Pilot Assessment of Piezoelectric Transducers as a Cost-Effective Alternative to EndoPAT.

INTRODUCTION: Current microvascular assessments may not be practical or accessible requiring experienced personnel and/or ongoing equipment costs. Piezoelectric transducers can reliably obtain finger blood pressure waves, similar to peripheral arterial tonometry devices; thus, they could be used to estimate microvascular function. We aimed to validate piezoelectric transducers as an alternative measure of microvascular function compared to EndoPAT. METHODS: Twenty-five adults (aged 20-64 years) completed reactive hyperemia (5 min forearm circulatory occlusion and 3 min recovery) with piezoelectric transducers on the middle fingers and EndoPAT probes on the index fingers. Average area under the curve (AUC) of the pulse wave signal for the occluded and control arms was determined at baseline, every 30 s post-occlusion, and 10 s around the peak response. Microvascular function index (MFI) was calculated as the ratio of AUC post-occlusion to AUC baseline in the test arm, then normalized to the same ratio in the control arm. MFI at each time point was correlated with the reactive hyperemia index (RHI) from the EndoPAT. RESULTS: The greatest significance was found between RHI and MFI at 10 s around the peak response (Spearman's r = 0.67, p = 0.0002; Pearson's r = 0.76, p = 0.00001). CONCLUSION: MFI is a reusable and user-friendly microvascular function assessment that could provide better access to vascular health screening.

A review of machine learning methods for cancer characterization from microbiome data.

Recent studies have shown that the microbiome can impact cancer development, progression, and response to therapies suggesting microbiome-based approaches for cancer characterization. As cancer-related signatures are complex and implicate many taxa, their discovery often requires Machine Learning approaches. This review discusses Machine Learning methods for cancer characterization from microbiome data. It focuses on the implications of choices undertaken during sample collection, feature selection and pre-processing. It also discusses ML model selection, guiding how to choose an ML model, and model validation. Finally, it enumerates current limitations and how these may be surpassed. Proposed methods, often based on Random Forests, show promising results, however insufficient for widespread clinical usage. Studies often report conflicting results mainly due to ML models with poor generalizability. We expect that evaluating models with expanded, hold-out datasets, removing technical artifacts, exploring representations of the microbiome other than taxonomical profiles, leveraging advances in deep learning, and developing ML models better adapted to the characteristics of microbiome data will improve the performance and generalizability of models and enable their usage in the clinic.

Mortality prediction using medical time series on TBI patients.

BACKGROUND AND OBJECTIVE: Traumatic Brain Injury (TBI) is one of the leading causes of injury-related mortality in the world, with severe cases reaching mortality rates of 30-40%. It is highly heterogeneous both in causes and consequences making more complex the medical interpretation and prognosis. Gathering clinical, demographic, and laboratory data to perform a prognosis requires time and skill in several clinical specialties. Artificial intelligence (AI) methods can take advantage of existing data by performing helpful predictions and guiding physicians toward a better prognosis and, consequently, better healthcare. The objective of this work was to develop learning models and evaluate their capability of predicting the mortality of TBI. The predictive model would allow the early assessment of the more serious cases and scarce medical resources can be pointed toward the patients who need them most. METHODS: Long Short Term Memory (LSTM) and Transformer architectures were tested and compared in performance, coupled with data imbalance, missing data, and feature selection strategies. From the Medical Information Mart for Intensive Care III (MIMIC-III) dataset, a cohort of TBI patients was selected and an analysis of the first 48 hours of multiple time series sequential variables was done to predict hospital mortality. RESULTS: The best performance was obtained with the Transformer architecture, achieving an AUC of 0.907 with the larger group of features and trained with class proportion class weights and binary cross entropy loss. CONCLUSIONS: Using the time series sequential data, LSTM and Transformers proved to be both viable options for predicting TBI hospital mortality in 48 hours after admission. Overall, using sequential deep learning models with time series data to predict TBI mortality is viable and can be used as a helpful indicator of the well-being of patients.

Machine learning-based approaches for cancer prediction using microbiome data.

