Federated learning is an upcoming machine learning paradigm which allows data from multiple sources to be used for training of classifiers without the data leaving the source it originally resides. This can be highly valuable for use cases such as medical research, where gathering data at a central location can be quite complicated due to privacy and legal concerns of the data. In such cases, federated learning has the potential to vastly speed up the research cycle. Although federated and central learning have been compared from a theoretical perspective, an extensive experimental comparison of performances and learning behavior still lacks. We have performed a comprehensive experimental comparison between federated and centralized learning. We evaluated various classifiers on various datasets exploring influences of different sample distributions as well as different class distributions across the clients. The results show similar performances under a wide variety of settings between the federated and central learning strategies. Federated learning is able to deal with various imbalances in the data distributions. It is sensitive to batch effects between different datasets when they coincide with location, similar to central learning, but this setting might go unobserved more easily. Federated learning seems to be robust to various challenges such as skewed data distributions, high data dimensionality, multiclass problems, and complex models. Taken together, the insights from our comparison gives much promise for applying federated learning as an alternative to sharing data. Code for reproducing the results in this work can be found at: https://github.com/swiergarst/FLComparison.

Background and ObjectivesIdentifying genetic causes of dementia in patients visiting memory clinics is important for patient care and family planning. Traditional clinical selection criteria for genetic testing may miss carriers of pathogenic variants in dementia-related genes. This study aimed identify how many carriers we are missing and to optimize criteria for selecting patients for genetic counseling in memory clinics.MethodsIn this clinical cohort study, we retrospectively genetically tested patients during 2.5 years (2010-2012) visiting the Alzheimer Center Amsterdam, a specialized memory clinic. Genetic tests consisted of a 54-gene dementia panel, focusing on Class IV/V variants per American College of Medical Genetics and Genomics guidelines, including APP duplications and the C9ORF72 repeat expansion. We determined the prevalence of pathogenic variants and propose new eligibility criteria for genetic testing in memory clinics. The eligibility criteria were prospectively applied for 1 year (2021-2022), and results were compared with the retrospective cohort.ResultsGenetic tests were retrospectively performed in in 1,022 of 1,138 patients (90%) who consecutively visited the memory clinic. Among these, 1,022 patients analyzed (mean age 62.1 ± 8.9 years; 40.4% were female), 34 pathogenic variant carriers were identified (3.3%), with 24 being symptomatic. Previous clinical criteria would have identified only 15 carriers (44% of all carriers, 65% of symptomatic carriers). The proposed criteria increased identification to 22 carriers (62.5% of all carriers, 91% of symptomatic carriers). In the prospective cohort, 148 (28.7%) of 515 patients were eligible for testing under the new criteria. Of the 90 eligible patients who consented to testing, 13 pathogenic carriers were identified, representing a 73% increase compared with the previous criteria.DiscussionWe found that patients who visit a memory clinic and carry a pathogenic genetic variant are often not eligible for genetic testing. The proposed new criteria improve the identification of patients with a genetic cause for their cognitive complaints. In systems without practical or financial barriers to genetic testing, the new criteria can enhance personalized care. In other countries where the health care systems differs and in other genetic ancestry groups, the performance of the criteria may be different.

Federated learning is a technique that enables the use of distributed datasets for machine learning purposes without requiring data to be pooled, thereby better preserving privacy and ownership of the data. While supervised FL research has grown substantially over the last years, unsupervised FL methods remain scarce. This work introduces an algorithm which implements K-means clustering in a federated manner, addressing the challenges of varying number of clusters between centers, as well as convergence on less separable datasets.

Introduction
The field of forensic DNA analysis has undergone rapid advancements in recent decades. The integration of massively parallel sequencing (MPS) has notably expanded the forensic toolkit, moving beyond identity matching to predicting phenotypic traits and biogeographical ancestry. This shift is of particular significance in cases where conventional DNA profiling fails to identify a single suspect. Supplementing forensic analyses with estimated biological age may be valuable but involves a complex and time-consuming DNA methylation analysis. This study explores and validates the performance of a comprehensive forensic third-generation sequencing assay utilizing Oxford Nanopore Technologies (ONT) in an adaptive and direct sequencing approach. We incorporated the most widely used forensic markers, i.e., STRs, SNPs, InDels, mitochondrial DNA (mtDNA), and two methylation-based clock classifiers, thereby combining forensic genetic and epigenetic analysis in one single workflow.

