CRIS

Permanent URI for this communityhttps://investigadores.udd.cl/handle/123456789/1

Browse

Search Results

Now showing 1 - 10 of 25

Some of the metrics are blocked by your
consent settings
Predicting Particulate Matter Values in Metropolitan Areas Using Machine Learning
(IEEE, 2024-12-18)
Andrés Leiva-Araos
;
Tushya Vemuri
;
David Mena
;
Xudong Liu
3
Some of the metrics are blocked by your
consent settings
Machine learning-based identification of efficient and restrictive physiological subphenotypes in acute respiratory distress syndrome
(Springer Science and Business Media LLC, 2025-03-01)
Gabriela Meza-Fuentes
;
DELGADO BECERRA, OROZIMBA IRIS
;
Mario Barbé
;
Ignacio Sánchez
;
RETAMAL LUCERO, MAURICIO ANTONIO
Acute respiratory distress syndrome (ARDS) is a severe condition with high morbidity and mortality, characterized by significant clinical heterogeneity. This heterogeneity complicates treatment selection and patient inclusion in clinical trials. Therefore, the objective of this study is to identify physiological subphenotypes of ARDS using machine learning, and to determine ventilatory variables that can effectively discriminate between these subphenotypes in a bedside setting with high performance, highlighting potential utility for future clinical stratification approaches.</jats:p> Methodology A retrospective cohort study was conducted using data from our ICU, covering admissions from 2017 to 2021. The study included 224 patients over 18 years of age diagnosed with ARDS according to the Berlin criteria and undergoing invasive mechanical ventilation (IMV). Data on physiological and ventilatory variables were collected during the first 24 h IMV. We applied machine learning techniques to categorize subphenotypes in ARDS patients. Initially, we employed the unsupervised Gaussian Mixture Classification Model approach to group patients into subphenotypes. Subsequently, we applied supervised models such as XGBoost to perform root cause analysis, evaluate the classification of patients into these subgroups, and measure their performance.</jats:p> </jats:sec> <jats:sec> <jats:title>Results</jats:title> <jats:p>Our models identified two ARDS subphenotypes with significant clinical differences and significant outcomes. Subphenotype Efficient (<jats:italic>n</jats:italic> = 172) was characterized by lower mortality, lower clinical severity and presented a less restrictive pattern with better gas exchange compared to Subphenotype Restrictive (<jats:italic>n</jats:italic> = 52), which showed the opposite. The models demonstrated high performance with an area under the ROC curve of 0.94, sensitivity of 94.2% and specificity of 87.5%, in addition to an F1 score of 0.85. The most influential variables in the discrimination of subphenotypes were distension pressure, respiratory frequency and exhaled carbon dioxide volume.Conclusion This study presents an approach to improve subphenotype categorization in ARDS. The generation of clustering and prediction models by machine learning involving clinical, ventilatory mechanics, and gas exchange variables allowed for more accurate stratification of patients. These findings have the potential to optimize individualized treatment selection and improve clinical outcomes in patients with ARDS.</jats:p> Graphical Abstract
Scopus© Citations 2 5
Some of the metrics are blocked by your
consent settings
Predictive Optimization of Patient No-Show Management in Primary Healthcare Using Machine Learning
(Springer Science and Business Media LLC, 2025-01-14)
Andrés Leiva-Araos
;
Cristián Contreras
;
Hemani Kaushal
;
Zornitza Prodanoff
Scopus© Citations 7 4
Some of the metrics are blocked by your
consent settings
A Simple Machine Learning-Based Quantitative Structure–Activity Relationship Model for Predicting pIC50 Inhibition Values of FLT3 Tyrosine Kinase
(MDPI AG, 2025-01-14)
ALCAZAR JIMENEZ, JACKSON JOSE
;
Ignacio Sánchez
;
Cristian Merino
;
Bruno Monasterio
;
Gaspar Sajuria
