both implemented models showed that the ward of discharge, year of discharge, type of procedure and complications during surgery had the greatest impact on LOS. The final focus to assess the impact of COVID-19 showed a statically significant increase in surgical complications. Conclusion: Through this study, it was possible to validate the use of regression and classification models to characterize the total LOS of mastectomy patients. LOS proves to be an excellent indicator of performance, and through its analysis with advanced methods, such as machine learning algorithms, it is possible to understand which of the demographic and organizational variables collected have a significant impact and thus build simple predictors to support healthcare management. Full article

Background: Amyotrophic Lateral Sclerosis (ALS) is a devastating neurological disorder with increasing prevalence rates. Currently, only 8 FDA-approved drugs and 44 clinical trials exist for ALS treatment specifying the lacuna in disease-specific treatment. Drug repurposing, an alternative approach, is gaining huge importance. This study aims to identify potential repurposable compounds using gene expression analysis and structural similarity approaches. Methods: GSE833 and GSE3307 were analysed to retrieve Differentially Expressed Genes (DEGs) which were utilized to identify compounds reversing the gene signatures from LINCS. SMILES of ALS-specific FDA-approved and clinical trial compounds were used to retrieve structurally similar drugs from DrugBank. Drug-Target-Network (DTN) was constructed for the identified compounds to retrieve drug targets which were further subjected to functional enrichment analysis. Results: GSE833 retrieved 13 & 5 whereas GSE3307 retrieved 280 & 430 significant upregulated and downregulated DEGs respectively. Gene expression similarity identified 213 approved drugs. Structural similarity analysis of 44 compounds resulted in 411 approved and investigational compounds. DTN was constructed for 266 compounds to identify drug targets. Functional enrichment analysis resulted in neuroinflammatory response, cAMP signaling, PI3K-AKT signaling, and oxidative stress pathways. A preliminary relevancy check identified previous association of 105 compounds in ALS research, validating the approach, with 172 potential repurposable compounds. Full article

(1) Background: As Kaplan–Meier (KM) analysis is limited to single unidirectional endpoints, most advanced cancer randomized clinical trials (RCTs) are powered for either progression-free survival (PFS) or overall survival (OS). This discards efficacy information carried by partial responses, complete responses, and stable disease that frequently precede progressive disease and death. Chauhan Weighted Trajectory Analysis (CWTA) is a generalization of KM that simultaneously assesses multiple rank-ordered endpoints. We hypothesized that CWTA could use this efficacy information to reduce sample size requirements and expedite efficacy signals in advanced cancer trials. (2) Methods: We performed 100-fold and 1000-fold simulations of solid tumor systemic therapy RCTs with health statuses rank-ordered from complete response (Stage 0) to death (Stage 4). At increments of the sample size and hazard ratio, we compared KM PFS and OS with CWTA for (i) sample size requirements to achieve a power of 0.8 and (ii) the time to first significant efficacy signal. (3) Results: CWTA consistently demonstrated greater power, and it reduced the sample size requirements by 18% to 35% compared to KM PFS and 14% to 20% compared to KM OS. CWTA also expedited time-to-efficacy signals by 2- to 6-fold. (4) Conclusions: CWTA, by incorporating all efficacy signals in the cancer treatment trajectory, provides a clinically relevant reduction in the required sample size and meaningfully expedites the efficacy signals of cancer treatments compared to KM PFS and KM OS. Using CWTA rather than KM as the primary trial outcome has the potential to meaningfully reduce the numbers of patients, trial duration, and costs to evaluate therapies in advanced cancer. Full article

Background: Ischemic stroke poses significant challenges in diagnosis and treatment, necessitating efficient and accurate methods for assessing collateral circulation, a critical determinant of patient prognosis. Manual classification of collateral circulation in ischemic stroke using traditional imaging techniques is labor-intensive and prone to subjectivity. This study presented the automated classification of collateral circulation patterns in cone-beam CT (CBCT) images, utilizing the VGG11 architecture. Methods: The study utilized a dataset of CBCT images from ischemic stroke patients, accurately labeled with their respective collateral circulation status. To ensure uniformity and comparability, image normalization was executed during the preprocessing phase to standardize pixel values to a consistent scale or range. Then, the VGG11 model is trained using an augmented dataset and classifies collateral circulation patterns. Results: Performance evaluation of the proposed approach demonstrates promising results, with the model achieving an accuracy of 58.32%, a sensitivity of 75.50%, a specificity of 44.10%, a precision of 52.70%, and an F1 score of 62.10% in classifying collateral circulation patterns. Conclusions: This approach automates classification, potentially reducing diagnostic delays and improving patient outcomes. It also lays the groundwork for future research in using deep learning for better stroke diagnosis and management. This study is a significant advancement toward developing practical tools to assist doctors in making informed decisions for ischemic stroke patients. Full article