Emerging evidence of the relationship between the microbiome composition and the development of numerous diseases, including cancer, has led to an increasing interest in the study of the human microbiome. Technological breakthroughs regarding DNA sequencing methods propelled microbiome studies with a large number of samples, which called for the necessity of more sophisticated data-analytical tools to analyze this complex relationship. The aim of this work was to develop a machine learning-based approach to distinguish the type of cancer based on the analysis of the tissue-specific microbial information, assessing the human microbiome as valuable predictive information for cancer identification. For this purpose, Random Forest algorithms were trained for the classification of five types of cancer-head and neck, esophageal, stomach, colon, and rectum cancers-with samples provided by The Cancer Microbiome Atlas database. One versus all and multi-class classification studies were conducted to evaluate the discriminative capability of the microbial data across increasing levels of cancer site specificity, with results showing a progressive rise in difficulty for accurate sample classification. Random Forest models achieved promising performances when predicting head and neck, stomach, and colon cancer cases, with the latter returning accuracy scores above 90% across the different studies conducted. However, there was also an increased difficulty when discriminating esophageal and rectum cancers, failing to differentiate with adequate results rectum from colon cancer cases, and esophageal from head and neck and stomach cancers. These results point to the fact that anatomically adjacent cancers can be more complex to identify due to microbial similarities. Despite the limitations, microbiome data analysis using machine learning may advance novel strategies to improve cancer detection and prevention, and decrease disease burden.

The 2023 wearable photoplethysmography roadmap.

Photoplethysmography is a key sensing technology which is used in wearable devices such as smartwatches and fitness trackers. Currently, photoplethysmography sensors are used to monitor physiological parameters including heart rate and heart rhythm, and to track activities like sleep and exercise. Yet, wearable photoplethysmography has potential to provide much more information on health and wellbeing, which could inform clinical decision making. This Roadmap outlines directions for research and development to realise the full potential of wearable photoplethysmography. Experts discuss key topics within the areas of sensor design, signal processing, clinical applications, and research directions. Their perspectives provide valuable guidance to researchers developing wearable photoplethysmography technology.

Single Modality vs. Multimodality: What Works Best for Lung Cancer Screening?

In a clinical context, physicians usually take into account information from more than one data modality when making decisions regarding cancer diagnosis and treatment planning. Artificial intelligence-based methods should mimic the clinical method and take into consideration different sources of data that allow a more comprehensive analysis of the patient and, as a consequence, a more accurate diagnosis. Lung cancer evaluation, in particular, can benefit from this approach since this pathology presents high mortality rates due to its late diagnosis. However, many related works make use of a single data source, namely imaging data. Therefore, this work aims to study the prediction of lung cancer when using more than one data modality. The National Lung Screening Trial dataset that contains data from different sources, specifically, computed tomography (CT) scans and clinical data, was used for the study, the development and comparison of single-modality and multimodality models, that may explore the predictive capability of these two types of data to their full potential. A ResNet18 network was trained to classify 3D CT nodule regions of interest (ROI), whereas a random forest algorithm was used to classify the clinical data, with the former achieving an area under the ROC curve (AUC) of 0.7897 and the latter 0.5241. Regarding the multimodality approaches, three strategies, based on intermediate and late fusion, were implemented to combine the information from the 3D CT nodule ROIs and the clinical data. From those, the best model-a fully connected layer that receives as input a combination of clinical data and deep imaging features, given by a ResNet18 inference model-presented an AUC of 0.8021. Lung cancer is a complex disease, characterized by a multitude of biological and physiological phenomena and influenced by multiple factors. It is thus imperative that the models are capable of responding to that need. The results obtained showed that the combination of different types may have the potential to produce more comprehensive analyses of the disease by the models.

Demonstrating the interference of tissue processing in the evaluation of tissue biomarkers: The case of PD-L1.

The immunohistochemical (IHC) expression of PD-L1 in cancer models is used as a predictive biomarker of response to immunotherapy. We aimed to evaluate the impact of the usage of 3 different tissue processors in the IHC expression of PD-L1 antibody clones: 22C3 and SP142. Three different topographies of samples (n = 73) were selected at the macroscopy room: 39 uterine leiomyomas, 17 placentas and 17 palatine tonsils. Three fragments were collected from each sample and were inked with a specific color that represented their separate processing in a different tissue processor (A, B or C). During embedding, the 3 fragments with distinct processing were ensemble in the same cassette for sectioning of 3 slides/each: hematoxylin-eosin, 22C3 PDL1 IHC staining and SP142 PD-L1 IHC staining, that were blindly observed by 2 pathologists under digital environment. All but one set of 3 fragments were considered adequate for observation even in the presence of artifacts associated with processing issues that were recorded as high as 50.7 % for processor C. The occurrence of background non-specific staining and the presence of false positive results appear to be unrelated with the PD-L1 clone or the type of tissue processing. 22C3 PD-L1 was more frequently considered adequate for evaluation than SP142 PD-L1 that, in 29.2 % of WSIs (after tissue processor C) were considered not adequate for observation due to lack of the typical pattern of expression. Similarly, the intensity of PD-L1 staining was significantly decreased in fragments processed by C (both PD-L1 clones) in tonsil and placenta specimens, and by A (both clones) in comparison with those processed by B. This study demonstrates the need to standardize the tissue processing in pathology to cope with the growing needs of precision medicine quantifications and the production of high-quality material necessary for computational pathology usage.

