Loretta Gasparini
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Loretta Gasparini has a total of 163 co-authors. Here are the top co-authors by number of shared publications:
Melissa Wake
5 shared publications- Sho Tsuji
International Research Center for Neurointelligence The University of Tokyo Tokyo Japan
4 shared publications Angela Morgan
3 shared publicationsDaisy Shepherd
3 shared publicationsEdith L. Bavin
3 shared publicationsJing Wang
3 shared publications
Latest Publications
- Open Access
- 25 July 2026
- Published by Elsevier in Natural Language Processing Journal
- Vol. 16
Automated parts–of–speech tagging in 52 language varieties: Benchmarking towards establishing suitability for multilingual clinical language analysis
- 25 July 2026
- Published by Elsevier in Natural Language Processing Journal
- Vol. 16
Open AccessAutomated parts–of–speech tagging in 52 language varieties: Benchmarking towards establishing suitability for multilingual clinical language analysis
- Open Access
- 17 February 2026
- Published by Springer Nature in Research Square
Beyond word error rate: Multidimensional evaluation of ASR performance for digital speech biomarkers
Automatic speech recognition (ASR) is increasingly used in digital health, yet its reliability for populations with atypical speech, such as people with dementia, is not well characterised beyond word error rate (WER). We evaluated eight ASR systems on speech from adults with dementia and healthy older adults using WER, part-of-speech sequence agreement (POS-sqWER), part-of-speech distribution mismatch (POS-MDE), sentence-embedding cosine distance, and stutter detection error (SDE). Mixed-effects models with Tukey-corrected contrasts were used for comparison. Performance was consistently poorer for dementia speech across all metrics. AWS and CrisperWhisper showed relatively strong lexical, semantic, and syntactic fidelity, whereas Google and Meta exhibited lower accuracy. Other systems showed intermediate performance with rankings varying by metric. POS-MDE revealed syntactic distortions not captured by WER or POS-sqWER. SDE performance was low across systems. Multidimensional evaluation reveals clinically relevant linguistic distortions obscured by WER alone, supporting the need for population- and task-specific ASR validation in digital health research.
- 17 February 2026
- Published by Springer Nature in Research Square
Open AccessBeyond word error rate: Multidimensional evaluation of ASR performance for digital speech biomarkers
Automatic speech recognition (ASR) is increasingly used in digital health, yet its reliability for populations with atypical speech, such as people with dementia, is not well characterised beyond word error rate (WER). We evaluated eight ASR systems on speech from adults with dementia and healthy older adults using WER, part-of-speech sequence agreement (POS-sqWER), part-of-speech distribution mismatch (POS-MDE), sentence-embedding cosine distance, and stutter detection error (SDE). Mixed-effects models with Tukey-corrected contrasts were used for comparison. Performance was consistently poorer for dementia speech across all metrics. AWS and CrisperWhisper showed relatively strong lexical, semantic, and syntactic fidelity, whereas Google and Meta exhibited lower accuracy. Other systems showed intermediate performance with rankings varying by metric. POS-MDE revealed syntactic distortions not captured by WER or POS-sqWER. SDE performance was low across systems. Multidimensional evaluation reveals clinically relevant linguistic distortions obscured by WER alone, supporting the need for population- and task-specific ASR validation in digital health research.
- Open Access
- 13 November 2025
- Published by Cambridge University Press (CUP) in Data & Policy
- Vol. 7, e78
A survey of large language model use in a hospital, research, and teaching campus
The use of large language models (LLMs) has exploded since November 2022, but there is sparse evidence regarding LLM use in health, medical, and research contexts. We aimed to summarise the current uses of and attitudes towards LLMs across our campus’ clinical, research, and teaching sites. We administered a survey about LLM uses and attitudes. We conducted summary quantitative analysis and inductive qualitative analysis of free text responses. In August–September 2023, we circulated the survey amongst all staff and students across our three campus sites (approximately n = 7500), comprising a paediatric academic hospital, research institute, and paediatric university department. We received 281 anonymous survey responses. We asked about participants’ knowledge of LLMs, their current use of LLMs in professional or learning contexts, and perspectives on possible future uses, opportunities, and risks of LLM use. Over 90% of respondents have heard of LLM tools and about two-thirds have used them in their work on our campus. Respondents reported using LLMs for various uses, including generating or editing text and exploring ideas. Many, but not necessarily all, respondents seem aware of the limitations and potential risks of LLMs, including privacy and security risks. Various respondents expressed enthusiasm about the opportunities of LLM use, including increased efficiency. Our findings show LLM tools are already widely used on our campus. Guidelines and governance are needed to keep up with practice. Insights from this survey were used to develop recommendations for the use of LLMs on our campus.