Background: Biomedical data are usually collections of longitudinal data assessed at certain points in time. Clinical observations assess the presences and severity of symptoms, which are the basis for the description and modeling of disease progression. Deciphering potential underlying unknowns from the distinct observation would substantially improve the understanding of pathological cascades. Hidden Markov Models (HMMs) have been successfully applied to the processing of possibly noisy continuous signals. We apply ensembles of HMMs to categorically distributed multivariate time series data, leaving space for expert domain knowledge in the prediction process. Methods: We use an ensemble of HMMs to predict the loss of free walking ability as one major clinical deterioration in the most common autosomal dominantly inherited ataxia disorder worldwide. Results: We present a prediction pipeline that processes data paired with a configuration file, enabling us to train, validate and query an ensemble of HMMs. In particular, we provide a theoretical and practical framework for multivariate time-series inference based on HMMs that includes constructing multiple HMMs, each to predict a particular observable variable. Our analysis is conducted on pseudo-data, but also on biomedical data based on Spinocerebellar ataxia type 3 disease. Conclusions: We find that the model shows promising results for the data we tested. The strength of this approach is that HMMs are well understood, probabilistic and interpretable models, setting it apart from most Deep Learning approaches. We publish all code and evaluation pseudo-data in an open-source repository. Full article

Background: Several studies have investigated various features and models in order to understand the growth and progression of the ocular disease geographic atrophy (GA). Commonly assessed features include age, sex, smoking, alcohol consumption, sedentary lifestyle, hypertension, and diabetes. There have been inconsistencies regarding which features correlate with GA progression. Chief amongst these inconsistencies is whether the investigated features are readily available for analysis across various ophthalmic institutions. Methods:In this study, we focused our attention on the association of fundus autofluorescence (FAF) imaging features and GA progression. Our method included feature extraction using radiomic processes and feature ranking by machine learning incorporating the algorithm XGBoost to determine the best-ranked features. This led to the development of an image-based linear mixed-effects model, which was designed to account for slope change based on within-subject variability and inter-eye correlation. Metrics used to assess the linear mixed-effects model included marginal and conditional $R^2$, Pearson’s correlation coefficient ($r$), root mean square error (RMSE), mean error (ME), mean absolute error (MAE), mean absolute deviation (MAD), the Akaike Information Criterion (AIC), the Bayesian Information Criterion (BIC), and loglikelihood. Results: We developed a linear mixed-effects model with 15 image-based features. The model results were as follows: $R^2$ = 0.96, $r$ = 0.981, RMSE = 1.32, ME = −7.3 × 10⁻¹⁵, MAE = 0.94, MAD = 0.999, AIC = 2084.93, BIC = 2169.97, and log likelihood = −1022.46. Conclusions: The advantage of our method is that it relies on the inherent properties of the image itself, rather than the availability of clinical or demographic data. Thus, the image features discovered in this study are universally and readily available across the board. Full article

Background/Objectives: Hepatitis E virus (HEV) is an RNA virus recognized to be spread mainly by fecal-contaminated water. Its infection is known to be a serious threat to public health globally, mostly in developing countries, in which Africa is one of the regions sternly affected. An African-based vaccine is necessary to actively prevent HEV infection. Methods: This study developed an in silico epitope-based subunit vaccine, incorporating CTL, HTL, and BL epitopes with suitable linkers and adjuvants. Results: The in silico-designed vaccine construct proved immunogenic, non-allergenic, and non-toxic and displayed appropriate physicochemical properties with high solubility. The 3D structure was modeled and subjected to protein docking with Toll-like receptors 2, 3, 4, 6, 8, and 9, which showed a stable binding efficacy, and the dynamics simulation indicated steady interaction. Furthermore, the immune simulation predicted that the designed vaccine would instigate immune responses when administered to humans. Lastly, using a codon adaptation for the E. coli K12 bacterium produced optimum GC content and a high CAI value, which was followed by in silico integration into a pET28 b (+) cloning vector. Conclusions: Generally, these results propose that the design of an epitope-based subunit vaccine can function as an outstanding preventive vaccine candidate against HEV, although validation techniques via in vitro and in vivo approaches are required to justify this statement. Full article

Background: Cognitive loss is one of the biggest health problems for older people. The incidence of dementia increases with age, so Alzheimer’s disease (AD), the most prevalent type of dementia, is expected to increase. Patients with dementia find it difficult to cope with their daily activities and resort to family members or caregivers. However, aging generally leads to a loss of orientation and navigation skills. This phenomenon creates great inconvenience for autonomous walking, especially in individuals with Mild Cognitive Impairment (MCI) or those suffering from Alzheimer’s disease. The loss of orientation and navigation skills is most felt when old people move from their usual environments to nursing homes or residential facilities. This necessarily involves a person’s constant presence to prevent the patient from moving without a defined destination or incurring dangerous situations. Methods: A navigation system is a support to allow older patients to move without resorting to their caregivers. This application meets the need for helping older people to move without incurring dangers. The aim of the study was to verify the possibility of applying the technology normally used for video games for the development of an indoor navigation system. There is no evidence of this in the literature. Results: We have developed an easy-to-use solution that can be extended to patients with MCI, easing the workload of caregivers and improving patient safety. The method applied was the use of the Unity Vuforia platform, with which an augmented reality APK application was produced on a smartphone. Conclusions: The model differs from traditional techniques because it does not use arrows or labels to identify the desired destination. The solution was tested in the laboratory with staff members. No animal species have been used. The destinations were successfully reached, with an error of 2%. A test was conducted against some evaluation parameters on the use of the model. The values are all close to the maximum expected value. Future developments include testing the application with a predefined protocol in a real-world environment with MCI patients. Full article