Alzheimer's disease (AD) lacks effective disease-modifying therapies and scalable, ecologically valid biomarkers to monitor treatment response. Transcranial pulse stimulation (TPS) is an emerging non-invasive neuromodulation technique with potential to attenuate cognitive decline. Sensitive digital endpoints are needed to quantify intervention-related changes.
Objective
To develop and validate connected-speech–derived digital biomarkers as a longitudinal framework for monitoring TPS treatment response in AD.
Methods
In this open-label, single-arm pilot study, 32 patients with AD were compared to cognitively healthy controls. A three-stage framework was implemented: (1) machine-learning classification using linguistic features to derive a parsimonious biomarker panel; (2) construction of a Speech Composite Index (SCI) calibrated against the CERAD total score (CTS); and (3) longitudinal SCI tracking in a sub-cohort receiving TPS.
Results
The classifier discriminated AD from controls with an AUROC of 0.879 and an F1-score of 0.825. The SCI showed strong convergent validity with global cognition (CTS: r = 0.76, p < 0.001; MMSE: r = 0.76, p < 0.001) and executive function (Stroop interference: r = −0.51, p = 0.015). Longitudinal modeling demonstrated a significant positive deviation from a CERAD-based progression reference (β_time = 0.057 z-units/month, p = 0.013), indicating relative stabilization of speech performance. Individual trajectories were heterogeneous (range −0.053 to +0.336) without significant demographic associations.
Conclusions
Connected-speech–derived digital biomarkers can serve as scalable longitudinal endpoints for neuromodulatory interventions in AD. The SCI captures treatment-related dynamics and may support response stratification. Further validation in larger, sham-controlled multicenter studies is needed to establish clinical utility and specificity to TPS.
BatemanRJXiongCBenzingerTLS, et al.Clinical and biomarker changes in dominantly inherited Alzheimer’s disease. N Engl J Med2012; 367: 795–804.
5.
VillemagneVLBurnhamSBourgeatP, et al.Amyloid β deposition, neurodegeneration, and cognitive decline in sporadic Alzheimer’s disease: a prospective cohort study. Lancet Neurol2013; 12: 357–367.
6.
SelkoeDJHardyJ. The amyloid hypothesis of Alzheimer’s disease at 25 years. EMBO Mol Med2016; 8: 595–608.
7.
MorrisJCHeymanAMohsRC, et al.The Consortium to Establish a Registry for Alzheimer’s Disease (CERAD). Part I. Clinical and neuropsychological assessment of Alzheimer’s disease. Neurology1989; 39: 1159–1165.
8.
BreijyehZKaramanR. Comprehensive review on Alzheimer’s disease: causes and treatment. Molecules2020; 25: 5789.
9.
CummingsJLeeGNahedP, et al.Alzheimer’s disease drug development pipeline: 2022. Alzheimers Dement (N Y2022; 8: e12295.
10.
SchottJMAisenPSCummingsJL, et al.Unsuccessful trials of therapies for Alzheimer’s disease. Lancet2019; 393: 29.
11.
KnopmanDSJonesDTGreiciusMD. Failure to demonstrate efficacy of aducanumab: an analysis of the EMERGE and ENGAGE trials as reported by Biogen, December 2019. Alzheimers Dement2021; 17: 696–701.
12.
Van DyckCHSwansonCJAisenP, et al.Lecanemab in early Alzheimer’s disease. N Engl J Med2023; 388: 9–21.
13.
LiXJiMZhangH, et al.Non-drug therapies for Alzheimer’s disease: a review. Neurol Ther2023; 12: 39–72.
14.
PolaníaRNitscheMARuffCC. Studying and modifying brain function with non-invasive brain stimulation. Nat Neurosci2018; 21: 174–187.
15.
DarmaniGBergmannTOPaulyKB, et al.Non-invasive transcranial ultrasound stimulation for neuromodulation. Clin Neurophysiol2022; 135: 51–73.
16.
MartinERobertsMGrigorasIF, et al.Ultrasound system for precise neuromodulation of human deep brain circuits. Nat Commun2025; 16: 8024.
