Alzheimer disease (AD) is a neurodegenerative condition involving an insidious decline of semantic and episodic memory alongside other functions [1]. Its current prevalence, of 55 million, will likely triple by 2050, with cases increasing by 116% in high-income countries and 250% in low- or middle-income countries [2-4]. This underscores the need for noninvasive, scalable markers that facilitate disease detection and monitoring [5]. Automated speech and language analysis (ASLA) meets these requisites [6-8].

In ASLA studies, patients and healthy controls (HCs) are simply required to speak, be it through spontaneous (eg, memory description), semispontaneous (eg, picture description), or nonspontaneous (eg, paragraph reading) tasks [9]. Thereupon, their recordings and transcripts can be digitally analyzed to identify disease-sensitive features [10,11]. This approach has been leveraged to detect early-stage cases [6,8,12], support differential diagnosis [7], predict dementia onset [6], and capture cognitive decline [13] and brain atrophy patterns [14,15]. As ASLA also reduces testing time and costs, it represents a promising framework to foster global equity in dementia assessments [16]. However, such potential remains unmet, as most studies target features with low interpretability and tests of between-language generalizability are incipient [16,17]. This casts doubts on the approach’s clinical utility and cross-linguistic validity.

Interpretability is often undermined by 2 analytical strategies. One involves targeting heterogeneous feature sets that mix domains known to be affected (eg, semantics) and often spared (eg, morphosyntax) in AD [8,18,19]. The other relies on black-box models (eg, transformers) operating on hidden layers without clinical significance—eg, deep learning models such as BERT (Bidirectional Encoder Representations from Transformers) or Wav2vec (Meta), which produce high-dimensional representations that do not correspond to well-defined linguistic or acoustic constructs [20,21]. Both strategies yield variable outcomes that cannot be readily integrated with core clinical knowledge about AD, reducing the framework’s translational potential.

Moreover, over 40% of ASLA research on AD targets English speakers [22]. This is highly inequitable, as English is spoken by less than 20% of the world’s population [16] and AD is most prevalent in non-Anglophone countries [2-5]. Importantly, several language domains can be affected by this disease in English speakers and spared in users of other languages [22]. Thus, not all ASLA results from English-speaking cohorts may generalize well to other language groups.

Promisingly, recent developments allow the circumvention of both issues. Robust, interpretable results have been obtained in ASLA studies targeting (1) speech timing features (eg, pause duration) as proxies of lexical search effort [23-26]; and (2) lexico-semantic features, including word class features (proportion of different lexical categories) [27-29], semantic granularity (conceptual precision when naming entities) [7,30], and semantic variability (conceptual distance across successive words) [30]. Such features can reveal distinct processing demands and strategies in AD, potentially yielding maximal results when combined than when framed in isolation [8,31].

Also, these features can be tested for cross-cultural validity by training classifiers with data from English-speaking participants and testing them on users of a different language, as recently proposed [22] and preliminarily attempted in promising studies and challenges [32-34]. In particular, a 0-shot approach, involving no cross-linguistic calibration or transfer, creates highly stringent, unbiased conditions for this examination. Conceivably, cross-linguistic generalizability could be higher for speech timing features (as word retrieval effort should increase in AD irrespective of the language) than for lexico-semantic features (which vary widely between English and other languages) [35,36]. As proposed elsewhere, such features are interpretable because they reflect dysfunctions of semantic memory, a core system affected in early disease stages. This allows results to be understood in relation to well-established neuropsychological models of AD [4,5].

Against this background, we examined whether interpretable ASLA features yield cross-linguistic AD markers. Using speech timing and lexico-semantic features from a validated task [17,19,24], we first trained classifiers with English-speaking patients and HCs, and then tested them in a within-language and a between-language setting (with English and Spanish speakers as testing folds, respectively). In each case, we ran separate classifiers for timing features, lexico-semantic features, and their combination. Finally, we explored whether the most sensitive features in each setting could predict patients’ cognitive decline, indexed through the Mini-Mental State Examination (MMSE) [37]. Relative to current literature [38-40], our approach is unique in its integration of clinically motivated acoustic and linguistic features with unimodal and fusion-based classifiers for 0-shot within- and between-language classification and severity prediction. Adding novelty, our design involves Latino individuals, a large, underserved population with a high prevalence of AD [41,42].

For the within-language setting, we hypothesized that interpretable features would enable patient identification in both modalities, with the best outcomes resulting from their combination. For the between-language setting, we anticipated better cross-linguistic generalization for timing than for lexico-semantic features. Finally, considering recent findings [43,44], we anticipated that the most discriminatory features in each setting would reliably predict patients’ MMSE scores. By testing these hypotheses, we seek to further ASLA research on AD with a translational, cross-cultural ethos.