Methods and results
In our investigation, DNA from six anonymous individuals was sequenced using the ONT standard adaptive direct sequencing approach, reaching a mean percentage of on-target reads ranging from 6.6 % to 7.7 % per sample. ONT data was compared to standard MPS data and Illumina EPIC DNA methylation profiles. Basecalling employed recommended ONT software packages. TREAT was used for ONT-based analysis of autosomal and Y-chromosome STRs, achieving 90–92 % correct calls depending on allelic read depth thresholds. InDel analyses for two lower-quality samples proved challenging due to inadequate read depth, while the remaining four samples significantly contributed to the observed percentage markers (60.9 %) and correct calls (97.8 %). SNP analysis achieved a 98 % call rate, with only two mismatches and two missed alleles. ONT-generated DNA methylation data demonstrated Pearson’s correlation coefficients with EPIC data ranging from 0.67 to 0.97 for Horvath’s clock. Additional age-associated markers exhibited Pearson’s correlation coefficients with chronological age between 0.14 (ELOVL2) and 0.96 (FHL2) at read depths of <30 and <20, respectively. Despite excluding mtDNA from our targeted sequencing approach, adaptive proof-reading fragments covered the complete mtDNA with an average read depth of 21–72, showing 100 % concordance with reference data.

Discussion
Our exploratory study using ONT adaptive sequencing for conventional forensic and age associated DNA methylation markers showed high sequencing accuracy for a significant number of markers, showcasing ONT as a promising (epi)genetic forensic method. Future studies must address three critical aspects: determining clear quantity and quality measures and detection thresholds for accuracy, optimizing input DNA quantity for forensic casework expectations, and addressing ethical considerations associated with phenotype and ancestry analysis to prevent ethnic biases.

Background: Despite several randomised controlled trials (RCTs) on the use of adjuvant treatment with corticosteroids in patients with community-acquired pneumonia (CAP), the effect of this intervention on mortality remains controversial. We aimed to evaluate heterogeneity of treatment effect (HTE) of adjuvant treatment with corticosteroids on 30-day mortality in patients with CAP. Methods: In this individual patient data meta-analysis, we included RCTs published before July 1, 2024, comparing adjuvant treatment with corticosteroids versus placebo in patients hospitalised with CAP. The primary endpoint was 30-day all-cause mortality, collected across all trials, and analyses followed the intention-to-treat principle. We analysed HTE using risk and effect modelling. For risk modelling, patients were classified as having less severe or severe CAP based on the pneumonia severity index (PSI), comparing PSI class I–III versus class IV–V. For effect modelling, we trained a corticosteroid-effect model on six trials and externally validated it using data from two trials, received after model preregistration. This model classified patients into two groups: no predicted benefit and predicted benefit from adjuvant treatment with corticosteroids. The literature search was registered on PROSPERO, CRD42022380746. Findings: We included eight RCTs with 3224 patients. Across all eight trials, 246 (7·6%) patients died within 30 days (106 [6·6%] of 1618 in the corticosteroid group vs 140 [8·7%] of 1606 in the placebo group; odds ratio [OR] 0·72 [95% CI 0·56–0·94], p=0·017). The corticosteroid-effect model, which selected C-reactive protein (CRP), showed significant HTE during external validation in the two most recent trials. In these trials, 154 (11·4%) of 1355 patients died within 30 days (88 [13·1%] of 671 in the placebo group vs 66 [9·6%] of 684 in the corticosteroid group; OR 0·71 [95% CI 0·50–0·99], p=0·044). Among patients predicted to have no benefit (CRP ≤204 mg/L, n=725), no significant effect was observed (OR 0·98 [95% CI 0·63–1·50]), whereas for those with predicted benefit (CRP >204 mg/L, n=630), 39 (13·0%) of 301 patients died in the placebo group compared with 20 (6·1%) of 329 in the corticosteroid group (0·43 [0·25–0·76], p_interaction=0·026). No significant HTE was found between less severe CAP (PSI class I–III, n=229) and severe CAP (PSI class IV–V, n=1126). Corticosteroid therapy significantly increased hyperglycaemia risk (44 [12·8%] of 344 in the placebo group vs 84 [24·8%] of 339 in the corticosteroid group; OR 2·50 [95% CI 1·63–3·83], p<0·0001) and hospital re-admission risk (30 [3·7%] of 814 in the placebo group vs 57 [7·0%] of 819 in the corticosteroid group; 1·95 [1·24–3·07], p=0·0038). Interpretation: Overall, adjuvant therapy with corticosteroids significantly reduces 30-day mortality in patients hospitalised with CAP. The treatment effect varied significantly among subgroups based on CRP concentrations, with a substantial mortality reduction observed only in patients with high baseline CRP. Funding: None.