17.
NielsenMBSøgaardSBBech AndersenS, et al.Highlights of the development in ultrasound during the last 70 years: a historical review. Acta Radiol2021; 62: 1499–1514.
18.
BlackmoreJShrivastavaSSalletJ, et al.Ultrasound neuromodulation: a review of results, mechanisms and safety. Ultrasound Med Biol2019; 45: 1509–1536.
19.
PasquinelliCHansonLGSiebnerHR, et al.Safety of transcranial focused ultrasound stimulation: a systematic review of the state of knowledge from both human and animal studies. Brain Stimul2019; 12: 1367–1380.
20.
FomenkoANeudorferCDallapiazzaRF, et al.Low-intensity ultrasound neuromodulation: an overview of mechanisms and emerging human applications. Brain Stimul2018; 11: 1209–1217.
21.
MattEMitterwallnerMRadjenovicS, et al. Ultrasound neuromodulation with transcranial pulse stimulation in Alzheimer disease: a randomized clinical trial. JAMA Netw Open2025; 8: e2459170.
22.
PolteSKlingmannLSeßmannA, et al. Neuromodulatory effects of transcranial pulse stimulation (TPS) in neurological and psychiatric disorders: a systematic review and meta-analysis. Neurol Int2025; 17: 188.
23.
HoHCChenWSHsiaoMY. Neuromodulation effects of low-intensity transcranial focused ultrasound in human, a systematic review focusing on motor and sensory functions. J Neuroeng Rehabil2025; 22: 254.
MattERadjenovicSMitterwallnerM, et al.Current state of clinical ultrasound neuromodulation. Front Neurosci2024; 18: 1420255.
26.
TruongDQThomasCHampsteadBM, et al.Comparison of transcranial focused ultrasound and transcranial pulse stimulation for neuromodulation: a computational study. Neuromodulation2022; 25: 606–613.
27.
BeisteinerRMattEFanC, et al.Transcranial pulse stimulation with ultrasound in Alzheimer’s disease—a new navigated focal brain therapy. Adv Sci (Weinh)2019; 7: 1902583.
28.
EhrenspergerMMBerresMTaylorKI, et al.Early detection of Alzheimer’s disease with a total score of the German CERAD. J Int Neuropsychol Soc2010; 16: 910–920.
29.
ContCStuteNGalliA, et al.Retrospective real-world pilot data on transcranial pulse stimulation in mild to severe Alzheimer’s patients. Front Neurol2022; 13: 948204.
30.
MattEDörlGBeisteinerR. Transcranial pulse stimulation (TPS) improves depression in AD patients on state-of-the-art treatment. Alzheimers Dement (N Y)2022; 8: e12245.
31.
PopescuTPernetCBeisteinerR. Transcranial ultrasound pulse stimulation reduces cortical atrophy in Alzheimer’s patients: a follow-up study. Alzheimers Dement (N Y)2021; 7: e12121.
32.
DörlGMattEBeisteinerR. Functional specificity of TPS brain stimulation effects in patients with Alzheimer’s disease: a follow-up fMRI analysis. Neurol Ther2022; 11: 1391–1398.
33.
ChenXYouJMaH, et al.Transcranial pulse stimulation in Alzheimer’s disease. CNS Neurosci Ther2024; 30: e14372.
34.
WojteckiLContCStuteN, et al.Electrical brain networks before and after transcranial pulsed shockwave stimulation in Alzheimer’s patients. Geroscience2025; 47: 953–964.
35.
GianlorencoACCamargoLYehHJ, et al.Neuromodulation in Parkinson’s disease with transcranial pulse stimulation: evidence of clinical efficacy and cortical oscillatory changes. J Neurol2026; 273: 52.
36.
ManganottiPLiccariMLombardoTMI, et al.Effects of transcranial pulse stimulation (TPS) as a potential “add-on” intervention in patients with Parkinson’s disease. Parkinsonism Relat Disord2026; 142: 108128.
37.
SpoonerDMPachanaNA. Ecological validity in neuropsychological assessment: a case for greater consideration in research with neurologically intact populations. Arch Clin Neuropsychol2006; 21: 327–337.