<jats:p>Background/Objectives: Acute myeloid leukemia (AML) presents significant therapeutic challenges, particularly in cases driven by mutations in the FLT3 tyrosine kinase. This study aimed to develop a robust and user-friendly machine learning-based quantitative structure–activity relationship (QSAR) model to predict the inhibitory potency (pIC50 values) of FLT3 inhibitors, addressing the limitations of previous models in dataset size, diversity, and predictive accuracy. Methods: Using a dataset which was 14 times larger than those employed in prior studies (1350 compounds with 1269 molecular descriptors), we trained a random forest regressor, chosen due to its superior predictive performance and resistance to overfitting. Rigorous internal validation via leave-one-out and 10-fold cross-validation yielded Q2 values of 0.926 and 0.922, respectively, while external validation on 270 independent compounds resulted in an R2 value of 0.941 with a standard deviation of 0.237. Results: Key molecular descriptors influencing the inhibitor potency were identified, thereby improving the interpretability of structural requirements. Additionally, a user-friendly computational tool was developed to enable rapid prediction of pIC50 values and facilitate ligand-based virtual screening, leading to the identification of promising FLT3 inhibitors. Conclusions: These results represent a significant advancement in the field of FLT3 inhibitor discovery, offering a reliable, practical, and efficient approach for early-stage drug development, potentially accelerating the creation of targeted therapies for AML.</jats:p>
Scopus© Citations 2 8
Some of the metrics are blocked by your
consent settings
Advances in machine learning for tumour classification in cancer of unknown primary: A mini-review
(2025)
Karen Oróstica
;
Felipe Mardones
;
Yanara A. Bernal
;
Samuel Molina
;
Marcos Orchard
Scopus© Citations 3 8
Some of the metrics are blocked by your
consent settings
Interpretable multimodal classification for age-related macular degeneration diagnosis
(2024)
Carla Vairetti
;
Sebastián Maldonado
;
Loreto Cuitino
;
URZUA SALINAS, CRISTHIAN
;
Xu Yanwu
<jats:p>Explainable Artificial Intelligence (XAI) is an emerging machine learning field that has been successful in medical image analysis. Interpretable approaches are able to “unbox” the black-box decisions made by AI systems, aiding medical doctors to justify their diagnostics better. In this paper, we analyze the performance of three different XAI strategies for medical image analysis in ophthalmology. We consider a multimodal deep learning model that combines optical coherence tomography (OCT) and infrared reflectance (IR) imaging for the diagnosis of age-related macular degeneration (AMD). The classification model is able to achieve an accuracy of 0.94, performing better than other unimodal alternatives. We analyze the XAI methods in terms of their ability to identify retinal damage and ease of interpretation, concluding that grad-CAM and guided grad-CAM can be combined to have both a coarse visual justification and a fine-grained analysis of the retinal layers. We provide important insights and recommendations for practitioners on how to design automated and explainable screening tests based on the combination of two image sources.</jats:p>
Scopus© Citations 1
Some of the metrics are blocked by your
consent settings
Characterizing last-mile freight transportation using mobile phone data: The case of Santiago, Chile
(2024)
Franco Basso
;
Tomás Cox
;
Raúl Pezoa
;
Tomás Maldonado
;
VARAS VALDÉS, MAURICIO ANDRÉS
Scopus© Citations 3 6
Some of the metrics are blocked by your
consent settings
Relevance of Machine Learning Techniques in Water Infrastructure Integrity and Quality: A Review Powered by Natural Language Processing
(2023)
José García
;
LEIVA ARAOS, ANDRÉS
;
Emerson Diaz-Saavedra
;
Paola Moraga
;
Hernan Pinto
Water infrastructure integrity, quality, and distribution are fundamental for public health, environmental sustainability, economic development, and climate change resilience. Ensuring the robustness and quality of water infrastructure is pivotal for sectors like agriculture, industry, and energy production. Machine learning (ML) offers potential for bolstering water infrastructure integrity and quality by analyzing extensive data from sensors and other sources, optimizing treatment protocols, minimizing water losses, and improving distribution methods. This study delves into ML applications in water infrastructure integrity and quality by analyzing English-language articles from 2015 onward, compiling a total of 1087 articles. Initially, a natural language processing