- 13 November 2025
- Published by Cambridge University Press (CUP) in Data & Policy
- Vol. 7, e78
Open AccessA survey of large language model use in a hospital, research, and teaching campus
The use of large language models (LLMs) has exploded since November 2022, but there is sparse evidence regarding LLM use in health, medical, and research contexts. We aimed to summarise the current uses of and attitudes towards LLMs across our campus’ clinical, research, and teaching sites. We administered a survey about LLM uses and attitudes. We conducted summary quantitative analysis and inductive qualitative analysis of free text responses. In August–September 2023, we circulated the survey amongst all staff and students across our three campus sites (approximately n = 7500), comprising a paediatric academic hospital, research institute, and paediatric university department. We received 281 anonymous survey responses. We asked about participants’ knowledge of LLMs, their current use of LLMs in professional or learning contexts, and perspectives on possible future uses, opportunities, and risks of LLM use. Over 90% of respondents have heard of LLM tools and about two-thirds have used them in their work on our campus. Respondents reported using LLMs for various uses, including generating or editing text and exploring ideas. Many, but not necessarily all, respondents seem aware of the limitations and potential risks of LLMs, including privacy and security risks. Various respondents expressed enthusiasm about the opportunities of LLM use, including increased efficiency. Our findings show LLM tools are already widely used on our campus. Guidelines and governance are needed to keep up with practice. Insights from this survey were used to develop recommendations for the use of LLMs on our campus.
- Open Access
- 10 November 2025
- Published by Center for Open Science in PsyArXiv
Combining genetic and behavioral predictors of 11-year language outcome
Background: Rapid population-level identification of language disorders could help provide care to young children to improve their outcomes. Two previous studies identified and replicated up to six parent-reported items that predicted 11-year language outcome with ≥71% sensitivity and specificity. Here, we assess whether including genetic propensity for toddlerhood vocabulary improves predictive accuracy. Method: The Early Language in Victoria Study (ELVS) recruited 1,910 8-month-olds in Melbourne in 2003-2004. The Longitudinal Study of Australian Children (LSAC) recruited 5,107 0-1-year-olds across Australia in 2004. Both collected parent-reported items at 2-3 years, a comparable 11-year language outcome: the Clinical Evaluation of Language Fundamentals (CELF-4) Core Language score or Recalling Sentences subtest, and biospecimens for genotyping. We derived polygenic scores capturing participants’ genetic propensity for parent-reported 24-38-month vocabulary. We calculated univariate associations with continuous language outcomes. We used ensemble method SuperLearner to estimate how accurately the parent-reported predictors and polygenic scores predict low 11-year language outcome (more than 1.5 standard deviations below the mean) in each cohort. Results: Language outcome was available for 839 ELVS and 1,441 LSAC participants. Polygenic scores accounted for little variance in continuous language outcomes (R-squared less than 1.5%). Adding polygenic scores to the predictor sets increased accuracy of predicting language outcome by up to 7%, but inconsistently between analyses. Conclusions: Polygenic scores derived for toddlerhood vocabulary did not meaningfully predict late childhood language. Polygenic scores derived for later global language measures in larger samples may be better predictors. Presently, parent-reported measures or clinician observation appear best for predicting language outcome at this age.