While deep learning (DL) is used in patients’ outcome predictions, the insufficiency of patient samples limits the accuracy. In this study, we investigated how transfer learning (TL) alleviates the small sample size problem. A 2-step TL framework was constructed for a difficult task: predicting the response of the drug temozolomide (TMZ) in glioblastoma (GBM) cell cultures. The GBM is aggressive, and most patients do not benefit from the only approved chemotherapeutic agent TMZ. O6-methylguanine-DNA methyltransferase (MGMT) promoter methylation status is the only biomarker for TMZ responsiveness but has shown limited predictive power. The 2-step TL framework was built on 3 datasets: (1) the subset of the Genomics of Drug Sensitivity in Cancer (GDSC) dataset, including miscellaneous cell cultures treated by TMZ, cyclophosphamide, bortezomib, and oxaliplatin, as the source dataset; (2) the Human Glioblastoma Cell Culture (HGCC) dataset, for fine-tuning; and (3) a small target dataset GSE232173, for validation. The latter two included specifically TMZ-treated GBM cell cultures. The DL models were pretrained on the cell cultures treated by each of the 4 drugs from GDSC, respectively. Then, the DL models were refined on HGCC, where the best source drug was identified. Finally, the DL model was validated on GSE232173. Using 2-step TL with pretraining on oxaliplatin was not only superior to those without TL and with 1-step TL but also better than 3 benchmark methods, including MGMT. The oxaliplatin-based TL improved the performance probably by increasing the weights of cell cycle-related genes, which relates to the TMZ response processes. Our findings support the potential of oxaliplatin being an alternative therapy for patients with GBM and TL facilitating drug repurposing research. We recommend that following our methodology, using mixed cancers and a related drug as the source and then fine-tuning the model with the target cancer and the target drug will enhance drug response prediction.

We appreciate the opportunity to further clarify our findings in response to the insightful comments from Shota Yamamoto and colleagues and Luis Felipe Reyes and Ignacio Martin-Loeches regarding our recent community-acquired pneumonia (CAP) study. [...]

Objective: To assess the feasibility of scalable, objective, and minimally invasive liquid biopsy-derived biomarkers such as cell-free DNA copy number profiles, human epididymis protein 4 (HE4), and cancer antigen 125 (CA125) for pre-operative risk assessment of early-stage ovarian cancer in a clinically representative and diagnostically challenging population and to compare the performance of these biomarkers with the Risk of Malignancy Index (RMI). Methods: In this case-control study, we included 100 patients with an ovarian mass clinically suspected to be early-stage ovarian cancer. Of these 100 patients, 50 were confirmed to have a malignant mass (cases) and 50 had a benign mass (controls). Using WisecondorX, an algorithm used extensively in non-invasive prenatal testing, we calculated the benign-calibrated copy number profile abnormality score. This score represents how different a sample is from benign controls based on copy number profiles. We combined this score with HE4 serum concentration to separate cases and controls. Results: Combining the benign-calibrated copy number profile abnormality score with HE4, we obtained a model with a significantly higher sensitivity (42% vs 0%; p<0.002) at 99% specificity as compared with the RMI that is currently employed in clinical practice. Investigating performance in subgroups, we observed especially large differences in the advanced stage and non-high-grade serous ovarian cancer groups. Conclusion: This study demonstrates that cell-free DNA can be successfully employed to perform pre-operative risk of malignancy assessment for ovarian masses; however, results warrant validation in a more extensive clinical study.

Most regulatory elements, especially enhancer sequences, are cell population-specific. One could even argue that a distinct set of regulatory elements is what defines a cell population. However, discovering which non-coding regions of the DNA are essential in which context, and as a result, which genes are expressed, is a difficult task. Some computational models tackle this problem by predicting gene expression directly from the genomic sequence. These models are currently limited to predicting bulk measurements and mainly make tissue-specific predictions. Here, we present a model that leverages single-cell RNA-sequencing data to predict gene expression. We show that cell population-specific models outperform tissue-specific models, especially when the expression profile of a cell population and the corresponding tissue are dissimilar. Further, we show that our model can prioritize GWAS variants and learn motifs of transcription factor binding sites. We envision that our model can be useful for delineating cell population-specific regulatory elements.