approach centered on topic modeling was adopted to classify salient topics. From each identified topic, key terms were extracted and utilized in a semi-automatic selection process, pinpointing the most relevant articles for further scrutiny, while unsupervised ML algorithms can assist in extracting themes from the documents, generating meaningful topics often requires intricate hyperparameter adjustments. Leveraging the Bidirectional Encoder Representations from Transformers (BERTopic) enhanced the study’s contextual comprehension in topic modeling. This semi-automatic methodology for bibliographic exploration begins with a broad topic categorization, advancing to an exhaustive analysis of each topic. The insights drawn underscore ML’s instrumental role in enhancing water infrastructure’s integrity and quality, suggesting promising future research directions. Specifically, the study has identified four key areas where ML has been applied to water management: (1) advancements in the detection of water contaminants and soil erosion; (2) forecasting of water levels; (3) advanced techniques for leak detection in water networks; and (4) evaluation of water quality and potability. These findings underscore the transformative impact of ML on water infrastructure and suggest promising paths for continued investigation.
Scopus© Citations 12 1
Some of the metrics are blocked by your
consent settings
The impact of electromobility in public transport: An estimation of energy consumption using disaggregated data in Santiago, Chile
(2024)
Franco Basso
;
Felipe Feijoo
;
Raúl Pezoa
;
VARAS VALDÉS, MAURICIO ANDRÉS
;
Brian Vidal
Scopus© Citations 23 1
Some of the metrics are blocked by your
consent settings
Multivariate word properties in fluency tasks reveal markers of Alzheimer's dementia
(2023)
Franco J. Ferrante
;
Joaquín Migeot
;
Agustina Birba
;
Lucía Amoruso
;
Gonzalo Pérez
<jats:title>Abstract</jats:title><jats:sec><jats:title>INTRODUCTION</jats:title><jats:p>Verbal fluency tasks are common in Alzheimer's disease (AD) assessments. Yet, standard valid response counts fail to reveal disease‐specific semantic memory patterns. Here, we leveraged automated word‐property analysis to capture neurocognitive markers of AD vis‐à‐vis behavioral variant frontotemporal dementia (bvFTD).</jats:p></jats:sec><jats:sec><jats:title>METHODS</jats:title><jats:p>Patients and healthy controls completed two fluency tasks. We counted valid responses and computed each word's frequency, granularity, neighborhood, length, familiarity, and imageability. These features were used for group‐level discrimination, patient‐level identification, and correlations with executive and neural (magnetic resonanance imaging [MRI], functional MRI [fMRI], electroencephalography [EEG]) patterns.</jats:p></jats:sec><jats:sec><jats:title>RESULTS</jats:title><jats:p>Valid responses revealed deficits in both disorders. Conversely, frequency, granularity, and neighborhood yielded robust group‐ and subject‐level discrimination only in AD, also predicting executive outcomes. Disease‐specific cortical thickness patterns were predicted by frequency in both disorders. Default‐mode and salience network hypoconnectivity, and EEG beta hypoconnectivity, were predicted by frequency and granularity only in AD.</jats:p></jats:sec><jats:sec><jats:title>DISCUSSION</jats:title><jats:p>Word‐property analysis of fluency can boost AD characterization and diagnosis.</jats:p></jats:sec><jats:sec><jats:title>Highlights</jats:title><jats:p><jats:list list-type="bullet"> <jats:list-item><jats:p>We report novel word‐property analyses of verbal fluency in AD and bvFTD.</jats:p></jats:list-item> <jats:list-item><jats:p>Standard valid response counts captured deficits and brain patterns in both groups.</jats:p></jats:list-item> <jats:list-item><jats:p>Specific word properties (e.g., frequency, granularity) were altered only in AD.</jats:p></jats:list-item> <jats:list-item><jats:p>Such properties predicted cognitive and neural (MRI, fMRI, EEG) patterns in AD.</jats:p></jats:list-item> <jats:list-item><jats:p>Word‐property analysis of fluency can boost AD characterization and diagnosis.</jats:p></jats:list-item> </jats:list></jats:p></jats:sec>
3Scopus© Citations 10

CRIS

Browse

Filters

Settings

Sort By

Results per page

Search Results