- 10 November 2025
- Published by Center for Open Science in PsyArXiv
Open AccessCombining genetic and behavioral predictors of 11-year language outcome
Background: Rapid population-level identification of language disorders could help provide care to young children to improve their outcomes. Two previous studies identified and replicated up to six parent-reported items that predicted 11-year language outcome with ≥71% sensitivity and specificity. Here, we assess whether including genetic propensity for toddlerhood vocabulary improves predictive accuracy. Method: The Early Language in Victoria Study (ELVS) recruited 1,910 8-month-olds in Melbourne in 2003-2004. The Longitudinal Study of Australian Children (LSAC) recruited 5,107 0-1-year-olds across Australia in 2004. Both collected parent-reported items at 2-3 years, a comparable 11-year language outcome: the Clinical Evaluation of Language Fundamentals (CELF-4) Core Language score or Recalling Sentences subtest, and biospecimens for genotyping. We derived polygenic scores capturing participants’ genetic propensity for parent-reported 24-38-month vocabulary. We calculated univariate associations with continuous language outcomes. We used ensemble method SuperLearner to estimate how accurately the parent-reported predictors and polygenic scores predict low 11-year language outcome (more than 1.5 standard deviations below the mean) in each cohort. Results: Language outcome was available for 839 ELVS and 1,441 LSAC participants. Polygenic scores accounted for little variance in continuous language outcomes (R-squared less than 1.5%). Adding polygenic scores to the predictor sets increased accuracy of predicting language outcome by up to 7%, but inconsistently between analyses. Conclusions: Polygenic scores derived for toddlerhood vocabulary did not meaningfully predict late childhood language. Polygenic scores derived for later global language measures in larger samples may be better predictors. Presently, parent-reported measures or clinician observation appear best for predicting language outcome at this age.
- Open Access
- 8 November 2025
- Published by Elsevier in Psychiatry Research
- Vol. 354, 116826
Combining genetic and behavioral predictors of 11-year language outcome
- 8 November 2025
- Published by Elsevier in Psychiatry Research
- Vol. 354, 116826
Open AccessCombining genetic and behavioral predictors of 11-year language outcome
- 3 December 2024
- Published by Wiley in International Journal of Language & Communication Disorders
- Vol. 60 (1) , e13142
How to create accessible research summaries for the developmental language disorder community
Background: Eighty‐five percent of medical research goes to waste, partly because it is not appropriately communicated to stakeholders. This represents a critical issue for the research community, especially because individuals who are impacted by research should be able to readily access that research. Making research findings accessible to key stakeholders is an important step in implementation science and in enabling research to have meaningful impacts. Plain language summaries are a tool to make research more accessible to individuals with communication disorders. While guidelines exist to support researchers to develop plain language summaries for some populations, no such guidelines exist for the developmental language disorder (DLD) community.Aims: We aimed to develop evidence‐informed guidelines to support researchers to create plain language summaries that are accessible for individuals with DLD, their families, and the broader community. This discussion paper describes the development of these guidelines and how they may be implemented by researchers who conduct research on the topic of DLD.Methods: We drew from existing plain language summary guidelines for other populations and knowledge of various barriers that may impact the DLD community's ability to access scientific research. We used this knowledge to create guidelines for researchers to develop plain language summaries of their research relating to the DLD population. This includes guidelines for creating written, visual, audio and video summaries. We consulted with an adult with DLD, an implementation scientist, and a speech‐language pathologist regarding the suitability of the guidelines.Main Contribution: The plain language summary guidelines are publicly available via https://osf.io/ydkw9. They include templates and examples, as well as suggestions for writing and visual styles. We encourage strengths‐based language, seeking feedback from non‐experts, and sharing the summaries on social media. We have also developed an online repository for researchers to disseminate their plain language summaries via DLD advocacy groups.Conclusions: The written, audio and video plain language summaries that researchers create using our guidelines can be used to disseminate research to the DLD community. This can facilitate science implementation and maximise the impact of DLD research. The plain language summaries may also help individuals with DLD better understand the research that has been conducted about them. This may in turn support their engagement with services and empower them to make evidence‐informed choices for themselves and partner in co‐designing new research. Future research could explore the perspectives of the DLD community and researchers regarding the implementation of these guidelines.Plain language summary: A lot of research goes to waste. This is partly because researchers rarely share their results with the non‐scientific community. People with communication disorders might find it hard to understand research papers. We made guidelines to help researchers explain their research to people with developmental language disorder (DLD. We brought together existing advice on how to explain research in a clear way. We sought advice from people with different experiences and perspectives, including an adult with DLD. The guidelines are at https://osf.io/ydkw9. The guidelines include advice on how to add pictures to research summaries. We also explain how to make a video or podcast summarising research. We encourage researchers to share their research summaries on social media. This means their research can reach more people and can make a difference. It is important that people with DLD understand DLD research. This might help them to understand their diagnosis and take part in future research.WHAT THIS PAPER ADDS: What is already known on the subject: For research to make a difference, it must be appropriately communicated to its stakeholders; however, only 1.5% of academic journals require authors to write plain language summaries. What this paper adds to existing knowledge: This paper presents publicly available guidelines for researchers to create written, visual, audio and video plain language summaries aimed to be accessible for individuals with developmental language disorder (DLD) and their families. What are the potential or actual clinical implications of this work?: Researchers can use plain language summaries to disseminate research to the wider community. This can help individuals with DLD better understand the research that has been conducted about them and may empower them to meaningfully partner in co‐designing new research.