Assessing the hearing of children exposed to zika virus with an initially normal newborn hearing screen: a longitudinal cohort study.

BACKGROUND: Zika virus (ZIKV) infection can result in hearing loss in babies, consequently, audiological monitoring is necessary. AIMS: This study aimed to evaluate the frequency of hearing impairment in neonates and children exposed to ZIKV during the intrauterine period. MATERIALS AND METHODS: A cohort of 30 children born to mothers infected with ZIKV during pregnancy (March 2016-January 2017) underwent repeated hearing assessments performed 48 h after birth. Universal Newborn Hearing Screening revealed normal results in all children at 6, 13, 24, and 36 months. Children were divided into two subgroups based on real-time polymerase chain reaction: RT-PCR(+) and RT-PCR(-). RESULTS: At 24 months, the cumulative incidence of hearing alteration was 57.1%. There was no significant difference in the detection of hearing alteration between RT-PCR(+) and (-) groups. None of the children had sensorineural hearing loss. CONCLUSIONS AND SIGNIFICANCE: None of the children had sensorineural hearing loss. Total incidence conductive type (per 1000 live births), RT-PCR ZIKV (-) 2.2, prevalence 20% and RT-PCR ZIKV 3.1, prevalence 35.7%.The incidence of hearing alteration was highest at 24 months of age (57.1%, n = 8; only conductive type).

Importância e desafios da vigilância em saúde em uma região de fronteira internacional: um estudo de caso / The importance and challenges of health surveillance in an international border: a case study

Resumo O objetivo deste artigo foi identificar os principais desafios da promoção da vigilância em saúde em uma região de tríplice fronteira da Amazônia Legal brasileira. Foi realizado um estudo de caso único, explicativo, com abordagem qualitativa, que utilizou dados documentais e entrevistas. Os resultados demonstram que a vigilância em saúde é fundamental para o controle de doenças na região. Além disso, as diferenças dos sistemas de saúde dos três países que compõem a tríplice fronteira (Brasil, Colômbia e Peru) se mostraram o principal desafio para o estabelecimento de políticas sanitárias.

Abstract The objective of This article was to identify the main challenges of promoting health surveillance in a triple border region of the Brazilian legal Amazon. A single explanatory case study was carried out, with a qualitative approach, which used documentary data and interviews. The Results demonstrate that health surveillance is essential for disease control in the studied region. In addition, the differences between the health systems of the three countries that make up the triple border (Brazil, Colombia, and Peru) showed to be the main challenge for establishing health policies.

Impact of Label Noise on the Learning Based Models for a Binary Classification of Physiological Signal.

Label noise is omnipresent in the annotations process and has an impact on supervised learning algorithms. This work focuses on the impact of label noise on the performance of learning models by examining the effect of random and class-dependent label noise on a binary classification task: quality assessment for photoplethysmography (PPG). PPG signal is used to detect physiological changes and its quality can have a significant impact on the subsequent tasks, which makes PPG quality assessment a particularly good target for examining the impact of label noise in the field of biomedicine. Random and class-dependent label noise was introduced separately into the training set to emulate the errors associated with fatigue and bias in labeling data samples. We also tested different representations of the PPG, including features defined by domain experts, 1D raw signal and 2D image. Three different classifiers are tested on the noisy training data, including support vector machine (SVM), XGBoost, 1D Resnet and 2D Resnet, which handle three representations, respectively. The results showed that the two deep learning models were more robust than the two traditional machine learning models for both the random and class-dependent label noise. From the representation perspective, the 2D image shows better robustness compared to the 1D raw signal. The logits from three classifiers are also analyzed, the predicted probabilities intend to be more dispersed when more label noise is introduced. From this work, we investigated various factors related to label noise, including representations, label noise type, and data imbalance, which can be a good guidebook for designing more robust methods for label noise in future work.