38.
KueperJKSpeechleyMMontero-OdassoM. The Alzheimer’s Disease Assessment Scale–Cognitive Subscale (ADAS-Cog): modifications and responsiveness in pre-dementia populations: a narrative review. J Alzheimers Dis2018; 63: 423–444.
39.
CalamiaMMarkonKTranelD. Scoring higher the second time around: meta-analyses of practice effects in neuropsychological assessment. Clin Neuropsychol2012; 26: 543–570.
40.
DuehringJAJacobsDMThomasML, et al.Implications of practice effects for the design of Alzheimer clinical trials. Alzheimers Dement (N Y)2025; 11: e70154.
41.
CohenSCummingsJKnoxS, et al.Clinical trial endpoints and their clinical meaningfulness in early stages of Alzheimer’s disease. J Prev Alzheimers Dis2022; 9: 507–522.
42.
DagumP. Digital biomarkers of cognitive function. NPJ Digit Med2018; 1: 10.
43.
KourtisLCRegeleOBWrightJM, et al.Digital biomarkers for Alzheimer’s disease: the mobile/wearable devices opportunity. NPJ Digit Med2019; 2: 9.
44.
GumusMKooMStudzinskiCM, et al.Linguistic changes in neurodegenerative diseases relate to clinical symptoms. Front Neurol2024; 15: 1373341.
45.
CaoFVogelAPGharahkhaniP, et al.Speech and language biomarkers for Parkinson’s disease prediction, early diagnosis and progression. NPJ Parkinsons Dis2025; 11: 57.
46.
De la Fuente GarciaSRitchieCWLuzS. Artificial intelligence, speech, and language processing approaches to monitoring Alzheimer’s disease: a systematic review. J Alzheimers Dis2020; 78: 1547–1574.
47.
DingKXiaWZhangS, et al.Speech-based detection of Alzheimer’s disease: a survey of methods, challenges, and clinical potential. Artif Intell Rev2024; 57: 325.
48.
ShankarRBundeleAMukhopadhyayA. A systematic review of natural language processing techniques for early detection of cognitive impairment. Mayo Clin Proc Digit Health2025; 3: 100205.
49.
AhmedSHaighAMFDe JagerCA, et al.Connected speech as a marker of disease progression in autopsy-proven Alzheimer’s disease. Brain2013; 136: 3727–3737.
50.
BoschiVCatricalàEConsonniM, et al.Connected speech in neurodegenerative language disorders: a review. Front Psychol2017; 8: 269.
51.
MuellerKDHermannBMecollariJ, et al.Connected speech and language in mild cognitive impairment and Alzheimer’s disease: a review of picture description tasks. J Clin Exp Neuropsychol2018; 40: 917–939.
52.
LuzSHaiderFDe la FuenteS, et al.Detecting cognitive decline using speech only: the ADReSSo challenge. In: Proceedings of Interspeech 2021, Brno, Czechia, 30 August–3 September 2021, pp.3780–3784.
53.
HartsuikerRBarkhuysenP. Language production and working memory: the case of subject–verb agreement. Lang Cogn Process2006; 21: 181–204.
54.
BarbeauEJDidicMJoubertS, et al.Extent and neural basis of semantic memory impairment in mild cognitive impairment. J Alzheimers Dis2012; 30: 645–657.
55.
HsuCW, et al.Revisiting human language and speech production network: a meta-analytic connectivity modeling study. Neuroimage2025; 306: 121008.
56.
HumphreysGFLambon RalphMA. Mapping the task-general and task-specific neural correlates of speech production: meta-analysis and fMRI direct comparisons of category fluency and picture naming. Imaging Neurosci2025; 3: e10042.
57.
CuetosFArango-LasprillaJCUribeC, et al.Linguistic changes in verbal expression: a preclinical marker of Alzheimer’s disease. J Int Neuropsychol Soc2007; 13: 433–439.
58.
PakhomovSVSChaconDWicklundM, et al.Computerized assessment of syntactic complexity in Alzheimer’s disease: a case-study of Iris Murdoch’s writing. Behav Res Methods2011; 43: 136–144.