Subtyping of acute myeloid leukaemia (AML) is predominantly based on recurrent genetic abnormalities, but recent literature indicates that transcriptomic phenotyping holds immense potential to further refine AML classification. Here we integrated five AML transcriptomic datasets with corresponding genetic information to provide an overview (n = 1224) of the transcriptomic AML landscape. Consensus clustering identified 17 robust patient clusters which improved identification of CEBPA-mutated patients with favourable outcomes, and uncovered transcriptomic subtypes for KMT2A rearrangements (2), NPM1 mutations (5), and AML with myelodysplasia-related changes (AML-MRC) (5). Transcriptomic subtypes of KMT2A, NPM1 and AML-MRC showed distinct mutational profiles, cell type differentiation arrests and immune properties, suggesting differences in underlying disease biology. Moreover, our transcriptomic clusters show differences in ex-vivo drug responses, even when corrected for differentiation arrest and superiorly capture differences in drug response compared to genetic classification. In conclusion, our findings underscore the importance of transcriptomics in AML subtyping and offer a basis for future research and personalised treatment strategies. Our transcriptomic compendium is publicly available and we supply an R package to project clusters to new transcriptomic studies.

Molecular effects of lifestyle interventions are typically studied in a single tissue. Here, we perform a secondary analysis on the sex-specific effects of the Growing Old TOgether trial (GOTO, trial registration number GOT NL3301 (https://onderzoekmetmensen.nl/nl/trial/27183), NL-OMON27183, primary outcomes have been previously reported in ref. 1), a moderate 13-week combined lifestyle intervention on the transcriptomes of postprandial blood, subcutaneous adipose tissue (SAT) and muscle tissue in healthy older adults, the overlap in effect between tissues and their relation to whole-body parameters of metabolic health. The GOTO intervention has virtually no effect on the postprandial blood transcriptome, while the SAT and muscle transcriptomes respond significantly. In SAT, pathways involved in HDL remodeling, O2/CO2 exchange and signaling are overrepresented, while in muscle, collagen and extracellular matrix pathways are significantly overexpressed. Additionally, we find that the effects of the SAT transcriptome closest associates with gains in metabolic health. Lastly, in males, we identify a shared variation between the transcriptomes of the three tissues. We conclude that the GOTO intervention has a significant effect on metabolic and muscle fibre pathways in the SAT and muscle transcriptome, respectively. Aligning the response in the three tissues revealed a blood transcriptome component which may act as an integrated health marker for metabolic intervention effects across tissues.

Cardiovascular disease (CVD) is the most important cause of morbidity and mortality worldwide. Early detection, prevention or even prediction is of pivotal importance to reduce the burden of cardiovascular disease and its associated costs. Low cost, consumer-grade smartwatches have the potential to revolutionize cardiovascular medicine by enabling continuous monitoring of heart rate and activity. When combined with machine learning(ML), the resulting large amounts of time series data hold the potential of detection, or exclusion of CVD. However, analyzing such large datasets is challenging due to the sparse presence of informative segments. Efficient selection of these segments is essential for developing predictive models for clinical deployment. The objective of this paper was to investigate the potential of an acceleration-deceleration curvebased ML model as a novel clinical indicator for the detection of cardiovascular diseases. We used data from the ME-TIME study; 42 participants from which 21 have a cardiovascular disease and 21 are health controls. Data from each subject was normalized to decrease inter-subject variability. A neural network model aggregated predictions per week. We showed that per-subject normalization by the peak value of curves during inactivity, aggregation of model predictions over a week, and using a contrastive loss, resulted in a predictive model with 99 % ± 3 % specificity and 40 % ± 49 % sensitivity on the development set, and 100 % specificity with 67 % ± 47 % sensitivity on the test set. Acceleration-deceleration curves are effective patterns for ruling out the presence of cardiovascular disease, but caution must be taken to properly pre-process the curves and carefully choosing a model that reduces the variability in the extracted curves.

Introduction
Unraveling how Alzheimer's disease (AD) genetic risk is related to neuropathological heterogeneity, and whether this occurs through specific biological pathways, is a key step toward precision medicine.

Methods
We computed pathway-specific genetic risk scores (GRSs) in non-demented individuals and investigated how AD risk variants predict cerebrospinal fluid (CSF) and imaging biomarkers reflecting AD pathology, cardiovascular, white matter integrity, and brain connectivity.

