SEARCH · Search PubMed

Results for “bimodal large language model”

Search indexed PubMed citations on genomics, clinical trials, systematic reviews and public health. Explore titles, authors and supplied subject terms, then open the PubMed record.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

907 recordsLinked to original sources

PubMed2026

A bimodal large language model reduces misalignment in patient education: A double-blinded randomized trial.

BACKGROUND: Effective patient education requires accurate communication aligned with patients' emotional and semantical needs. Text-based large language models (LLMs) lack access to non-verbal cues, which may contribute to misaligned responses. METHODS: We evaluated emotional and semantic misalignment in a text-based LLM using 64,200 utterances from 16,583 patient education cases across six departments and three centers. Dolphin was developed integrating text and audio cues and evaluated through emotion recognition, semantic consistency assessment, branch-level ablations, and a double-blinded randomized trial against a matched text-based LLM comparator (Chinese Clinical Trial Registry: (ChiCTR2500095933). FINDINGS: The text-based LLM showed emotional misalignment in 36.7% of responses and semantic misalignment in 28.3% of cases, with higher misalignment under greater burden. Dolphin outperformed the text-based LLM in emotion recognition accuracy (0.886 vs. 0.713) and semantic consistency (84.9% vs. 82.1%; both adjusted p < 0.001). Ablations supported contribution of audio branches. Dolphin received higher expert ratings than the text-based LLM and human educators (all p < 0.001). In 555 patients, Dolphin was associated with greater patient satisfaction (98.6% vs. 93.8%), suggestion acceptance (76.1% vs. 58.9%; p < 0.001), proactive disclosure (44.6% vs. 26.5%; p < 0.001), and fewer 7-day unplanned recontact (12.9% vs. 22.9%; p = 0.002). No unsafe recommendations or safety events were identified. CONCLUSIONS: Compared with text-based LLM, Dolphin improved emotional-semantic alignment and patient-education outcomes, supporting bimodal alignment as a strategy for reducing misalignment-driven communication failures. FUNDING: National Natural Science Foundation of China, State Key Laboratory Special Fund, and Chinese Academy of Medical Sciences Innovation Fund.

Humans↗

PubMed2026

The landscape of pruning for large language models: A systematic review and unified taxonomy.

Confronting the inherent tension between the exceptional capabilities and the immense computational costs of Large Language Models (LLMs), pruning has become a crucial technique for achieving efficient deployment. However, a systematic analytical framework dedicated specifically to LLM pruning remains absent. In this paper, we aim to bridge this gap. We first elucidate the theoretical foundations that underpin the effectiveness of pruning, namely overparameterization and redundancy, and then propose a multidimensional taxonomy that organizes existing approaches along the axes of granularity, timing, and criteria. Building upon this unified perspective, we further analyze performance recovery mechanisms and the broader evaluation ecosystem, while also exploring forward-looking challenges such as interpretability, automation, and hardware-algorithm co-design. Through this comprehensive synthesis, we seek to provide an integrated and coherent analytical lens for advancing both research and practice in LLM pruning.

Large Language Models↗

PubMed2026

Evaluation of a cornea-specialized large language model for diagnostic and management accuracy in complex corneal cases.

PURPOSE: To evaluate whether a cornea-specialized large language model (LLM) enhanced with retrieval-augmented generation (RAG) improves clinicians' diagnostic and management accuracy in complex corneal cases compared to a general-purpose GPT-4o model and unaided clinician performance. METHODS: This prospective, randomized, masked evaluation study involved three cornea trainees who each independently reviewed 39 real-world corneal cases under three experimental conditions: unaided, GPT-4o-assisted, and assisted by a cornea-specialized GPT-4o model. The cornea-specialized model was constructed by embedding over 200 publicly available Wikipedia articles into GPT-4o's RAG framework. Participants provided open-ended diagnoses and selected the next-step management options (multiple choice). They were allowed up to three GPT-4o queries per case, and the AI-assisted arms were randomized to minimize bias. Accuracy for both tasks was compared against expert reference standards using McNemar's test. RESULTS: Diagnostic accuracy was 48.7%, 20.5%, and 38.5% unaided, improving to 69.2%, 46.2%, and 59.0% with general GPT-4o (p<0.04). The cornea-specialized GPT-4o further improved accuracy to 71.8%, 48.7%, and 74.4%, with improvements over unaided performance for all clinicians (p<0.01). For next-step decisions, unaided accuracy was 76.9%, 87.2%, and 59.0%. With the specialized model, Ophthalmologist 3 improved to 71.8% (p<0.05), Ophthalmologist 1 remained high at 82.1%, and Ophthalmologist 2 declined to 64.1% (p<0.05). CONCLUSIONS: A cornea-specialized LLM enhanced with RAG improved diagnostic accuracy in complex corneal cases, particularly among clinicians with lower baseline performance. Effects on management accuracy were inconsistent. Future studies should explore the use of open-ended management tasks and examine whether smaller, curated retrieval corpora yield better model performance.

