Ho Nhat Minh Nguyen

National Economics University

Unclaimed · AI-structured profileOpenAlex

ML researcher at National Economics University spanning clinical perioperative prediction and computational toxicology.

papers here

reviewed by Evolve

first-author

corresponding

—

works · OpenAlex

—

h-index · OpenAlex

Bibliometric figures come from OpenAlex (2026-10-08) and cover the author's entire public record, not just the papers listed here. Reproducibility signal comes from Evolve's own reviews.

Research profile

Output—

Not yet scored: this profile has no aggregate publication count, venue record, or cumulative output volume in the provided data. The axis would measure the scale of research production and how it is distributed across years and publication venues.

Impact—

Not yet scored: no citation counts, h-index-style indicators, or usage signals are available in the provided data. This axis would measure how far the two cataloged 2026 preprints are cited, reused, or taken up by subsequent research.

Focus0/100

The focus score is currently 0, driven by an even 50/50 field distribution across the two cataloged 2026 papers: clinical machine learning / perioperative medicine (0.5) and machine learning for drug discovery / computational toxicology (0.5). With only two arXiv papers on record, research concentration cannot yet be meaningfully assessed; the shared methodological thread of multimodal fusion and leakage-aware evaluation is the main connective tissue between the two areas.

Collaboration48/100

Collaboration scores 48, based on 10 distinct coauthors across the two cataloged papers. The recurring core group is Quang Minh Nguyen, Duc Minh Le, Thuy Quynh Nguyen, Trong Nghia Nguyen, and Thanh Long Dai Doan. Nguyen holds a middle author position and is not the corresponding author on either paper, consistent with a technical contributor role within a small, stable team rather than an independent leading one.

Activity—

Not yet scored: the provided data includes no publication cadence or year-by-year volume beyond two 2026 preprints. This axis would measure recent research tempo — outputs per year and the consistency of publishing activity over time.

Reproducibility38/100

Reproducibility scores 38, computed as the mean readiness rating across 2 papers. The SMILESGNN toxicity paper is rated medium, while the leakage-aware intraoperative AKI framework is rated low, with Evolve's review flagging thin statistics (5 folds, 180 events). Overall readiness is early-stage; released code, data pipelines, and larger event counts would be the natural levers to raise it.

Research summary

Ho Nhat Minh Nguyen is, at this early-stage profile, a machine learning researcher affiliated with National Economics University whose reviewed work spans two application domains in equal measure: clinical machine learning for perioperative medicine and machine learning for drug discovery / computational toxicology. The Evolve catalog currently holds two 2026 arXiv papers, on both of which Nguyen appears as a middle author rather than first or corresponding author. The first, SMILESGNN, couples a SMILES Transformer with a GATv2 graph network through cross-attention for clinical toxicity prediction; Evolve's review notes the graph branch brings no accuracy gain over the sequence-only baseline, leaving the contribution in qualitative interpretability, with medium reproducibility readiness. The second proposes a leakage-aware multimodal evaluation framework for early intraoperative acute kidney injury prediction on VitalDB, arguing that waveform-only models are insufficient and stacked multimodal ensembles perform best, though the review flags thin statistics (5 folds, 180 events) and rates reproducibility readiness low. Radar indicators place collaboration at 48 (10 distinct coauthors), reproducibility at 38 (mean across 2 papers), and focus at 0, reflecting the even 50/50 split between the two fields; output, impact, and activity metrics are not yet available. The recurring co-author group includes Quang Minh Nguyen, Duc Minh Le, Thuy Quynh Nguyen, Trong Nghia Nguyen, and Thanh Long Dai Doan.

Collaboration pattern

Nguyen works within a compact, recurring co-author group — Quang Minh Nguyen, Duc Minh Le, Thuy Quynh Nguyen, Trong Nghia Nguyen, and Thanh Long Dai Doan — with 10 distinct coauthors across the two cataloged 2026 papers. On both papers Nguyen holds a middle author position and is not the corresponding author, consistent with a technical contributor role in team projects rather than an independent research lead; the collaboration score of 48 reflects this moderate, team-embedded pattern.

Research keywords

drug toxicity predictionmultimodal fusioncross-attentiongraph neural networkGATv2SMILES Transformeracute kidney injurypostoperative predictionintraoperative vital signsVitalDBstacked ensemblingleakage-aware evaluation

Highlights

Interpretable toxicity prediction by fusing SMILES Transformers with graph attention
The 2026 SMILESGNN paper combines a SMILES Transformer with a GATv2 graph network via cross-attention for clinical toxicity prediction. Evolve's review finds the fusion shows no accuracy gain over the sequence-only model, so the practical value rests on qualitative interpretability; reproducibility readiness is rated medium.
Leakage-aware evaluation for intraoperative AKI prediction on VitalDB
A 2026 framework argues that leakage-aware evaluation shows waveform-only models are insufficient for early intraoperative acute kidney injury prediction, with stacked multimodal ensembles performing best. Evolve's review cautions that the supporting statistics are thin — 5 folds and 180 events — and rates reproducibility readiness low.

Timeline

2026SMILESGNN appears on arXiv: interpretable clinical toxicity prediction fusing SMILES and graph representations via cross-attention; middle authorship, medium reproducibility readiness.
2026A leakage-aware multimodal evaluation framework for early intraoperative acute kidney injury prediction on VitalDB appears on arXiv; middle authorship, low reproducibility readiness.
2026Both cataloged papers land in the same year, splitting output evenly between perioperative clinical ML and computational toxicology, with 10 distinct coauthors involved.

Papers in the Evolve catalog

Frequent co-authors

Quang Minh Nguyen×1 Duc Minh Le×1 Ho Nhat Minh Nguyen×1 Thuy Quynh Nguyen×1 Trong Nghia Nguyen×1 Quang Minh Nguyen×1 Thuy Quynh Nguyen×1 Duc Minh Le×1 Thanh Long Dai Doan×1 Trong Nghia Nguyen×1

About this profile

This profile is AI-structured by Evolve.Pub from public bibliographic data (OpenAlex) and Evolve's own paper reviews. It is not written or endorsed by the researcher unless the profile is claimed. Radar dimensions are computed from real bibliometrics with fixed formulas — raw figures are shown alongside; missing dimensions mean insufficient data, never zero. Errors? Claim the profile to correct or hide it.

Bibliometric dimensions and the field distribution are computed by Evolve from a limited public bibliometric snapshot; only two 2026 arXiv papers are in scope.
Output, impact, and activity lack underlying data (no citation counts, publication totals, or multi-year cadence), so these dimensions are left unscored rather than estimated.
No ORCID or country field is provided, and the name is a common Vietnamese-style name, so this profile is name-resolved from public bibliographic data and could merge or miss records.
Both reviewed papers are arXiv preprints with middle authorship and no corresponding role; peer-review status and per-author contributions are outside the provided data.