MyMedR

Displaying all 3 publications

Abstract:

Sort:

Data-driven total organic carbon prediction using feature selection methods incorporated in an automated machine learning framework

Macêdo BDS, Wayo DDK, Campos D, De Santis RB, Martinho AD, Yaseen ZM, et al.

Sci Rep, 2025 Mar 27;15(1):10658.
PMID: 40148387 DOI: 10.1038/s41598-025-91224-4

An accurate assessment of shale gas resources is highly important for the sustainable development of these energy resources. Total organic carbon (TOC) analysis thus becomes fundamental for understanding the distribution and quality of hydrocarbon source rocks within a shale gas reservoir. The elevation of the TOC is often associated with the presence of source rocks, indicating the potential for oil and gas production. TOC assessment is performed using laboratory methods, which can be time-consuming and costly. Data-driven models have been successfully applied to model the relationship between TOC and other constituents and to predict the TOC content. However, these methods depend on extensive parameter adjustments that must be carefully conducted in different sedimentary environments. In this context, Automated Machine Learning (AutoML) is an alternative for accurately predicting TOCs, saving time-consuming fine-tuning steps in model development. This study aims to develop an AutoML strategy for estimating TOC using well log data. This procedure automatically preprocesses the search for the best method parameters, reducing the execution time. Among the methods evaluated, Extremely Randomized Trees (XT) performed best (R = 0.8632, MSE = 0.1806) in the test set. The proposed strategy provides a powerful data-driven method, which allows real-world use of the well to assist in data analysis and subsequent decision-making.
Fulltext Bridging the Gap in Access to Care for Children With CNS Tumors Worldwide

Moreira DC, Rajagopal R, Navarro-Martin Del Campo RM, Polanco AC, Alcasabas AP, Arredondo-Navarro LA, et al.

JCO Glob Oncol, 2020 04;6:583-584.
PMID: 32293939 DOI: 10.1200/GO.20.00047
Development of the pediatric neuro-oncology services assessment aid: An assessment tool for pediatric neuro-oncology service delivery capacity

Rajagopal R, Diaz Coronado R, Hamid SA, Navarro Martin Del Campo R, Boop F, Bag A, et al.

Neurooncol Adv, 2024;6(1):vdae171.
PMID: 39534540 DOI: 10.1093/noajnl/vdae171

BACKGROUND: To enhance the quality of care available for children with central nervous system (CNS) tumors across the world, a systematic evaluation of capacity is needed to identify gaps and prioritize interventions. To that end, we created the pediatric neuro-oncology (PNO) resource assessment aid (PANORAMA) tool.
METHODS: The development of PANORAMA encompassed 3 phases: operationalization, consensus building, and piloting. PANORAMA aimed to capture the elements of the PNO care continuum through domains with weighted assessments reflecting their importance. Responses were ordinally scored to reflect the level of satisfaction. PANORAMA was revised based on feedback at various phases to improve its relevance, usability, and clarity.
RESULTS: The operationalization phase identified 14 domains by using 252 questions. The consensus phase involved 15 experts (6 pediatric oncologists, 3 radiation oncologists, 2 neurosurgeons, 2 radiologists, and 2 pathologists). The consensus phase validated the identified domains, questions, and scoring methodology. The PANORAMA domains included national context, hospital infrastructure, organization and service integration, human resources, financing, laboratory, neurosurgery, diagnostic imaging, pathology, chemotherapy, radiotherapy, supportive care, and patient outcomes. PANORAMA was piloted at 13 institutions in 12 countries, representing diverse patient care contexts. Face validity was assessed by examining the correlation between the estimated score by respondents and calculated PANORAMA scores for each domain (r = 0.67, P

Filters

Please provide feedback to Administrator (afdal@afpm.org.my)

External Links