This study used interpretable ASLA features to identify persons with AD in within- and between-language settings. Trained on data from English speakers, our models detected English-speaking patients through timing and lexico-semantic features (especially when combined), with timing features yielding the best prediction of MMSE scores. Conversely, testing on Spanish speakers showed that only speech timing features were useful for identifying patients and capturing their MMSE scores. These findings inform the quest for clinically relevant and cross-linguistically valid ASLA features, as discussed below.

Within-language classification reached AUC values of 0.79 and 0.80 when based on speech timing and lexico-semantic features, respectively. These classification scores resemble those of other acoustic [17,24,33] and linguistic [18,64,88] studies while meeting the requirements of interpretability. As proposed in previous AD research, longer pauses and syllables likely reflect reduced word retrieval efficiency [89]. Extended silences and phonated segments are typically observed when intended words are not easily retrieved, either because they are not optimally entrenched in memory or because reduced contextual awareness complicates decisions among other lexical candidates. Compatibly, the observed lexico-semantic alterations replicate previous findings from AD research [7,30]. These include high semantic variability and low semantic granularity, pointing to greater variance in conceptual proximity across words and reduced conceptual precision [7,30]. Such patterns also seem absent in other neurodegenerative disorders [7,30], highlighting their role as distinct candidate markers of AD.

Of note, joint analysis of both dimensions yielded an AUC of 0.88, corroborating that within-language AD detection is higher for multimodal (acoustic plus linguistic) than unimodal (eg, linguistic only) ASLA approaches [8,31]. Importantly, these results approximate others derived from uninterpretable audio- and text-level embeddings (eg, Wav2vec and transformer-based models such as BERT) [60,90], suggesting that focus on interpretable ASLA features does not entail a loss of sensitivity. Briefly, the integration of strategic acoustic and linguistic features can optimize AD identification while illuminating patients’ cognitive dysfunctions.

Further, timing features successfully captured patients’ MMSE scores in the within-language setting. This replicates previous works based on timing and other audio-derived features [88,91,92], underscoring the importance of speech rhythm as a candidate marker of the disorder [93]. Specific speech dimensions, then, seem related to overall cognitive status in AD—a promising finding given the vast intra- and interindividual cognitive heterogeneity across patients [94].

Additional insights were obtained through between-language analyses. Identification of AD patients was significantly better for timing features (AUC=0.75) than for lexico-semantic or fusion features (AUCs<0.65). Accordingly, we propose that low word retrieval efficiency (captured by timing metrics) would represent a general cognitive trait of AD, affecting verbal production irrespective of the patient’s language. Indeed, this dimension has enabled AD detection in separate studies targeting languages as diverse as English, Spanish, and Mandarin Chinese [25,95-97]. Conversely, lower cross-linguistic generalization for lexico-semantic patterns would follow from the vast vocabulary differences across typologically distant languages [35,36]. Indeed, specific linguistic patterns may exhibit different and even opposite alterations in AD depending on the patients’ language—for example, pronouns are overused by English-speaking patients and underused by patients who speak Bengali, a language with a more complex pronoun system [16]. Importantly, features yielding moderate AUCs can still support clinical decision-making when interpretability and generalizability are prioritized [98]. Briefly, timing features seem to outperform lexico-semantic features as potential cross-linguistically valid markers of AD.

The poor cross-linguistic performance of lexico-semantic features invites reflection for further research. First, weak classification and MMSE prediction results may reflect the inadequacy of the specific features we used rather than an overarching futility of lexico-semantic measures for between-language studies. In fact, it might even be that these very features do generalize robustly between other (eg, typologically close) language pairs. Further, beyond our study’s goals, cross-linguistic generalizability might be enhanced through alternative strategies, including transfer learning and model training with data from multiple languages [99].

This notion is reinforced by MMSE estimation results. In the between-language setting, MMSE scores were captured by timing features, but not by the lexico-semantic or fusion models. Compatibly, a model trained on silence features and acoustic embeddings from English-speaking patients with AD and HCs yielded good prediction of MMSE scores in a Greek-speaking sample [33]. Thus, speech timing features emerge as promising candidates not only for identifying patients but also for estimating symptom severity across typologically different languages.