- 3 December 2024
- Published by Wiley in International Journal of Language & Communication Disorders
- Vol. 60 (1) , e13142
How to create accessible research summaries for the developmental language disorder community
Background: Eighty‐five percent of medical research goes to waste, partly because it is not appropriately communicated to stakeholders. This represents a critical issue for the research community, especially because individuals who are impacted by research should be able to readily access that research. Making research findings accessible to key stakeholders is an important step in implementation science and in enabling research to have meaningful impacts. Plain language summaries are a tool to make research more accessible to individuals with communication disorders. While guidelines exist to support researchers to develop plain language summaries for some populations, no such guidelines exist for the developmental language disorder (DLD) community.Aims: We aimed to develop evidence‐informed guidelines to support researchers to create plain language summaries that are accessible for individuals with DLD, their families, and the broader community. This discussion paper describes the development of these guidelines and how they may be implemented by researchers who conduct research on the topic of DLD.Methods: We drew from existing plain language summary guidelines for other populations and knowledge of various barriers that may impact the DLD community's ability to access scientific research. We used this knowledge to create guidelines for researchers to develop plain language summaries of their research relating to the DLD population. This includes guidelines for creating written, visual, audio and video summaries. We consulted with an adult with DLD, an implementation scientist, and a speech‐language pathologist regarding the suitability of the guidelines.Main Contribution: The plain language summary guidelines are publicly available via https://osf.io/ydkw9. They include templates and examples, as well as suggestions for writing and visual styles. We encourage strengths‐based language, seeking feedback from non‐experts, and sharing the summaries on social media. We have also developed an online repository for researchers to disseminate their plain language summaries via DLD advocacy groups.Conclusions: The written, audio and video plain language summaries that researchers create using our guidelines can be used to disseminate research to the DLD community. This can facilitate science implementation and maximise the impact of DLD research. The plain language summaries may also help individuals with DLD better understand the research that has been conducted about them. This may in turn support their engagement with services and empower them to make evidence‐informed choices for themselves and partner in co‐designing new research. Future research could explore the perspectives of the DLD community and researchers regarding the implementation of these guidelines.Plain language summary: A lot of research goes to waste. This is partly because researchers rarely share their results with the non‐scientific community. People with communication disorders might find it hard to understand research papers. We made guidelines to help researchers explain their research to people with developmental language disorder (DLD. We brought together existing advice on how to explain research in a clear way. We sought advice from people with different experiences and perspectives, including an adult with DLD. The guidelines are at https://osf.io/ydkw9. The guidelines include advice on how to add pictures to research summaries. We also explain how to make a video or podcast summarising research. We encourage researchers to share their research summaries on social media. This means their research can reach more people and can make a difference. It is important that people with DLD understand DLD research. This might help them to understand their diagnosis and take part in future research.WHAT THIS PAPER ADDS: What is already known on the subject: For research to make a difference, it must be appropriately communicated to its stakeholders; however, only 1.5% of academic journals require authors to write plain language summaries. What this paper adds to existing knowledge: This paper presents publicly available guidelines for researchers to create written, visual, audio and video plain language summaries aimed to be accessible for individuals with developmental language disorder (DLD) and their families. What are the potential or actual clinical implications of this work?: Researchers can use plain language summaries to disseminate research to the wider community. This can help individuals with DLD better understand the research that has been conducted about them and may empower them to meaningfully partner in co‐designing new research.