Humans↗

PubMed2026

Can ChatGPT Replace Human Clinical Coders? A Comparative Study in Otology Billing.

OBJECTIVE: Evaluate the utility of the large language model (LLM), ChatGPT, for the analysis of operative notes and the generation of Current Procedural Terminology (CPT) codes in comparison to human clinical coders. STUDY DESIGN: CPT billing codes assigned by ChatGPT were compared to existing billing data. Otology practice within a tertiary academic center. METHODS: About 191 operative notes from a single surgeon (9/2022-10/2023) were analyzed. ChatGPT-3.5 and 4 models were prompted for CPT codes based on operative notes. Assessment included determining exact and partial match rates, sensitivity and specificity for targeted procedures, and work Relative Value Units (wRVU) differences between ChatGPT-generated and human-assigned codes. RESULTS: ChatGPT-3.5 achieved exact matches in 22% of cases and partial matches in 32%, while ChatGPT-4 achieved 14% exact and 33% partial matches. When cochlear implantation (CI) was excluded, performance dropped significantly. For CI, ChatGPT-3.5 demonstrated a sensitivity of 94% and specificity of 90%, while ChatGPT-4 showed a sensitivity of 96% and specificity of 92%. In contrast, performance on cartilage grafting was poor, with sensitivities of 4.2% for ChatGPT-3.5 and 0% for ChatGPT-4. ChatGPT-3.5 and 4 showed moderate CPT code matching accuracy among themselves, with slight agreement to human coders. Both models tended to underbill for wRVUs compared to human coders, with significant differences in the values generated. CONCLUSION: This study assessed ChatGPT's effectiveness in automating CPT code assignment for otologic surgeries. While the models achieved high sensitivity values for assigning codes related to cochlear implantation, both models struggled with complex cases, failed to apply modifiers, and often assigned fewer wRVUs. The findings highlight ChatGPT's potential in medical billing but indicate a need for further refinement.

Humans↗

PubMed2026

Pedagogical Efficacy of LLM-Generated Synthetic Data Versus Real-World Clinical Records: A Randomized Controlled Non-Inferiority Trial.

BACKGROUND: Expert-reviewed clinical cases generated by large language models (LLMs) may supplement case resources in medical education, but their short-term educational performance relative to real-case-derived teaching materials remains uncertain. We compared immediate post-training test performance after teaching with the two types of case materials and assessed non-inferiority against a prespecified margin. METHODS: We conducted a prospective, parallel-group, randomized non-inferiority trial. Through the Wenjuanxing online platform, participants were randomized 1:1 to learn with either real-case-derived teaching cases compiled by clinicians and reviewed by experts or AI-generated clinical cases produced by Gemini 3.0 Pro from fully de-identified matched real cases and reviewed by three senior general surgery specialists with full-professor rank. The primary outcome was the total score on an independent 10-item immediate post-training test (0-10 points), with a prespecified non-inferiority margin of -0.5 points. Secondary outcomes included the training-phase performance score, learning efficiency index, single-item mental effort rating, case realism, and case-source judgment. RESULTS: A total of 403 participants were randomized, of whom 386 were included in the modified intention-to-treat analysis: 192 in the real-case group and 194 in the AI-generated case group. The mean post-training test score was 4.95 (SD, 3.35) in the real-case group and 4.61 (SD, 3.35) in the AI-generated case group. The mean difference (AI-generated minus real-case group) was -0.335 points (95% CI, -1.006 to 0.337). Because the lower bound of the confidence interval was below the prespecified non-inferiority margin of -0.5 points, non-inferiority was not demonstrated (one-sided P = 0.314). No significant between-group differences were observed in the training-phase performance score, learning efficiency index, or single-item mental effort rating. AI-generated cases received lower realism ratings for Level 3 cases. The proportion of participants with at least one high-confidence completely incorrect response was 1.6% in the real-case group and 2.1% in the AI-generated case group. CONCLUSIONS: In this short-term, text-based online case-learning setting, no statistically significant between-group difference was observed in immediate post-training test performance; however, non-inferiority of AI-generated clinical cases relative to real-case-derived teaching materials was not demonstrated.

