About
Activity
-
What a great day for LLM developers! OpenAI has just announced major price reductions for GPT-4o: 𝟱𝟬% 𝗰𝗵𝗲𝗮𝗽𝗲𝗿 𝗳𝗼𝗿 𝗶𝗻𝗽𝘂𝘁 and 𝟯𝟯%…
What a great day for LLM developers! OpenAI has just announced major price reductions for GPT-4o: 𝟱𝟬% 𝗰𝗵𝗲𝗮𝗽𝗲𝗿 𝗳𝗼𝗿 𝗶𝗻𝗽𝘂𝘁 and 𝟯𝟯%…
Liked by Miguel Ángel Sánchez Razo
-
Hace 10 años conocí a mi socio Sergio Haro Pérez mientras estudiábamos la maestría en ciencia de datos. Ahí noté que su capacidad técnica es…
Hace 10 años conocí a mi socio Sergio Haro Pérez mientras estudiábamos la maestría en ciencia de datos. Ahí noté que su capacidad técnica es…
Liked by Miguel Ángel Sánchez Razo
Experience & Education
Licenses & Certifications
Publications
-
Classification-Biased Apparent Brain Age for the Prediction of Alzheimer's Disease
Frontiers in Neuroscience
Machine Learning methods are often adopted to infer useful biomarkers for the early diagnosis of many neurodegenerative diseases and, in general, of neuroanatomical ageing. Some of these methods estimate the subject age from morphological brain data, which is then indicated as “brain age”. The difference between such a predicted brain age and the actual chronological age of a subject can be used as an indication of a pathological deviation from normal brain ageing. An important use of the brain…
Machine Learning methods are often adopted to infer useful biomarkers for the early diagnosis of many neurodegenerative diseases and, in general, of neuroanatomical ageing. Some of these methods estimate the subject age from morphological brain data, which is then indicated as “brain age”. The difference between such a predicted brain age and the actual chronological age of a subject can be used as an indication of a pathological deviation from normal brain ageing. An important use of the brain age model as biomarker is the prediction of Alzheimer's disease (AD) from structural Magnetic Resonance Imaging (MRI). Many different machine learning approaches have been applied to this specific predictive task, some of which have achieved high accuracy at the expense of the descriptiveness of the model. This work investigates an appropriate combination of data science techniques and linear models to provide, at the same time, high accuracy and good descriptiveness. The proposed method is based on a data workflow that include typical data science methods, such as outliers detection, feature selection, linear regression, and logistic regression. In particular, a novel inductive bias is introduced in the regression model, which is aimed at improving the accuracy and the specificity of the classification task. The method is compared to other machine learning approaches for AD classification based on morphological brain data with and without the use of the brain age, including Support Vector Machines and Deep Neural Networks. This study adopts brain MRI scans of 1, 901 subjects which have been acquired from three repositories (ADNI, AIBL, and IXI). A predictive model based only on the proposed apparent brain age and the chronological age has an accuracy of 88% and 92%, respectively, for male and female subjects, in a repeated cross-validation analysis, thus achieving a comparable or superior performance than state of the art machine learning methods.
Projects
-
Eli Lilly - Mexico Sales Data Warehouse Development
-
Activities: Business Intelligence, Data Integration, Data Governance, DWH Design (Data Vault), Master Data Manage-ment and Data Profiling. Team members: 10
Outcome: Implementation of the DWH which covers Institution’s information needs of reporting and data integration for Sales Productivity Process and Market Research areas; design and set up of a Data Governance Structure
Tools: SQL Server 2012, Master Data Management, Integration Services
-
FOVISSSTE - Data Governance and Business Intelligence Platform Implementation
-
Activities: Business Intelligence, Data Governance, and Data Profiling, BI Competency Center. Team members: 22.
Outcome: Implementation of the DWH and Dashboards that covers Institution’s information needs of reporting and data integration; design and set up of a structure of Data Governance and BI Competency Center.
Tools: Oracle 11g, ODI and Artus (Reporting). -
SAT - Information Lifecycle Management
-
Activities: Definition and implementation of Information Lifecycle Management Strategy. Team members: 10.