59.
BerishaVWangSLaCrossA, et al.Tracking discourse complexity preceding Alzheimer’s disease diagnosis: a case study of President Ronald Reagan. J Alzheimers Dis2015; 45: 1107–1113.
60.
EyigozEMathurSSantamariaM, et al.Linguistic markers predict onset of Alzheimer’s disease. eClinicalMed2020; 28: 100583.
61.
SnowdonDAGreinerLHKemperSJ, et al.Linguistic ability in early life and cognitive function and Alzheimer’s disease in late life: findings from the Nun Study. JAMA1996; 275: 528–532.
62.
ClarkeKMEtemadmoghadamSDannerB, et al.The Nun Study: insights from 30 years of aging and dementia research. Alzheimers Dement2025; 21: e14626.
63.
European Medicines Agency. Questions and answers: qualification of digital technology-based methodologies to support approval of medicinal products. Report no. EMA/219860/2020, 1 June 2020. Amsterdam: European Medicines Agency.
64.
Martínez-NicolásILlorenteTEMartínez-SánchezF, et al.Ten years of research on automatic voice and speech analysis of people with Alzheimer’s disease and mild cognitive impairment: a systematic review article. Front Psychol2021; 12: 620251.
65.
Deutsche Gesellschaft für Neurologie, Deutsche Gesellschaft für Psychiatrie und Psychotherapie, Psychosomatik und Nervenheilkunde, et al. S3-Leitlinie, Demenzen“ (Langversion, Januar 2016). AWMF-Registernummer 038-013. Report, Arbeitsgemeinschaft der Wissenschaftlichen Medizinischen Fachgesellschaften, Germany, January 2016.
66.
ChandlerMJLacritzLHHynanLS, et al.A total score for the CERAD neuropsychological battery. Neurology2005; 65: 102–106.
67.
FolsteinMFFolsteinSEMcHughPR. “Mini-mental state”: a practical method for grading the cognitive state of patients for the clinician. J Psychiatr Res1975; 12: 189–198.
68.
StroopJR. Studies of interference in serial verbal reactions. J Exp Psychol1935; 18: 643–662.
69.
Cont-RichterCStuteNGalliA, et al.Transcranial pulse stimulation in Alzheimer’s: long-term feasibility and a multifocal treatment approach. Brain Sci2025; 15: 830.
70.
LanziAMSaylorAKFrommD, et al.Dementiabank: theoretical rationale, protocol, and illustrative analyses. Am J Speech Lang Pathol2023; 32: 426–438.
NicholasLEBrookshireRH. A system for quantifying the informativeness and efficiency of the connected speech of adults. J Speech Hear Res1993; 36: 338–350.
73.
RockwellN. Going and coming [oil on canvas]. Indianapolis, IN: Norman Rockwell Art Collection Trust, 1947.
74.
GrimesN. Walt Disney’s Cinderella. New York: Random House, 2005.
75.
RadfordAKimJWXuT, et al.Robust speech recognition via large-scale weak supervision. In: Proceedings of the 40th International Conference on Machine Learning, Honolulu, HI, USA, 23–29 July 2023, pp.28492–28518: PMLR.
76.
BuechelSRückerSHahnU. Learning and evaluating emotion lexicons for 91 languages. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, online, 5–10 July 2020, pp.1202–1217. Stroudsburg, PA: Association for Computational Linguistics.
77.
SchmidtkeDSSchröderTJacobsAM, et al.ANGST: affective norms for German sentiment terms, derived from the affective norms for English words. Behav Res Methods2014; 46: 1108–1118.
78.
RemusRQuasthoffUHeyerG. SentiWS – a publicly available German-language resource for sentiment analysis. In: Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC 2010), Valletta, Malta, 17–23 May 2010. European Language Resources Association.
79.
SimpragaSAlvarez-JimenezRMansvelderHD, et al.EEG Machine learning for accurate detection of cholinergic intervention and Alzheimer’s disease. Sci Rep2017; 7: 5775.