Humans↗

PubMed2025

Respiratory-swallow coordination training using bimodal signal biofeedback for patients with post-stroke dysphagia: a randomized controlled trial.

OBJECTIVE: The purpose was to investigate the effects of respiratory-swallow coordination training with bimodal signal biofeedback on swallowing function in patients with post-stroke dysphagia. METHODS: Post-stroke dysphagia Patients were randomly assigned to either the control group or the experimental group. The control group received conventional rehabilitation, while the experimental group underwent additional respiratory-swallow coordination training based on biofeedback. The training protocol consisted of three phases, conducted at an intensity of 30 min/day, 6 days/week, for two consecutive weeks. Outcome measures included the Functional Oral Intake Scale (FOIS) score, the Rosenbek Penetration-Aspiration Scale (PAS) score, respiratory-swallow coordination, and videofluoroscopic swallowing study temporal and kinematic parameter. Assessments were conducted at baseline, post-treatment, and at a one-month follow-up. RESULTS: Thirty patients were enrolled. Both groups showed significant improvement in FOIS scores from baseline to both two-week post-treatment and one-month follow-up (p < 0.001). Compared to the controls, the experimental group demonstrated significantly greater FOIS scoreimprovement at both post-treatment and follow-up (p < 0.001). The proportion of patients with a ≥ 2-point increase in FOIS scores was significantly higher in the experimental group than in the control group at both post-treatment (p < 0.01) and one-month follow-up (p < 0.01). After two weeks of treatment, the percentage of PAS scores ≥6 was significantly lower in the experimental group than in the control group (p < 0.001). Additionally, the percentage of optimal respiratory-swallow pattern was significantly higher in the experimental group than in the control group (p < 0.001). CONCLUSION: Bimodal signal biofeedback-based respiratory-swallow coordination training can effectively improve respiratory-swallow coordination and swallowing function in patients with post-stroke dysphagia.

Humans↗

PubMed2026

Neuromodulation for Subjective Tinnitus: A Systematic Review and Meta-Analysis of Randomized Trials.

OBJECTIVE: To evaluate the effectiveness and safety of neuromodulation and bimodal stimulation for chronic subjective tinnitus in randomized controlled trials (RCTs). DATA SOURCES: PubMed/MEDLINE, Web of Science, and EMBASE (January 2015-December 2025) searched per PRISMA 2020. REVIEW METHODS: Adult RCTs (≥ 18 years) with chronic subjective tinnitus (> 3 months) assessing validated outcomes (THI, TFI, TQ) for neuromodulation/bimodal interventions vs. sham/controls. Two-stage screening, Cochrane RoB-2 risk-of-bias assessment. Random-effects meta-analyses (REML) were performed when ≥ 3 comparable trials were available; effects reported as standardized mean differences (SMD) with 95% CIs. Main Outcomes and measures included change in tinnitus severity (THI/TFI/TQ) while secondary outcomes included loudness (VAS/NRS), durability, and adverse events. RESULTS: Twenty-six RCTs (n = 1576) met criteria: tES (11; n = 372), rTMS (8; n = 432), acoustic coordinated reset (1; n = 100), vagus nerve stimulation (2; n = 90), and bimodal stimulation (4; n = 582). Meta-analysis showed a nonsignificant pooled effect for tDCS (SMD -0.36; 95% CI -0.75 to 0.02; I 2 = 51%) and rTMS (SMD -0.15; 95% CI -0.37 to 0.07; I 2 = 0%). Single-trial evidence for coordinated reset showed no advantage over broadband noise. VNS demonstrated modest benefits with safety concerns limited to implanted approaches. Bimodal stimulation yielded consistent, clinically meaningful reductions (often ≥ 10-20 points on THI/TFI), with durability up to 12 months. Adverse events were mild/transient across noninvasive modalities. CONCLUSIONS: Noninvasive neuromodulation appears safe with average benefits; among modalities, bimodal stimulation shows the most consistent and durable clinical improvements. Standardized, adequately powered RCTs with harmonized protocols and long-term follow-up are needed to refine targets and dosing.

Humans↗

PubMed2026

Comparative Bioavailability of Trimodal (CTx-1301) Versus Bimodal Dexmethylphenidate Modified-Release Formulations in Adults with Attention-Deficit/Hyperactivity Disorder: A Randomized, Single-Dose, Crossover Study.