- Open Access
A survey of Large Language Model use in a hospital, research, and teaching campus
Background: The use of Large Language Models (LLMs) has exploded since November 2022 but there is sparse evidence regarding LLM use in health, medical and research contexts. Objective: To summarise the current uses of and attitudes towards LLMs across the clinical, research and teaching contexts in our campus. Design: We administered a survey about LLM uses and attitudes. We conducted summary quantitative analysis and inductive qualitative analysis of free text responses. Setting: In August-September 2023, we circulated the survey amongst all staff and students across our campus (approximately n=7500), a fully integrated paediatric academic hospital and research institute. Participants: We received 281 anonymous survey responses. Main outcome measures: We asked about participants’ knowledge of LLMs, their current use of LLMs in professional or learning contexts, and perspectives on possible future uses, opportunities, and risks of LLM use. Results: Over 90% of respondents have heard of LLM tools and about two-thirds have used them in their work on our campus. Respondents reported using LLMs for a range of uses, including for generating or editing text and exploring ideas. Many, but not necessarily all, respondents seem aware of the limitations and potential risks of LLMs, including privacy and security risks. Various respondents expressed enthusiasm about opportunities of LLM use, including increased efficiency. Conclusions: Our findings show LLM tools are already widely used on our campus. Guidelines and governance are needed to keep up with practice. We have developed recommendations for the use of LLMs on our campus using insights from this survey. What is known: The known: The use of Large Language Models (LLMs) has increased rapidly since the introduction of ChatGPT in November 2022. The new: Most survey respondents are aware of, if not using, LLMs in their work across our hospital, research, and university campus. Diverse uses were reported, including generating or editing text and exploring ideas. There were varying attitudes towards LLMs. Perceived risks included privacy and security risks. A key perceived opportunity was increased efficiency. The implications: LLM tools are already widely used on our campus, highlighting the need for guidelines and governance to keep up with practice.
Open AccessA survey of Large Language Model use in a hospital, research, and teaching campus
Background: The use of Large Language Models (LLMs) has exploded since November 2022 but there is sparse evidence regarding LLM use in health, medical and research contexts. Objective: To summarise the current uses of and attitudes towards LLMs across the clinical, research and teaching contexts in our campus. Design: We administered a survey about LLM uses and attitudes. We conducted summary quantitative analysis and inductive qualitative analysis of free text responses. Setting: In August-September 2023, we circulated the survey amongst all staff and students across our campus (approximately n=7500), a fully integrated paediatric academic hospital and research institute. Participants: We received 281 anonymous survey responses. Main outcome measures: We asked about participants’ knowledge of LLMs, their current use of LLMs in professional or learning contexts, and perspectives on possible future uses, opportunities, and risks of LLM use. Results: Over 90% of respondents have heard of LLM tools and about two-thirds have used them in their work on our campus. Respondents reported using LLMs for a range of uses, including for generating or editing text and exploring ideas. Many, but not necessarily all, respondents seem aware of the limitations and potential risks of LLMs, including privacy and security risks. Various respondents expressed enthusiasm about opportunities of LLM use, including increased efficiency. Conclusions: Our findings show LLM tools are already widely used on our campus. Guidelines and governance are needed to keep up with practice. We have developed recommendations for the use of LLMs on our campus using insights from this survey. What is known: The known: The use of Large Language Models (LLMs) has increased rapidly since the introduction of ChatGPT in November 2022. The new: Most survey respondents are aware of, if not using, LLMs in their work across our hospital, research, and university campus. Diverse uses were reported, including generating or editing text and exploring ideas. There were varying attitudes towards LLMs. Perceived risks included privacy and security risks. A key perceived opportunity was increased efficiency. The implications: LLM tools are already widely used on our campus, highlighting the need for guidelines and governance to keep up with practice.