Limited Stress Response to Transplantation in the Mediterranean Macroalga Ericaria amentacea, a Key Species for Marine Forest Restoration.

In the Mediterranean Sea, brown macroalgae represent the dominant species in intertidal and subtidal habitats. Despite conservation efforts, these canopy-forming species showed a dramatic decline, highlighting the urge for active intervention to regenerate self-sustaining populations. For this reason, the restoration of macroalgae forests through transplantation has been recognized as a promising approach. However, the potential stress caused by the handling of thalli has never been assessed. Here, we used a manipulative approach to assess the transplant-induced stress in the Mediterranean Ericaria amentacea, through the analysis of biochemical proxies, i.e., phenolic compounds, lipids, and fatty acids in both transplanted and natural macroalgae over time. The results showed that seasonal environmental variability had an important effect on the biochemical composition of macroalgae, suggesting the occurrence of acclimation responses to summer increased temperature and light irradiance. Transplant-induced stress appears to have only amplified the biochemical response, probably due to increased sensitivity of the macroalgae already subjected to mechanical and osmotic stress (e.g., handling, wounding, desiccation). The ability of E. amentacea to cope with both environmental and transplant-induced stress highlights the high plasticity of the species studied, as well as the suitability of transplantation of adult thalli to restore E. amentacea beds.

Unsupervised Approach for Malignancy Assessment of Lung Nodules in Computed Tomography Scans Using Radiomic Features.

Lung cancer is the leading cause of cancer death worldwide. Early low-dose computed tomography (CT) screening can decrease its mortality rate and computer-aided diagnoses systems may make these screenings more accessible. Radiomic features and supervised machine learning have traditionally been employed in these systems. Contrary to supervised methods, unsupervised learning techniques do not require large amounts of annotated data which are labor-intensive to gather and long training times. Therefore, recent approaches have used unsupervised methods, such as clustering, to improve the performance of supervised models. However, an analysis of purely unsupervised methods for malignancy prediction of lung nodules from CT images has not been performed. This work studies nodule malignancy in the LIDC-IDRI image collection of chest CT scans using established radiomic features and unsupervised learning methods based on k-Means, Spectral Clustering, and Gaussian Mixture clustering. All tested methods resulted in clusters of high homogeneity malignancy. Results suggest convex feature distributions and well-separated feature subspaces associated with different diagnoses. Furthermore, diagnosis uncertainty may be explained by common characteristics captured by radiomic features. The k-Means and Gaussian Mixture models are able to generalize to unseen data, achieving a balanced accuracy of 87.23% and 86.96% when inference was tested. These results motivate the usage of unsupervised approaches for malignancy prediction of lung nodules, such as cluster-then-label models. Clinical Relevance- Unsupervised clustering of radiomic features of lung nodules in chest CT scans can differentiate between malignant and benign cases and reflects experts' diagnosis uncertainty.

A Random Forest-based Classifier for MYCN Status Prediction in Neuroblastoma using CT Images.

Neuroblastoma (NB) is the most common extracranial solid tumor in childhood. Genomic amplification of MYCN is associated with poor outcomes and is detected in 16% of all NB cases. CT scans and MRI are the imaging techniques recommended for diagnosis and disease staging. The assessment of imaging features such as tumor volume, shape, and local extension represent relevant prognostic information. Radiogenomics have shown powerful results in the assessment of the genotype based on imaging findings automatically extracted from medical images. In this work, random forest was used to classify the MYCN amplification using radiomic features extracted from CT slices in a population of 46 NB patients. The learning model showed an area under the curve (AUC) of 0.85 ± 0.13, suggesting that radiomic-based methodologies might be helpful in the extraction of information that is not accessible by human naked eyes but could aid the clinicians on the diagnosis and treatment plan definition. Clinical relevance - This approach represents a random forest-based model to predict the MYCN amplification in NB patients that could give a faster, earlier, and repeatable analysis of the tumor along the time.

Synthesizing 3D Lung CT scans with Generative Adversarial Networks.