BACKGROUND AND OBJECTIVES: Attention-deficit/hyperactivity disorder (ADHD) is a chronic neurodevelopmental disorder that often requires sustained symptom control throughout the day. Although bimodal extended-release dexmethylphenidate (d-MPH XR) formulations provide initial and intermediate drug release, they may not consistently maintain therapeutic exposure into the late afternoon and evening. Trimodal formulations with an additional delayed release component may extend drug exposure later in the day, although this remains to be established. To explore differences in pharmacokinetic (PK) profiles between trimodal (CTx-1301) and bimodal delivery of d-MPH XR, a comparative bioavailability study was conducted at the highest and lowest doses for both formulations. METHODS: In this randomized, 4-period, crossover study, adults with ADHD received single doses of CTx-1301 (50 mg and 6.25 mg) and d-MPH XR (40 mg and 5 mg). Comparative bioavailability was assessed through adjusted geometric mean ratios for exposure parameters (maximum observed plasma concentration [Cmax], area under plasma concentration-time curve to last measurable concentration [AUClast] and extrapolated to infinity [AUC0-inf]), with a prespecified bioequivalence range of 0.80 to 1.25. Secondary endpoints included partial AUCs and safety assessments. RESULTS: The study population (N = 45) was predominantly male (88.9%) and White (55.6%), with mean age of 29.6 ± 8.01 years. Adjusted geometric mean ratios comparing the primary exposure parameters (Cmax, AUClast, and AUC0-inf) for CTx-1301 versus d-MPH XR were within the bioequivalence range (0.80-1.25) at both the high and low doses. The CTx-1301-to-d-MPH XR partial AUC ratios were within the bioequivalence range from 0 to 9 hours post-dose. At later intervals (AUC9-12 and AUC12-16), adjusted geometric mean ratios exceeded the upper bioequivalence threshold, consistent with the expected contribution of the third medication release component. Dose proportionality was observed between the two CTx-1301 doses and two d-MPH XR formulations. CTx-1301 was generally well tolerated. The most commonly reported adverse events included tachycardia, insomnia, headache, nausea, and euphoric mood. The incidence of treatment-emergent adverse events was numerically lower with CTx-1301 than with d-MPH XR; however, no statistical analysis was performed. CONCLUSIONS: Key exposure parameters including Cmax, AUClast, and AUC0-inf for trimodal CTx-1301 were statistically bioequivalent to bimodal d-MPH XR. Interval‑specific PK analyses demonstrated higher exposure with CTx‑1301 during later post-dose intervals (9-16 h), consistent with the formulation's third release component. However, the clinical relevance of these PK differences requires further evaluation. CTx-1301 demonstrated dose proportionality and was well tolerated at high and low doses. REGISTRATION: ClinicalTrials.gov, NCT04138498; 19 September 2019.

Humans↗

PubMed2026

Epitranscriptomic erasers in bivalves: Evolutionary divergence and species-specific transcriptional plasticity of the ALKBH family under acute thermal stress.

The AlkB homolog (ALKBH) family of Fe(II)/α-ketoglutarate-dependent dioxygenases mediates nucleic acid demethylation, thereby governing RNA metabolism and genomic stability. Despite their pivotal roles in epitranscriptomic regulation across vertebrates, the evolutionary dynamics and functional significance of ALKBH proteins in bivalve mollusks remain largely unexplored. Here, we present a comprehensive phylogenomic analysis of 210 ALKBH genes identified across 35 bivalve species. Our analyses reveal a distinct evolutionary trajectory characterized by the lineage-specific loss of ALKBH4 and the restricted distribution of ALKBH5 to the Mytilidae family, contrasting sharply with vertebrate repertoires. Using the noble scallop (Chlamys nobilis) and Pacific oyster (Crassostrea gigas) as model systems, we demonstrate that ALKBH genes exhibit conserved spatiotemporal expression patterns, with pronounced enrichment in gonadal tissues and during metamorphic transitions, implicating these enzymes in gametogenesis and larval development. Furthermore, comparative thermal stress experiments reveal divergent transcriptional plasticity: the subtropical scallop C. nobilis mounts rapid, transient induction of ALKBH1/2/6 under heat shock, whereas the eurythermal oyster C. gigas maintains sustained ALKBH3 expression, potentially underpinning its superior thermal tolerance. Conversely, cold stress elicits bimodal regulation in C. nobilis, with ALKBH1/2 upregulation contrasting with ALKBH6/7/8 suppression. These findings illuminate the functional diversification of bivalve ALKBH genes and their potential utility as molecular biomarkers for assessing developmental competence and thermal resilience in shellfish aquaculture.