- Open Access
- 9 September 2024
- Published by SAGE Publications in Research Ethics
- Vol. 21 (1) , 180-202
A rapid review of the benefits and challenges of dynamic consent
Dynamic consent is increasingly recommended for longitudinal and biobanking research; however, the value of investing in such systems is unclear. We undertook a rapid review of the benefits and challenges of implementing dynamic consent by searching five databases (Ovid Medline, Ovid Embase, Scopus, Web of Science, Cumulative Index to Nursing and Allied Health Literature – CINAHL) for articles published up to May 2023 that report on participants’ or researchers’ experience of dynamic consent. From 1611 papers screened, 12 met inclusion criteria. Guided by thematic analysis with an inductive approach, we synthesised 31 benefits and 8 challenges. Benefits included: enhanced participant experience through improved consent management and tailoring; greater participant engagement and retention through increased autonomy, trust and communication; reduced costs and burden and increased accessibility and inclusivity. Participants and researchers also valued additional features that dynamic consent platforms facilitate such as two-way communication and return of research updates. The main challenges included the digital divide and consent fatigue. The papers gave recommendations to mitigate these challenges, for example by supplementing with other communication tools and allowing a broad consent approach, respectively. Overall, dynamic consent was described as a valuable consent approach with many benefits and some surmountable challenges. Most included literature was qualitative, so further research is needed to quantify the impact of dynamic consent on recruitment, retention, and participant experience. Further long-term investigations are necessary to explore whether participants want to and do change their consent over time, as well as the impact of dynamic consent on participant privacy.
- 9 September 2024
- Published by SAGE Publications in Research Ethics
- Vol. 21 (1) , 180-202
Open AccessA rapid review of the benefits and challenges of dynamic consent
Dynamic consent is increasingly recommended for longitudinal and biobanking research; however, the value of investing in such systems is unclear. We undertook a rapid review of the benefits and challenges of implementing dynamic consent by searching five databases (Ovid Medline, Ovid Embase, Scopus, Web of Science, Cumulative Index to Nursing and Allied Health Literature – CINAHL) for articles published up to May 2023 that report on participants’ or researchers’ experience of dynamic consent. From 1611 papers screened, 12 met inclusion criteria. Guided by thematic analysis with an inductive approach, we synthesised 31 benefits and 8 challenges. Benefits included: enhanced participant experience through improved consent management and tailoring; greater participant engagement and retention through increased autonomy, trust and communication; reduced costs and burden and increased accessibility and inclusivity. Participants and researchers also valued additional features that dynamic consent platforms facilitate such as two-way communication and return of research updates. The main challenges included the digital divide and consent fatigue. The papers gave recommendations to mitigate these challenges, for example by supplementing with other communication tools and allowing a broad consent approach, respectively. Overall, dynamic consent was described as a valuable consent approach with many benefits and some surmountable challenges. Most included literature was qualitative, so further research is needed to quantify the impact of dynamic consent on recruitment, retention, and participant experience. Further long-term investigations are necessary to explore whether participants want to and do change their consent over time, as well as the impact of dynamic consent on participant privacy.
- Open Access
- 1 July 2024
- Published by Wiley in International Journal of Language & Communication Disorders
- Vol. 59 (6) , 2352-2366
Identifying early language predictors: A replication of Gasparini et al. (2023) confirming applicability in a general population cohort
Background: Identifying language disorders earlier can help children receive the support needed to improve developmental outcomes and quality of life. Despite the prevalence and impacts of persistent language disorder, there are surprisingly no robust predictor tools available. This makes it difficult for researchers to recruit young children into early intervention trials, which in turn impedes advances in providing effective early interventions to children who need it.Aims: To validate externally a predictor set of six variables previously identified to be predictive of language at 11 years of age, using data from the Longitudinal Study of Australian Children (LSAC) birth cohort. Also, to examine whether additional LSAC variables arose as predictive of language outcome.Methods & Procedures: A total of 5107 children were recruited to LSAC with developmental measures collected from 0 to 3 years. At 11–12 years, children completed the Clinical Evaluation of Language Fundamentals, 4th Edition, Recalling Sentences subtest. We used SuperLearner to estimate the accuracy of six previously identified parent‐reported variables from ages 2–3 years in predicting low language (sentence recall score ≥ 1.5 SD below the mean) at 11–12 years. Random forests were used to identify any additional variables predictive of language outcome.Outcomes & Results: Complete data were available for 523 participants (52.20% girls), 27 (5.16%) of whom had a low language score. The six predictors yielded fair accuracy: 78% sensitivity (95% confidence interval (CI) = [58, 91]) and 71% specificity (95% CI = [67, 75]). These predictors relate to sentence complexity, vocabulary and behaviour. The random forests analysis identified similar predictors.Conclusions & Implications: We identified an ultra‐short set of variables that predicts 11–12‐year language outcome with ‘fair’ accuracy. In one of few replication studies of this scale in the field, these methods have now been conducted across two population‐based cohorts, with consistent results. An imminent practical implication of these findings is using these predictors to aid recruitment into early language intervention studies. Future research can continue to refine the accuracy of early predictors to work towards earlier identification in a clinical context.WHAT THIS PAPER ADDS: What is already known on the subject: There are no robust predictor sets of child language disorder despite its prevalence and far‐reaching impacts. A previous study identified six variables collected at age 2–3 years that predicted 11–12‐year language with 75% sensitivity and 81% specificity, which warranted replication in a separate cohort. What this study adds to the existing knowledge: We used machine learning methods to identify a set of six questions asked at age 2–3 years with ≥ 71% sensitivity and specificity for predicting low language outcome at 11–12 years, now showing consistent results across two large‐scale population‐based cohort studies. What are the potential or clinical implications of this work?: This predictor set is more accurate than existing feasible methods and can be translated into a low‐resource and time‐efficient recruitment tool for early language intervention studies, leading to improved clinical service provision for young children likely to have persisting language difficulties.