Results
CSF amyloidbeta and phosphorylated tau were related to most GRSs. Inflammatory pathways were associated with cerebrovascular disease, whereas quantitative measures of white matter lesion and microstructure integrity were predicted by clearance and migration pathways. Functional connectivity alterations were related to genetic variants involved in signal transduction and synaptic communication.

Discussion
This study reveals distinct genetic risk profiles in association with specific pathophysiological aspects in predementia stages of AD, unraveling the biological substrates of the heterogeneity of AD-associated endophenotypes and promoting a step forward in disease understanding and development of personalized therapies.

Highlights
- Polygenic risk for Alzheimer's disease encompasses six biological pathways that can be quantified with pathway-specific genetic risk scores, and differentially relate to cerebrospinal fluid and imaging biomarkers.
- Inflammatory pathways are mostly related to cerebrovascular burden.
- White matter health is associated with pathways of clearance and membrane integrity, whereas functional connectivity measures are related to signal transduction and synaptic communication pathways.

Anomaly detection in time series data is crucial across various domains. The scarcity of labeled data for such tasks has increased the attention towards unsupervised learning methods. These approaches, often relying solely on reconstruction error, typically fail to detect subtle anomalies in complex datasets. To address this, we introduce RESTAD, an adaptation of the Transformer model by incorporating a layer of Radial Basis Function (RBF) neurons within its architecture. This layer fits a non-parametric density in the latent representation, such that a high RBF output indicates similarity with predominantly normal training data. RESTAD integrates the RBF similarity scores with the reconstruction errors to increase sensitivity to anomalies. Our empirical evaluations demonstrate that RESTAD outperforms various established baselines across multiple benchmark datasets.

Biological age uses biophysiological information to capture a person’s age-related risk of adverse outcomes. MetaboAge and MetaboHealth are metabolomics-based biomarkers of biological age trained on chronological age and mortality risk, respectively. Lifestyle factors contribute to the extent chronological and biological age differ. The association of lifestyle factors with MetaboAge and MetaboHealth, potential sex differences in these associations, and MetaboAge’s and MetaboHealth’s sensitivity to lifestyle changes have not been studied yet.

Linear regression analyses and mixed-effect models were used to examine the cross-sectional and longitudinal associations of scaled lifestyle factors with scaled MetaboAge and MetaboHealth in 24,332 middle-aged participants from the Doetinchem Cohort Study, Rotterdam Study, and UK Biobank. Random-effect meta-analyses were performed across cohorts. Repeated metabolomics measurements had a ten-year interval in the Doetinchem Cohort Study and a five-year interval in the UK Biobank.

In the first study incorporating longitudinal information on MetaboAge and MetaboHealth, we demonstrate associations between current smoking, sleeping ≥8 hours/day, higher BMI, and larger waist circumference were associated with higher MetaboHealth, the latter two also with higher MetaboAge. Furthermore, adhering to the dietary and physical activity guidelines were inversely associated with MetaboHealth. Lastly, we observed sex differences in the associations between alcohol use and MetaboHealth.

Multi-omic analyses are necessary to understand the complex biological processes taking place at the tissue and cell level, but also to make reliable predictions about, for example, disease outcome. Several linear methods exist that create a joint embedding using paired information per sample, but recently there has been a rise in the popularity of neural architectures that embed paired -omics into the same non-linear manifold. This work describes a head-to-head comparison of linear and non-linear joint embedding methods using both bulk and single-cell multi-modal datasets. We found that non-linear methods have a clear advantage with respect to linear ones for missing modality imputation. Performance comparisons in the downstream tasks of survival analysis for bulk tumor data and cell type classification for single-cell data lead to the following insights: First, concatenating the principal components of each modality is a competitive baseline and hard to beat if all modalities are available at test time. However, if we only have one modality available at test time, training a predictive model on the joint space of that modality can lead to performance improvements with respect to just using the unimodal principal components. Second, -omic profiles imputed by neural joint embedding methods are realistic enough to be used by a classifier trained on real data with limited performance drops. Taken together, our comparisons give hints to which joint embedding to use for which downstream task. Overall, product-of-experts performed well in most tasks and was reasonably fast, while early integration (concatenation) of modalities did quite poorly.