Animals↗

PubMed2026

Characterizing Caregiver-Child Interactions Through a Transactional Lens: A Baseline Analysis of a Caregiver-Implemented Intervention.

PURPOSE: This study was motivated by the transactional model of development and examined the reciprocal influences that children and caregivers have on caregiver-child interactions (CCXs) prior to a caregiver-implemented intervention. We tested whether child communication characteristics were associated with caregiver strategy use and whether these strategies, in turn, influenced children's communication to understand how caregivers and children mutually shaped the language learning environment. METHOD: Caregiver-child dyads (N = 105) were participants in a randomized controlled trial. CCXs were collected when children were approximately 30 months of age, transcribed, and coded for four caregiver language facilitation strategies and child communication variables. RESULTS: Least Absolute Shrinkage and Selection Operator regression and postselection inference indicated that child communication characteristics in CCXs were associated with both the frequency and type of strategies caregivers used. Children's overall communication acts were significantly associated with caregiver use of vocabulary strategies, whereas children's vocabulary diversity was significantly associated with caregiver use of sentence strategies. Mixed-effects logistic regression demonstrated that all four caregiver strategies significantly increased the likelihood of spontaneous lexical overlap in subsequent child turns. CONCLUSIONS: Prior to the intervention, caregivers and children reciprocally shaped the language environment. This supports a transactional perspective and warrants further consideration of reciprocal influences when assessing the impact of caregiver-implemented interventions. SUPPLEMENTAL MATERIAL: https://doi.org/10.23641/asha.32995796.

Humans↗

PubMed2026

Modulating sentence comprehension in people with aphasia through anodal tDCS: A double-blind randomized cross-over study.

This double-blind randomized cross-over study investigated the effects of perilesional anodal transcranial direct current stimulation (AtDCS) combined with speech-language therapy on sentence comprehension in eight individuals with chronic nonfluent agrammatic aphasia. The behavioral therapy consisted of an intensive comprehension treatment including drilling in sentence-to-picture matching and Mapping Therapy. Each participant underwent both the anodal tDCS and sham stimulation conditions (five received sham first followed by real stimulation, and the remaining three the reverse sequence), with each condition paired with the same behavioral treatment and separated by a four-month washout period. Stimulation was applied over the perilesional area (left BA6) for 20 min during daily 40-min therapy sessions over four consecutive weeks. Sentence comprehension was assessed with the RiComprendo battery and functional communication with the Communicative Effectiveness Index (CETI). Data were analyzed using paired t-tests, Bayesian analyses, and linear mixed-effects models to control for baseline performance and individual variability. Both stimulation conditions produced significant pre-to-post improvements in sentence comprehension, particularly for syntactically complex structures such as passives and center-embedded object relatives. However, gains were overall greater following AtDCS, as reflected in larger effect sizes, stronger Bayes factors, and a significant treatment effect in the mixed-effects models. Only the AtDCS condition yielded significant improvements in self-perceived comprehension abilities on the CETI. These findings suggest that AtDCS over perilesional cortical areas may boost the effects of traditional language therapy on sentence comprehension, supporting its feasibility and potential as an adjuvant intervention in post-stroke aphasia rehabilitation.

Humans↗

PubMed2026

Automated CEAP Classification of Venous Duplex Reports Using Multimodal Artificial Intelligence.

OBJECTIVE: To develop and internally validate a prototype multimodal artificial intelligence system for automated CEAP (Clinical, Etiological, Anatomical and Pathophysiological) classification of venous duplex ultrasound (VDUS) reports, integrating natural language processing of free-text components with computer vision analysis of hand-drawn anatomical diagrams. METHODS: Single centre retrospective observational study using routinely collected clinical data. One thousand consecutive venous duplex ultrasound reports from Cambridge University Hospitals NHS Foundation Trust, UK (July 2024 - May 2025) were labelled according to the CEAP classification, excluding the Etiological component, which could not be reliably determined from duplex reports alone. Transfer learning was applied using ClinicalBERT for text and MobileNetV3 for diagrammatic data. Clinical classes were predicted from request line text. Text- and image-based pathophysiological models were developed for four anatomical territories (Great Saphenous Vein, Small Saphenous Vein, Deep system, Perforators), combined using late fusion with probability averaging. RESULTS: The clinical CEAP model achieved accuracy of 0.91, macro-F1 of 0.82, and macro-AUC of 0.98. Pathophysiological prediction varied, with text models broadly outperforming image models. Fusion yielded heterogeneous benefits, improving SSV performance but reducing Deep system accuracy. The performance of the final pathophysiological CEAP fusion models varied across anatomical territories: accuracy ranged from 0.70-0.92 and macro-AUC from 0.80-0.92. CONCLUSION: This study demonstrates the feasibility of automated CEAP classification from VDUS reports. Despite class imbalance affecting minority class predictions, the strong discriminatory performance validates this multimodal ML model for extracting clinically meaningful information from real-world data. This approach offers potential, pending external validation, to streamline vascular services through automated triage and guideline-compliant decision making.