- 1 July 2024
- Published by Wiley in International Journal of Language & Communication Disorders
- Vol. 59 (6) , 2352-2366
Open AccessIdentifying early language predictors: A replication of Gasparini et al. (2023) confirming applicability in a general population cohort
Background: Identifying language disorders earlier can help children receive the support needed to improve developmental outcomes and quality of life. Despite the prevalence and impacts of persistent language disorder, there are surprisingly no robust predictor tools available. This makes it difficult for researchers to recruit young children into early intervention trials, which in turn impedes advances in providing effective early interventions to children who need it.Aims: To validate externally a predictor set of six variables previously identified to be predictive of language at 11 years of age, using data from the Longitudinal Study of Australian Children (LSAC) birth cohort. Also, to examine whether additional LSAC variables arose as predictive of language outcome.Methods & Procedures: A total of 5107 children were recruited to LSAC with developmental measures collected from 0 to 3 years. At 11–12 years, children completed the Clinical Evaluation of Language Fundamentals, 4th Edition, Recalling Sentences subtest. We used SuperLearner to estimate the accuracy of six previously identified parent‐reported variables from ages 2–3 years in predicting low language (sentence recall score ≥ 1.5 SD below the mean) at 11–12 years. Random forests were used to identify any additional variables predictive of language outcome.Outcomes & Results: Complete data were available for 523 participants (52.20% girls), 27 (5.16%) of whom had a low language score. The six predictors yielded fair accuracy: 78% sensitivity (95% confidence interval (CI) = [58, 91]) and 71% specificity (95% CI = [67, 75]). These predictors relate to sentence complexity, vocabulary and behaviour. The random forests analysis identified similar predictors.Conclusions & Implications: We identified an ultra‐short set of variables that predicts 11–12‐year language outcome with ‘fair’ accuracy. In one of few replication studies of this scale in the field, these methods have now been conducted across two population‐based cohorts, with consistent results. An imminent practical implication of these findings is using these predictors to aid recruitment into early language intervention studies. Future research can continue to refine the accuracy of early predictors to work towards earlier identification in a clinical context.WHAT THIS PAPER ADDS: What is already known on the subject: There are no robust predictor sets of child language disorder despite its prevalence and far‐reaching impacts. A previous study identified six variables collected at age 2–3 years that predicted 11–12‐year language with 75% sensitivity and 81% specificity, which warranted replication in a separate cohort. What this study adds to the existing knowledge: We used machine learning methods to identify a set of six questions asked at age 2–3 years with ≥ 71% sensitivity and specificity for predicting low language outcome at 11–12 years, now showing consistent results across two large‐scale population‐based cohort studies. What are the potential or clinical implications of this work?: This predictor set is more accurate than existing feasible methods and can be translated into a low‐resource and time‐efficient recruitment tool for early language intervention studies, leading to improved clinical service provision for young children likely to have persisting language difficulties.