Photoplethysmography (PPG) signals, typically acquired from wearable devices, hold significant potential for continuous fitness-health monitoring. In particular, heart conditions that manifest in rare and subtle deviating heart patterns may be interesting. However, robust and reliable anomaly detection within these data remains a challenge due to the scarcity of labeled data and high inter-subject variability. This paper introduces a two-stage framework leveraging representation learning and personalization to improve anomaly detection performance in PPG data. The proposed framework first employs representation learning to transform the original PPG signals into a more discriminative and compact representation. We then apply three different unsupervised anomaly detection methods for movement detection and biometric identification. We validate our approach using two different datasets in both generalized and personalized scenarios. Our results demonstrate significant improvements: for movement detection, in the generalized scenario, AUCs improved from barely 0.5 to above 0.9 with representation learning. Importantly, inter-subject variability was substantially reduced, from around 0.4 to below 0.1. In the personalized scenario, AUCs became close to 1.0, with variability further reduced to below 0.05, indicating the effectiveness of both representation learning and personalization for anomaly detection in PPG data. Similar enhancements were observed in biometric identification, emphasizing how our approach can minimize inter-subject variability and enhance PPG-based health monitoring systems.

Background
Genome-Wide Association Studies (GWAS) have identified 86 SNPs associated with Alzheimer’s disease (AD). GWAS-SNPs are markers of genetic variation in linkage disequilibrium (LD), which may drive the association with AD. One major class of genetic variation are Structural Variants (SVs), which can regulate transcription and translation of nearby genes. Here, we explored the interplay between large SVs (>50 bp) and AD-associated SNPs.

Method
We performed long-read whole-genome sequencing of 214 individuals representing the extreme ends of the cognitive spectrum: N = 93 AD patients (age 67.2∓8.5), and N = 121 cognitively healthy centenarians (age 101.2∓1.8). We identified SVs using sniffles2 genome-wide, further characterised them through (local) de novo assembly, and annotated tandem repeats (TR) and transposable elements (TE). Next, we estimated LD between SVs and 86 AD-associated GWAS-SNPs, Finally, we compared SNP frequencies and SV sizes between AD cases and centenarians using logistic regression models.

Result
Across all 214 individuals, we found >27,404 SVs (>50 bp), with a Minor Allele Frequency (MAF) ≥ 5%. Most SVs were TRs (63%), followed by TEs (37%). We found that 37 AD GWAS-SNPs paired with 90 SVs in low to strong LD (R2 > 0.1), 56 of which involved SNP-TR pairs (62%) and 34 involved SNP-TE pairs (38%). In six AD loci, the SVs associated more strongly with AD risk than the leading GWAS-SNP (p < 0.05). This includes ADAM10, CTSH, SLC2A4RG, CD2AP, SPI1, and IDUA, which were encompassed by complex haplotypes harbouring multiple TRs and TEs.

Conclusion
Our findings provide the first support for SVs as candidate-drivers of the association between respective GWAS loci with AD risk. Hence, SVs may lead to increased effect sizes.

BACKGROUND: Alzheimer's disease (AD) prevalence increases with age, yet a small fraction of the population reaches ages > 100 years without cognitive decline. We studied the genetic factors associated with such resilience against AD. METHODS: Genome-wide association studies identified 86 single nucleotide polymorphisms (SNPs) associated with AD risk. We estimated SNP frequency in 2281 AD cases, 3165 age-matched controls, and 346 cognitively healthy centenarians. We calculated a polygenic risk score (PRS) for each individual and investigated the functional properties of SNPs enriched/depleted in centenarians. RESULTS: Cognitively healthy centenarians were enriched with the protective alleles of the SNPs associated with AD risk. The protective effect concentrated on the alleles in/near ANKH, GRN, TMEM106B, SORT1, PLCG2, RIN3, and APOE genes. This translated to >5-fold lower PRS in centenarians compared to AD cases (P = 7.69 × 10⁻⁷¹), and 2-fold lower compared to age-matched controls (P = 5.83 × 10⁻¹⁷). DISCUSSION: Maintaining cognitive health until extreme ages requires complex genetic protection against AD, which concentrates on the genes associated with the endolysosomal and immune systems. Highlights: Cognitively healthy cent enarians are enriched with the protective alleles of genetic variants associated with Alzheimer's disease (AD). The protective effect is concentrated on variants involved in the immune and endolysosomal systems. Combining variants into a polygenic risk score (PRS) translated to > 5-fold lower PRS in centenarians compared to AD cases, and ≈ 2-fold lower compared to middle-aged healthy controls.