Artificial intelligence↗

PubMed2026

Reliability-aware hierarchical learning for Chagas disease screening from 12-lead ECGs: tackling label uncertainty and class imbalance.

Objective.Chagas disease, a neglected tropical disease (NTD) with significant cardiovascular impact, remains underdiagnosed in resource-limited regions. Electrocardiogram (ECG) screening offers a low-cost tool for detecting cardiac involvement, yet algorithm development is challenged by label noise, data scarcity, and the latent nature of infection. This study proposes a robust ECG-based screening framework that explicitly addresses these constraints.Approach.We introduce aReliability-Aware Hierarchical Learningstrategy that calibrates supervision according to data provenance, prioritizing serology-confirmed labels over noisy self-reports. To mitigate data scarcity, we compare a specialized convolutional neural network (CNN) trained from scratch with a transfer learning approach based on a Spatio-Temporal ECG foundation Model (FM). Performance is evaluated across varying data scales, and the representation structure is analyzed to interpret model behavior.Main results.On the official hidden test set of the George B. Moody PhysioNet/Computing in Cardiology Challenge 2025, our approach achieved a Challenge Score of 0.163. We observe that while the specialized CNN performs competitively in data-rich regimes, the FM exhibits superior robustness in extreme low-resource settings. Furthermore, performance reaches a plateau imposed by underlying disease physiology. Bimodal score distributions suggest that models distinguish established cardiomyopathy from indeterminate infection, which remains electrophysiologically indistinguishable from healthy controls.Significance.These findings clarify both the potential and intrinsic limits of ECG-based AI screening for NTD-associated cardiac involvement. Reliability-aware supervision and data-efficient transfer learning provide a practical framework toward scalable and clinically meaningful ECG screening systems in resource-constrained environments.

Humans↗

PubMed2026

Effectiveness of Caregiver-Mediated Spoken Language Interventions for Children Under Five at Risk of Developmental Language Disorder: A Systematic Review and Meta-Analysis.