Note that our approach cannot ascertain the cause of observed anomalies. In particular, speech timing anomalies may certainly reflect cognitive deficits, but they may also reflect motor speech dysfunction. While motor deficits are rarely reported in AD, they may be present in several cases [100], inviting new studies integrating relevant measures for patient stratification or covariance analysis. The same analytical approaches could be used with strategic measures (eg, picture naming response times) to test the conjecture that speech timing metrics reflect lexical retrieval effort.

Our results bear clinical implications. First, the features used here, as opposed to scores from black-box models, may enhance patient phenotyping and therapeutic decision-making. Indeed, they can be linked to specific cognitive dysfunctions that practitioners are well versed in. Second, they indicate that some, but not all, findings from Anglophone samples may be useful for assessing AD in other Indo-European language communities. The point is important because of the overrepresentation of English in ASLA studies [16,46] and the tendency to derive language-agnostic conclusions from the Pitt Corpus (the English-language dataset used here, which has been leveraged by numerous studies) [17,19,32,44,46] and wide-ranging research challenges [17]. Third, our approach rests entirely on automated methods, increasing cost-efficiency and scalability while minimizing the potential for human error. In this sense, our pipeline has been deployed in a recent version of the Toolkit to Examine Lifelike Language, a speech testing app used in several clinics worldwide [11,101,102]. This allows for its widespread implementation in actual screening, diagnostic, and monitoring scenarios—a key milestone for bridging the gap between basic research and real-world applications.

Yet, our work is not without limitations. First, the 2 datasets we used differed in terms of acquisition conditions. Although we included gold-standard audio normalization steps ensuring comparability, it would be useful to replicate our approach with harmonized cross-linguistic protocols. Second, AD in the English dataset was established before the release of contemporary diagnostic criteria. Although we chose patients with AD-consistent MMSE scores and ensured their sociodemographic matching with same-language controls as well as Spanish-speaking groups, future works should replicate our approach with Anglophone cohorts fulfilling NINCDS-ADRDA criteria or other validated standards. Third, we acknowledge that the limited sample size, especially in the Spanish cohort, restricts statistical power and constrains our capacity to rigorously assess model generalization. Future works should aim for substantially larger groups and include models trained with Spanish speakers and tested on English speakers—thus illuminating their potential for bidirectional generalizability while enabling alternative analytical approaches, based on cross-linguistic calibration or transfer. Fourth, while we controlled for sociodemographic variables, and participants’ dialects were consistent within language groups, our datasets lacked data on education quality, cultural communication norms, and other factors influencing speech production. Future studies should be strategically designed to tackle these factors.

Fifth, we lacked data on when and how examiners intervened during participants’ descriptions. While all examiners’ segments were removed, future works should contemplate the potential impact of this factor. Sixth, our cross-sectional design reveals features that are sensitive to patients’ current cognitive status, but moot on their clinical trajectories. Longitudinal datasets should be leveraged to examine whether these features can predict AD progression. Seventh, though vital for enhancing VAD and downstream processing [7,17], denoising in our preprocessing pipeline might have introduced speech artifacts. These were mitigated through manual revision of all processed audio files and careful tuning of the algorithm’s threshold parameters to minimize unintended distortions. Yet, future studies with more controlled acoustic conditions (eg, in recording booths) could replicate our approach without applying denoising. Eighth, while our 0-shot framework provides insights into the cross-linguistic generalizability of interpretable features, we recognize that performance could likely be improved through few-shot learning strategies, particularly if small amounts of target-language data are available [16,17]. Prior studies leveraging embeddings have demonstrated such gains [32], though often at the cost of transparency. Future research should explore hybrid approaches that incorporate limited target-language samples to enhance model robustness while preserving clinical interpretability.

Finally, note that we aimed to examine whether a model trained in 1 language can generalize to another using interpretable features. Thus, we avoided multilingual large language models or Wav2vec-style embeddings due to their lack of clinical interpretability. Likewise, we did not aim to train a model with interpretable features from both languages, as this would have hindered insights into cross-linguistic generalizability. Such strategies could be leveraged in further research with different goals. Here, evidence that an English-only model can be applied to a lower-resource language helps in understanding which mainstream (English-based) results might hold promise for global speech and language frameworks. Thus, future works should compare our target features with embedding-based features to establish whether interpretability involves a trade-off with sensitivity.

In sum, this study reveals 2 novel empirical patterns for ASLA research on dementia. Interpretable timing and lexico-semantic features support AD detection and cognitive decline estimation among English speakers, but only timing features generalize well from English to Spanish speakers. This suggests that timing features are more language-agnostic than lexico-semantic features. Further work can aid the search for cross-linguistic and language-specific ASLA markers of brain health.