Multi-omic data integration
Genomic, epigenetic and clinical data integrated with Whole Genome Sequencing (WGS) to investigate disease mechanisms and build high-resolution disease profiles.
00 / jpML · SmartInsights
Precision biotech frameworks for multilayered disease profiling.
Architecting systems that leverage AI (ML), computer vision and multi-omic data integration — delivering customized solutions that enhance clinical diagnostics, strengthen patient autonomy and empower decision-making by HCLS institution leaders.
- Discipline
- Medicine & Systems Informatics
- Focus
- Genomics · ML · Precision medicine
- Scope
- Governments · Hospitals · Biotech
Institutions, hospitals and biotech collaborations
01 / About
“I believe biotech and healthcare should put people first — using technology not to replace human care, but to deepen it.”
I am CSciO (Chief Scientific Officer) at Origen Genetics. My daily work combines personalized medicine, machine learning, Panomics, computer vision and AI to restore the essence of the doctor–patient relationship while delivering precise, evidence-based and affordable care. Trained in Medicine and Systems Informatics, I began by supporting health and life sciences startups, discovering the transformative power of AI (ML) in real-world healthcare.
Today I translate cutting-edge technologies into practical, explainable tools that physicians and health institutions can apply every day — turning reactive care into measurable prevention, freeing clinical time for what matters, and equipping health-system leaders to modernize care delivery at scale. My approach is pragmatic and data-driven: prevent early, diagnose better, and empower both sides of care.
I work at the intersection of biotechnology, artificial intelligence, data governance and precision medicine, helping governments, hospitals and health organizations transform fragmented biomedical data into integrated, decision-ready systems that improve population health outcomes. I work globally — consulting, speaking and building solutions that bring a vision of truly human-centered healthcare to life.
Approach
“The goal is not to replace clinical judgement, but to support it with validated, causally grounded evidence — as already deployed in population-scale health records and genomic platforms.”
Formalised in GAUGE, a causal translation protocol for biomedical ML: estimand definition before modelling, dataset design as a first-class phase, six conjunctive gates with explicit stop rules, and recommendations surfaced only when they are clinician-modifiable, guideline-concordant and supported by an identified effect.
Credentials & memberships
- Holds a fully completed medical school education (6-year curriculum, 360+ ECTS / EQF Level 7 equivalent) along with U.S. academic equivalency evaluated under AACRAO standards — qualifications formally vetted and accepted in public procurement tenders within the Spanish Public Administration.
- Certified Machine Learning Engineer. Verify
- Member of IAAA — International Association of Algorithmic Auditors. iaaa-algorithmicauditors.org
- Member of LatinX in AI. latinxinai.org
- Member of the Spanish Society of Genetics. segenetica.es
- Specialization in biotechnology. Verify
- Certification in Evaluations of AI Applications in Healthcare. Verify
02 / Expertise
Core areas of work
Bioinformatics expertise combined with specialized biomarker measurement partners. Predictive models are continuously validated by a multidisciplinary scientific committee and updated with emerging evidence from non-coding genomic regions and spatial transcriptomics, enabling discovery of tissue-specific biomarker patterns.
Machine learning & computer vision
Design and clinical validation of machine learning and deep learning models for image-based diagnostics and biomedical signal interpretation.
Scalable omics architecture
Scalable architectures for omics data processing, and MLOps pipelines with post-deployment monitoring, external validation and target-trial emulation as evidence changes.
Data governance & responsible AI
Causal-first governance for clinical AI: every claim carries an evidence label, every variable a causal role and actionability class, with models reviewed by a multidisciplinary scientific committee.
Precision & pharmacogenetics
Clinically actionable insight that supports decision-making, including pharmacogenetic treatment optimization.
Institutional enablement
Training on practical machine learning and computer vision adoption, plus technical strategy discussions with institutional stakeholders.
03 / Work
Selected roles and projects
Origen Biotech Corp — Genetics
Scientific & Data Officer
Defining scientific and data strategy at the convergence of genomics, clinical data and applied machine learning — translating complex biomedical problems into deployable technology for the Health & Life Sciences ecosystem.
Lifely — Genomic preventive health
CSciO, Origen Genetics
Scientific direction of Lifely, Origen's consumer genomics service: a single DNA analysis interpreted across disease predisposition (200+ conditions), epigenetics, nutrigenetics and pharmacogenetics, translated by genetics specialists into a personalised prevention plan with year-long follow-up as new evidence emerges.
Care Integration Modules at population scale
Public Electronic Health Record — SERGAS
Orchestrated AI-driven modules embedded across chronic and oncologic care pathways: reconciling multi-source clinical data into a real-time 360° patient view, surfacing guideline-concordant decision support and automating administrative workflows.
Genomic knowlake
MLOps & knowledge infrastructure
A domain-specific scientific crawler continuously updates the genomic knowledge base with peer-reviewed research, keeping models aligned with emerging evidence.
Public sector & hospital collaborations
Consulting, training, strategy
Contributions to public sector projects, hospital collaborations and biotech initiatives — helping governments, hospitals and health organizations turn fragmented biomedical data into decision-ready systems.
Meloom
Supporter & advisor
A lifelong interest in music led to helping nurture Meloom, a company taking music learning to a higher level and supporting health and wellbeing.
Ecosystem & collaborations
04 / Thinking
GAUGE
Granularity And Uncertainty Gating of Evidence
How I decide what a project can and cannot claim.
Most failures in biomedical data work aren't modelling failures. They happen earlier, when a question is never defined precisely enough for any answer to be valid — and nobody notices until a model is deployed, a trial reads out, or a report reaches a clinician who acts on it.
GAUGE is the protocol I built to catch that: a sequence of decisions made before data is collected, with explicit criteria at each step — what exactly is being estimated, for which intervention, in which population, measured where, and which questions the available data genuinely cannot answer. Each gate returns a verdict. Projects advance only when every condition holds, not when most of them do.
Decides what to measure
Every project adds to it: definitions negotiated with the clinicians who own the outcome, failure modes found in real registries, constraints that only appear in practice.
Decides what the measurement can support
Versioned and fed by published evidence, including studies that contradict it — a framework that can't be wrong isn't a framework.
Finds structure at scale
It does what it's good at, at a scale no person can. What it doesn't do is tell you which variable to act on — separating those two questions is most of the work.
The result is a method that is both efficient and transparent: efficient because projects that can't succeed are stopped early rather than late, transparent because every recommendation carries its evidence level and its assumptions, in writing.
“Saying what the data cannot answer is usually the most valuable thing I deliver.”
Academic engagement
Selected contributions to interdisciplinary teaching and scientific exchange.
- A Multiomics Revolution in Medicine Through AI and Machine LearningLecturer · 10th International Conference on the Historical Links between Spain and the AmericasCCNY Division of Interdisciplinary Studies · Center for Worker EducationApril–May 2025View source
- Consideraciones Éticas en la Adopción de Inteligencia Artificial en SaludSpeaker · Biomedical SeminarUniversity of Zaragoza · Faculty of Medicine6 May 2025View source
- Tech FabLab Sprint — BiotechnologyAcademic and innovation participationInstituto Aragonés de FomentoView source
Longer-form writing lives on Medium.
05 / Contact
Extend diagnostic capability beyond conventional limits.
Available for consulting, speaking and institutional collaboration acrossbiotechnology, AI and precision medicine.