BACKGROUND AND AIMS: Caregiver-mediated interventions are commonly used by Speech and Language Therapists to support early language development. Developmental Language Disorder (DLD) is associated with reduced quality of life throughout the lifespan. Understanding factors that predict intervention success is essential for developing appropriate, cost-effective therapy provision for the approximately 12% of preschool children who present with early markers for Developmental Language Disorder (DLD). This systematic review and meta-analysis examined the effectiveness of caregiver-mediated spoken language interventions for under-fives at risk of DLD, and factors influencing intervention effectiveness. METHODS: A systematic review following PRISMA guidelines was conducted. Five electronic databases were searched to identify experimental studies comparing caregiver-mediated spoken language interventions to control conditions in under-fives presenting with risk factors for DLD. Risk factors included prematurity, socioeconomic factors, caregiver language development concerns, and formal or informal language screening or assessment scores. Twenty-six experimental studies with 1407 child participants were included in qualitative synthesis. Meta-analysis was performed on nine Randomised Controlled Trials involving 947 children. RESULTS: Effectiveness was examined for outcomes including child language gains, child wellbeing, inclusion and attainment. Meta-analysis indicated a significant effect of caregiver-mediated spoken language interventions on language outcomes compared to treatment-as-usual, non-language intervention or waitlist control conditions. Non-language outcomes were evaluated via qualitative synthesis. Interventions significantly improved language development trajectories for under-fives presenting with risk factors or early markers for DLD. CONCLUSION AND IMPLICATIONS: This review contributes to the growing evidence base demonstrating that caregiver-mediated interventions can positively impact language development and wellbeing outcomes for children under five at risk of DLD. These findings support the implementation of caregiver-mediated environmental language interventions in clinical practice to maximise accessibility and cost-effectiveness while delivering optimal outcomes for vulnerable populations. WHAT THIS PAPER ADDS: What is already known on this subject Previous research on caregiver-mediated spoken language interventions has highlighted gaps in the evidence regarding the impact of risk factors, demographic characteristics, dosage and intervention components on child language outcomes. Developmental Language Disorder has relatively high population prevalence, estimated at 7%. Prevalence is associated with risk factors including low household socioeconomic status (SES), prematurity and late language emergence. In contrast to its prevalence, there is low public and professional awareness of DLD and a low diagnostic rate. Therefore, a strengthened evidence base and additional insights into the factors affecting success of family-based interventions is important in order to increase the effectiveness of service provision and care planning for this underserved population. Timely and effective intervention with young children presenting with early markers for DLD has the potential to offer lifelong improvement to their wellbeing, inclusion and attainment outcomes. Recent systematic reviews of the effectiveness of caregiver-mediated language interventions had differences in population age range and diagnostic inclusion criteria. What this paper adds to existing knowledge Our review examines the effectiveness of caregiver-mediated early spoken language interventions on child language, attainment and wellbeing, and on caregiver self-efficacy and adherence to language support strategies. Our population was children under five presenting with risk factors for Developmental Language Disorder, in the absence of other neurodevelopmental or genetic conditions such as intellectual disability or autism. This review adds depth and detail to the evidence base supporting the effectiveness of caregiver-mediated spoken language interventions in improving outcomes for this population of young children, and factors that influence their success. What are the potential or actual clinical implications of this work? The high prevalence of Developmental Language Disorder, estimated at around 7% of the population, and the strong association with risk factors including low SES, prematurity and late language emergence, coupled with the low awareness of DLD and low diagnostic rate, mean that a strengthened evidence base and additional insights into the factors affecting success of family-based interventions can increase the effectiveness of service provision and care planning for this population. Timely and effective intervention in this group of young children has the potential to improve wellbeing and attainment outcomes across the lifespan. This review contributes to our understanding of how to implement cost-effective, socially valid and maximally engaging partnership working with families of young children at risk for DLD.

Humans↗

PubMed2026

Novel Proactive Speech-Language Intervention Is More Effective Than Usual Care: Randomized Controlled Trial of Babble Boot Camp for Infants With Classic Galactosemia.

PURPOSE: Speech and language disorders cannot be diagnosed and treated until children are approximately 2-4 years old. To investigate whether these disorders can be prevented, we developed and trialed Babble Boot Camp (BBC), the first proactive sustained intervention starting with precursor skills including cooing and babbling. METHOD: Participants were two randomly assigned groups of 22 infants with classic galactosemia, a metabolic disease with known risks for severe speech and language disorders. One group started BBC at under 6 months of age, and the other started at 15 months of age, both completing BBC at 24 months of age. Coached by a speech-language pathologist in weekly telehealth sessions, caregivers implemented BBC activities and routines daily at home. A typical control group and a group of children with classic galactosemia who received usual care participated as well. All children completed standardized assessments of speech and language at postintervention. RESULTS: Assessment scores showed that BBC was more effective than usual care for both intervention groups. Greatest benefits were seen in the group that started at or before 6 months of age, with a proportion of clinically concerning scores equal to that in the typically developing peers. No effects of sex, genotype, or milk consumption were evident in the outcomes. CONCLUSIONS: Findings motivate a paradigm shift from deficit-based to proactive approaches for infants with classic galactosemia. BBC is extensible to many other disorders, with trials currently underway for infants with Down syndrome and infants born preterm.

Humans↗

PubMed2026

Genomic history of the Caucasus: A systematic review and meta-analysis of ancient DNA studies.

The Caucasus region represents a unique natural laboratory for paleogenetic research due to its complex topography, long-standing role as a migratory corridor and glacial refugium, and exceptional preservation conditions for ancient DNA. This review synthesizes recent genome-wide studies to reconstruct the demographic history shaping the distinctive genetic landscape of modern Caucasus populations. The analysis reveals a deep pattern of continuity, isolation, and periodic admixture. Early genetic differentiation emerged in the Neolithic and Chalcolithic, forming distinct steppe and mountain population clusters. The Bronze Age was a pivotal period marked by large-scale gene flow from the Eurasian Steppe, particularly linked to the Yamnaya expansion, and interactions with Iranian and Anatolian-related groups. Despite these influences, many populations demonstrate remarkable genetic continuity from the Bronze Age to the present day. Significant knowledge gaps persist, particularly for the Paleolithic, Mesolithic, and Neolithic of the North Caucasus, as well as for the Late Medieval and Early Modern periods across the entire region. Addressing these gaps through targeted archaeogenomic studies is crucial for understanding the fine-scale processes that formed the hierarchical structure and high linguistic diversity of Caucasus populations, offering a powerful model for studying human adaptation, interaction, and language-genetics dynamics in a mountainous environment.