80.
LiZMirjahanmardiSHSaliR, et al.Automated cell annotation and classification on histopathology for spatial biomarker discovery. Nat Commun2025; 16: 6240.
81.
TibshiraniR. Regression shrinkage and selection via the lasso. J R Stat Soc Series B Methodol1996; 58: 267–288.
82.
ZouHHastieT. Regularization and variable selection via the elastic net. J R Stat Soc Series B Stat Methodol2005; 67: 301–320.
83.
MeinshausenNBühlmannP. Stability selection. J R Stat Soc Series B Stat Methodol2010; 72: 417–473.
84.
BreimanLFriedmanJHOlshenRA, et al.Classification and regression trees. Belmont, CA: Wadsworth International Group, 1984.
85.
HastieTTibshiraniRFriedmanJ. The elements of statistical learning: data mining, inference, and prediction. 2nd ed. New York: Springer, 2009.
86.
BeyeneHBGilesCHuynhK, et al.Metabolic phenotyping of BMI to characterize cardiometabolic risk: evidence from large population-based cohorts. Nat Commun2023; 14: 6280.
87.
HelgasonHEiriksdottirTUlfarssonMO, et al.Evaluation of large-scale proteomics for prediction of cardiovascular events. JAMA2023; 330: 725–735.
88.
RossettiHCLacritzLHCullumCM, et al.The CERAD Neuropsychological Battery Total Score and the progression of Alzheimer disease. Alzheimer Dis Assoc Disord2010; 24: 138–142.
89.
VirtanenPGommersROliphantTE, et al.Scipy 1.0: fundamental algorithms for scientific computing in Python. Nat Methods2020; 17: 261–272.
90.
LundbergSMLeeSI. A unified approach to interpreting model predictions. In: GuyonILuxburgUVBengioS, et al. (eds) Advances in neural information processing systems 30. Red Hook, NY: Curran Associates, Inc., 2017, pp.4765–4774.
91.
LundbergSMErionGChenH, et al.From local explanations to global understanding with explainable AI for trees. Nat Mach Intell2020; 2: 252–259.
BerishaVLissJM. Responsible development of clinical speech AI: bridging the gap between clinical research and technology. NPJ Digit Med2024; 7: 208.
94.
SeeleyWWCrawfordRKZhouJ, et al.Neurodegenerative diseases target large-scale human brain networks. Neuron2009; 62: 42–52.
95.
BucknerRLSepulcreJTalukdarT, et al.Cortical hubs revealed by intrinsic functional connectivity: mapping, assessment of stability, and relation to Alzheimer’s disease. J Neurosci2009; 29: 1860–1873.
96.
AgostaFGalantucciSFilippiM. Advanced magnetic resonance imaging of neurodegenerative diseases. Brain Connect2015; 5: 307–333.
97.
PereiraJBMijalkovMKakaeiE, et al.Disrupted network topology in patients with stable and progressive mild cognitive impairment and Alzheimer’s disease. Cereb Cortex2018; 28: 1993–2006.
98.
RuszJKrackPTripolitiE. From prodromal stages to clinical trials: the promise of digital speech biomarkers in Parkinson’s disease. Neurosci Biobehav Rev2024; 167: 105922.
99.
QiWZhuXWangB, et al.Alzheimer’s disease digital biomarkers multidimensional landscape and AI model scoping review. NPJ Digit Med2025; 8: 366.
100.
LiLMUeharaKHanakawaT. The contribution of interindividual factors to variability of response in transcranial direct current stimulation studies. Front Cell Neurosci2015; 9: 181.
101.
VergallitoAFeroldiSPisoniA, et al.Inter-individual variability in tDCS effects: a narrative review on the contribution of stable, variable, and contextual factors. Brain Sci2022; 12: 522.
102.
ChenHLiMQinZ, et al.Functional network connectivity patterns predicting the efficacy of repetitive transcranial magnetic stimulation in the spectrum of Alzheimer’s disease. Eur Radiol Exp2023; 7: 63.
Supplementary Material
Please find the following supplemental material available below.
For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.
For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.