In the healthcare domain, datasets are often private and lack large amounts of samples, making it difficult to cope with the inherent patient data heterogeneity. As an attempt to mitigate data scarcity, generative models are being used due to their ability to produce new data, using a dataset as a reference. However, synthesis studies often rely on a 2D representation of data, a seriously limited form of information when it comes to lung computed tomography scans where, for example, pathologies like nodules can manifest anywhere in the organ. Here, we develop a 3D Progressive Growing Generative Adversarial Network capable of generating thoracic CT volumes at a resolution of 1283, and analyze the model outputs through a quantitative metric (3D Muli-Scale Structural Similarity) and a Visual Turing Test. Clinical relevance - This paper is a novel application of the 3D PGGAN model to synthesize CT lung scans. This preliminary study focuses on synthesizing the entire volume of the lung rather than just the lung nodules. The synthesized data represent an attempt to mitigate data scarcity which is one of the major limitations to create learning models with good generalization in healthcare.

On the way for the best imaging features from CT images to predict EGFR Mutation Status in Lung Cancer.

Artificial Intelligence-based tools have shown promising results to help clinicians in diagnosis tasks. Radio-genomics would aid in the genotype characterization using information from radiologic images. The prediction of the mutations status of main oncogenes associated with lung cancer will help the clinicians to have a more accurate diagnosis and a personalized treatment plan, decreasing the need to use the biopsy. In this work, novel and objective features were extracted from the lung that contained the nodule, and several machine learning methods were combined with feature selection techniques to select the best approach to predict the EGFR mutation status in lung cancer CT images. An AUC of 0.756 ± 0.055 was obtained using a logistic regression and independent component analysis as feature selector, supporting the hypothesis that CT images can capture pathophysiological information with great value for clinical assessment and personalized medicine of lung cancer. Clinical Relevance - Radiogenomic approaches could be an interesting help for lung cancer characterization. This work represents a preliminary study for the development of computer-aided decision systems to provide a more accurate and fast characterization of lung cancer which is fundamental for an adequate treatment plan for lung cancer patients.

Menstrual cycle and oral contraceptives influence cerebrovascular dynamics during hypercapnia.

Women experience fluctuating orthostatic intolerance during the menstrual cycle, suggesting sex hormones may influence cerebral blood flow. Young (aged 18-30) healthy women, either taking oral contraceptives (OC; n = 14) or not taking OC (NOC; n = 12), were administered hypercapnic gas (5%) for 5 min in the low hormone (LH; placebo pill) and high hormone (HH; active pill) menstrual phases. Hemodynamic and cerebrovascular variables were continuously measured. Cerebral blood velocity changes were monitored using transcranial doppler ultrasound of the middle cerebral artery to determine cerebrovascular reactivity. Cerebral autoregulation was assessed using steady-state analysis (static cerebral autoregulation) and transfer function analysis (dynamic cerebral autoregulation; dCA). In response to hypercapnia, menstrual phase did not influence static cardiovascular or cerebrovascular responses (all p > 0.07); however, OC users had a greater increase of mean middle cerebral artery blood velocity compared to NOC (NOC-LH 12 ± 6 cm/s vs. NOC-HH 16 ± 9 cm/s; OC-LH 18 ± 5 cm/s vs. OC-HH 17 ± 11 cm/s; p = 0.048). In all women, hypercapnia improved high frequency (HF) and very low frequency (VLF) cerebral autoregulation (decreased nGain; p = 0.002 and <0.001, respectively), whereas low frequency (LF) Phase decreased in NOC-HH (p = 0.001) and OC-LH (p = 0.004). Therefore, endogenous sex hormones reduce LF dCA during hypercapnia in the HH menstrual phase. In contrast, pharmaceutical sex hormones (OC use) have no acute influence (HH menstrual phase) yet elicit a chronic attenuation of LF dCA (LH menstrual phase) during hypercapnia.

Learning Models for Traumatic Brain Injury Mortality Prediction on Pediatric Electronic Health Records.