Humans↗

PubMed2026

The Role of Artificial Intelligence for Intimate Partner Violence Prevention: A Systematic Review.

INTRODUCTION: Intimate partner violence (IPV), encompassing physical, sexual, emotional and economic abuse, remains a pervasive global health concern. Traditional prevention efforts face obstacles such as underreporting, delayed detection and limited personalised support. Emerging artificial intelligence (AI) approaches offer new opportunities to enhance IPV prevention. AIM: This systematic review maps and synthesises evidence on AI-driven tools in IPV prevention based on studies published between 2004 and 2024. METHODS: Following PRISMA 2020 guidelines and PROSPERO registration, we searched PubMed, Embase, CINAHL, PsycINFO, IEEE Xplore and Web of Science. Eligible studies explicitly evaluated AI technologies targeting IPV prediction, screening, intervention or support delivery. Study quality was appraised using the Mixed Methods Appraisal Tool (MMAT). RESULTS: Of 1304 records initially identified, 41 studies met eligibility criteria. AI applications ranged from machine learning (ML) for risk prediction and natural language processing (NLP) for IPV detection in clinical and social media data, to image analysis for forensic evaluation and chatbot-based support. Predictive modelling demonstrated strong discriminative performance, while NLP-based screening detected IPV with notable sensitivity. Chatbots showed feasibility and user acceptability, but evidence of their direct impact on reducing IPV incidence was limited, with one randomised controlled trial showing a modest reduction. Key challenges identified included algorithmic bias, data privacy risks and barriers to integration across health and social care systems. DISCUSSION: AI-informed interventions show promise for improving IPV detection, risk assessment, and scalable support, but questions remain about long-term effectiveness, ethical fairness, transparency and equitable implementation. Future interdisciplinary research should address these concerns to responsibly deploy AI in IPV prevention. RELEVANCE TO CLINICAL PRACTICE: The findings highlight the importance of trauma-informed, culturally responsive care and provider training in AI applications. Nurse-led innovation and policy advocacy will be crucial for safe, equitable integration of AI in IPV prevention.

Artificial Intelligence↗

PubMed2026

Characterizing Submental Neuromuscular Activity of Swallowing Rehabilitation: An Electromyographic Evaluation of Rehabilitative Maneuvers in Healthy Adults.

PURPOSE: The effortful swallow (ES), the Mendelsohn maneuver (MM), and isometric tongue presses (TPs) are widely used swallowing maneuvers/exercises to improve elements of swallowing, such as muscle strength and biomechanics. However, the underlying neuromuscular mechanisms of these exercises remain unclear, potentially limiting our ability to specify treatment targets and improve treatment efficacy. This study aimed to compare submental neuromuscular activation patterns during the ES, MM, TPs, and typical swallows in healthy young and older adults. METHOD: As part of a larger randomized crossover validation study, 60 healthy adults (30 young and 30 older) completed typical swallows and three maneuvers using a wearable submental surface electromyographic (sEMG) system (i-Phagia). Outcome variables included (a) normalized mean sEMG amplitude and (b) time to peak sEMG amplitude. Linear mixed models were used to examine effects of task, age, and sex on both outcomes. RESULTS: Normalized mean amplitude was significantly different across tasks. Post hoc pairwise comparisons confirmed that all three maneuvers produced higher normalized mean sEMG amplitude than typical swallows, with the ES eliciting the highest amplitude across age groups. Time to peak amplitude differed significantly across tasks, with typical swallows requiring the shortest time to reach peak amplitude, followed by the ES, MM, and TP. CONCLUSIONS: The ES required the highest neuromuscular effort with the shortest time to reach peak amplitude, suggesting its potential for targeting submental muscle power. Typical swallows required the least neuromuscular effort with the shortest time to reach peak amplitude, suggesting their potential for training submental muscle speed. The MM and TP may also improve submental muscle strength; however, given their temporal requirements (longer durations), they may be more beneficial for targeting coordination and endurance, though more research in this area is warranted. These findings underscore the importance of task-specific neuromuscular profiling to inform mechanism-based swallowing rehabilitation. SUPPLEMENTAL MATERIAL: https://doi.org/10.23641/asha.32948549.

Humans↗