- Open Access
- 6 February 2024
- Published by Center for Open Science in PsyArXiv
How to create accessible research summaries for the Developmental Language Disorder community
Background: Eighty-five percent of medical research goes to waste, in part because it is not appropriately communicated to stakeholders. Individuals who are impacted by research should be able to readily access that research: an important step in making research impactful. Plain Language Summaries are a tool to make research more accessible to individuals with communication disorders. No guidelines exist to support researchers to develop Plain Language Summaries for the Developmental Language Disorder (DLD) community.Aim: We aimed to develop evidence-informed guidelines to support researchers to create Plain Language Summaries that are accessible for individuals with DLD, their families, and the broader community. Methods: We drew from existing Plain Language Summary guidelines for other populations and knowledge of barriers that may impact the DLD community’s ability to access scientific research. We used this knowledge to create guidelines for researchers to develop written, visual, audio, and video Plain Language Summaries of their research relating to DLD. We consulted with an adult with DLD, an implementation scientist, and a speech-language pathologist regarding the suitability of the guidelines.Main Contribution: The Plain Language Summary guidelines are available via https://osf.io/ydkw9/. They include suggestions for writing and visual styles, templates and examples. We encourage strengths-based language, seeking feedback from non-experts, and sharing the summaries on social media and via DLD advocacy groups.Conclusions: The Plain Language Summaries that researchers create using our guidelines can be used to disseminate research to the DLD community , maximising the impact of DLD research. The Plain Language Summaries may also help individuals with DLD better understand research that has been conducted about them. This may in turn empower them to make evidence-informed choices for themselves and partner in co-designing new research. Future research could explore the perspectives of the DLD community regarding the implementation of these guidelines.Plain language summary: A lot of research goes to waste. This is partly because researchers rarely share their results with the non-scientific community. People with communication disorders might find it hard to understand research papers. We made guidelines to help researchers explain their research to people with Developmental Language Disorder (DLD). We brought together existing advice on how to explain research in a clear way. We sought advice from people with different experiences and perspectives, including an adult with DLD. The guidelines are at https://osf.io/ydkw9/. The guidelines include advice on how to add pictures to research summaries. We also explain how to make a video or podcast summarising research. We encourage researchers to share their research summaries on social media. This means their research can reach more people and can make a difference. It is important that people with DLD understand DLD research. This might help them to understand their diagnosis and take part in future research.
- 6 February 2024
- Published by Center for Open Science in PsyArXiv
Open AccessHow to create accessible research summaries for the Developmental Language Disorder community
Background: Eighty-five percent of medical research goes to waste, in part because it is not appropriately communicated to stakeholders. Individuals who are impacted by research should be able to readily access that research: an important step in making research impactful. Plain Language Summaries are a tool to make research more accessible to individuals with communication disorders. No guidelines exist to support researchers to develop Plain Language Summaries for the Developmental Language Disorder (DLD) community.Aim: We aimed to develop evidence-informed guidelines to support researchers to create Plain Language Summaries that are accessible for individuals with DLD, their families, and the broader community. Methods: We drew from existing Plain Language Summary guidelines for other populations and knowledge of barriers that may impact the DLD community’s ability to access scientific research. We used this knowledge to create guidelines for researchers to develop written, visual, audio, and video Plain Language Summaries of their research relating to DLD. We consulted with an adult with DLD, an implementation scientist, and a speech-language pathologist regarding the suitability of the guidelines.Main Contribution: The Plain Language Summary guidelines are available via https://osf.io/ydkw9/. They include suggestions for writing and visual styles, templates and examples. We encourage strengths-based language, seeking feedback from non-experts, and sharing the summaries on social media and via DLD advocacy groups.Conclusions: The Plain Language Summaries that researchers create using our guidelines can be used to disseminate research to the DLD community , maximising the impact of DLD research. The Plain Language Summaries may also help individuals with DLD better understand research that has been conducted about them. This may in turn empower them to make evidence-informed choices for themselves and partner in co-designing new research. Future research could explore the perspectives of the DLD community regarding the implementation of these guidelines.Plain language summary: A lot of research goes to waste. This is partly because researchers rarely share their results with the non-scientific community. People with communication disorders might find it hard to understand research papers. We made guidelines to help researchers explain their research to people with Developmental Language Disorder (DLD). We brought together existing advice on how to explain research in a clear way. We sought advice from people with different experiences and perspectives, including an adult with DLD. The guidelines are at https://osf.io/ydkw9/. The guidelines include advice on how to add pictures to research summaries. We also explain how to make a video or podcast summarising research. We encourage researchers to share their research summaries on social media. This means their research can reach more people and can make a difference. It is important that people with DLD understand DLD research. This might help them to understand their diagnosis and take part in future research.