Outcome: Improvement in the storage infrastructures administration by implementing Institution’s information life cycle defining storage, backup and recovery policies.
Tools: Oracle 11g, SQL and Excel. -
SAT - Information Lifecycle Management
-
Activities: Definition and implementation of Information Lifecycle Management Strategy. Team members: 10.
Outcome: Improvement in the storage infrastructures administration by implementing Institution’s information life cycle defining storage, backup and recovery policies.
Tools: Oracle 11g, SQL and Excel. -
IMSS - Information Lifecycle Management
-
Activities: Information and Compliance analysis
Outcomes: Improve information management by implementing an Information Lifecycle Management (ILM) Strategy for different organization’s data sets
Tools: Microsoft Office -
PEMEX - P3
-
Activities: Information and Compliance analysis
Outcome: Creating a framework to standardize future projects of Enterprise Content Management
Tools: Microsoft Office -
IMSS - BDU
-
Activities: Data analysis and Database Design
Outcome: Institute’s Master Data management focused on creation of the Governance Framework which will guide the unique database structure within this Institute
Tools: Microsoft Office
Languages
-
Spanish
Native or bilingual proficiency
-
English
Professional working proficiency
More activity by Miguel Ángel
-
Git commands I have used most frequently during my 10+ years as a Software Engineer with the following workflow: 𝟭. 𝗴𝗶𝘁 𝗱𝗶𝗳𝗳: Installed Git…
Git commands I have used most frequently during my 10+ years as a Software Engineer with the following workflow: 𝟭. 𝗴𝗶𝘁 𝗱𝗶𝗳𝗳: Installed Git…
Liked by Miguel Ángel Sánchez Razo
-
🚨Falcon Sensor causes global IT outage🚨 But what is it? Falcon is a ✨ cloud-native ✨ security solution designed to detect and prevent cyber…
🚨Falcon Sensor causes global IT outage🚨 But what is it? Falcon is a ✨ cloud-native ✨ security solution designed to detect and prevent cyber…
Liked by Miguel Ángel Sánchez Razo
-
🔏 How encrypted is your encryption? Data Protection in the Age of AI and Big Data 🔑 The convergence of artificial intelligence, big data…
🔏 How encrypted is your encryption? Data Protection in the Age of AI and Big Data 🔑 The convergence of artificial intelligence, big data…
Liked by Miguel Ángel Sánchez Razo
-
Our 2024 UK Data & AI Salary Guide is now live!!! 🚀🚀🚀 📩 Download the Guide now: https://lnkd.in/evu6_SCm Designed to help professionals…
Our 2024 UK Data & AI Salary Guide is now live!!! 🚀🚀🚀 📩 Download the Guide now: https://lnkd.in/evu6_SCm Designed to help professionals…
Liked by Miguel Ángel Sánchez Razo
-
Me alegra que la IA esté en boca de todos, ya que cuando tu empresa intenta aplicarla, se enfrenta con el eterno problema: tener datos confiables…
Me alegra que la IA esté en boca de todos, ya que cuando tu empresa intenta aplicarla, se enfrenta con el eterno problema: tener datos confiables…
Liked by Miguel Ángel Sánchez Razo
-
Is now the right time to appoint a chief AI officer? Rockborne CEO, Waseem Ali spoke with Cath Everett, over at the Raconteur | B Corp™ earlier this…
Is now the right time to appoint a chief AI officer? Rockborne CEO, Waseem Ali spoke with Cath Everett, over at the Raconteur | B Corp™ earlier this…
Liked by Miguel Ángel Sánchez Razo
-
Proud to share another dashboard I created during my training at Rockborne a few months ago - this time using Power BI! This dashboard analyses…
Proud to share another dashboard I created during my training at Rockborne a few months ago - this time using Power BI! This dashboard analyses…
Liked by Miguel Ángel Sánchez Razo
Other similar profiles
Explore collaborative articles
We’re unlocking community knowledge in a new way. Experts add insights directly into each article, started with the help of AI.
Explore More