Background: Traumatic Brain Injury (TBI) is one of the leading causes of injury related mortality in the world, with severe cases reaching mortality rates of 30-40%. It is highly heterogeneous both in causes and consequences, complicating medical interpretation and prognosis. Gathering clinical, demographic, and laboratory data to perform a prognosis requires time and skill in several clinical specialties. Machine learning (ML) methods can take advantage of the data and guide physicians toward a better prognosis and, consequently, better healthcare. The objective of this study was to develop and test a wide range of machine learning models and evaluate their capability of predicting mortality of TBI, at hospital discharge, while assessing the similarity between the predictive value of the data and clinical significance. Methods: The used dataset is the Hackathon Pediatric Traumatic Brain Injury (HPTBI) dataset, composed of electronic health records containing clinical annotations and demographic data of 300 patients. Four different classification models were tested, either with or without feature selection. For each combination of the classification model and feature selection method, the area under the receiver operator curve (ROC-AUC), balanced accuracy, precision, and recall were calculated. Results: Methods based on decision trees perform better when using all features (Random Forest, AUC = 0.86 and XGBoost, AUC = 0.91) but other models require prior feature selection to obtain the best results (k-Nearest Neighbors, AUC = 0.90 and Artificial Neural Networks, AUC = 0.84). Additionally, Random Forest and XGBoost allow assessing the feature's importance, which could give insights for future strategies on the clinical routine. Conclusion: Predictive capability depends greatly on the combination of model and feature selection methods used but, overall, ML models showed a very good performance in mortality prediction for TBI. The feature importance results indicate that predictive value is not directly related to clinical significance.

The Influence of a Coherent Annotation and Synthetic Addition of Lung Nodules for Lung Segmentation in CT Scans.

Lung cancer is a highly prevalent pathology and a leading cause of cancer-related deaths. Most patients are diagnosed when the disease has manifested itself, which usually is a sign of lung cancer in an advanced stage and, as a consequence, the 5-year survival rates are low. To increase the chances of survival, improving the cancer early detection capacity is crucial, for which computed tomography (CT) scans represent a key role. The manual evaluation of the CTs is a time-consuming task and computer-aided diagnosis (CAD) systems can help relieve that burden. The segmentation of the lung is one of the first steps in these systems, yet it is very challenging given the heterogeneity of lung diseases usually present and associated with cancer development. In our previous work, a segmentation model based on a ResNet34 and U-Net combination was developed on a cross-cohort dataset that yielded good segmentation masks for multiple pathological conditions but misclassified some of the lung nodules. The multiple datasets used for the model development were originated from different annotation protocols, which generated inconsistencies for the learning process, and the annotations are usually not adequate for lung cancer studies since they did not comprise lung nodules. In addition, the initial datasets used for training presented a reduced number of nodules, which was showed not to be enough to allow the segmentation model to learn to include them as a lung part. In this work, an objective protocol for the lung mask's segmentation was defined and the previous annotations were carefully reviewed and corrected to create consistent and adequate ground-truth masks for the development of the segmentation model. Data augmentation with domain knowledge was used to create lung nodules in the cases used to train the model. The model developed achieved a Dice similarity coefficient (DSC) above 0.9350 for all test datasets and it showed an ability to cope, not only with a variety of lung patterns, but also with the presence of lung nodules as well. This study shows the importance of using consistent annotations for the supervised learning process, which is a very time-consuming task, but that has great importance to healthcare applications. Due to the lack of massive datasets in the medical field, which consequently brings a lack of wide representativity, data augmentation with domain knowledge could represent a promising help to overcome this limitation for learning models development.

Multiple instance learning for lung pathophysiological findings detection using CT scans.

Lung diseases affect the lives of billions of people worldwide, and 4 million people, each year, die prematurely due to this condition. These pathologies are characterized by specific imagiological findings in CT scans. The traditional Computer-Aided Diagnosis (CAD) approaches have been showing promising results to help clinicians; however, CADs normally consider a small part of the medical image for analysis, excluding possible relevant information for clinical evaluation. Multiple Instance Learning (MIL) approach takes into consideration different small pieces that are relevant for the final classification and creates a comprehensive analysis of pathophysiological changes. This study uses MIL-based approaches to identify the presence of lung pathophysiological findings in CT scans for the characterization of lung disease development. This work was focus on the detection of the following: Fibrosis, Emphysema, Satellite Nodules in Primary Lesion Lobe, Nodules in Contralateral Lung and Ground Glass, being Fibrosis and Emphysema the ones with more outstanding results, reaching an Area Under the Curve (AUC) of 0.89 and 0.72, respectively. Additionally, the MIL-based approach was used for EGFR mutation status prediction - the most relevant oncogene on lung cancer, with an AUC of 0.69. The results showed that this comprehensive approach can be a useful tool for lung pathophysiological characterization.

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.