AI improves accuracy, agreement and efficiency of pathologists for Ki67 assessments in breast cancer.

The Ki-67 proliferation index (PI) guides treatment decisions in breast cancer but suffers from poor inter-rater reproducibility. Although AI tools have been designed for Ki-67 assessment, their impact on pathologists' work remains understudied. 90 international pathologists were recruited to assess the Ki-67 PI of ten breast cancer tissue microarrays with and without AI. Accuracy, agreement, and turnaround time with and without AI were compared. Pathologists' perspectives on AI were collected. Using AI led to a significant decrease in PI error (2.1% with AI vs. 5.9% without AI, p < 0.001), better inter-rater agreement (ICC: 0.70 vs. 0.92; Krippendorff's α: 0.63 vs. 0.89; Fleiss' Kappa: 0.40 vs. 0.86), and an 11.9% overall median reduction in turnaround time. Most pathologists (84%) found the AI reliable. For Ki-67 assessments, 76% of respondents believed AI enhances accuracy, 82% said it improves consistency, and 83% trust it will improve efficiency. This study highlights AI's potential to standardize Ki-67 scoring, especially between 5 and 30% PI-a range with low PI agreement. This could pave the way for a universally accepted PI score to guide treatment decisions, emphasizing the promising role of AI integration into pathologist workflows.

Quantification of titanium and zirconium elements in oral mucosa around healthy dental implants: a case-control pilot study.

OBJECTIVES: Metallic particles are detected in different sites of the oral cavity, mainly in patients with peri-implantitis lesions. The aim of this pilot study was to analyze the levels of titanium and zirconium elements in the oral mucosa around healthy implants and to investigate the impact of titanium exogenous contamination on the measurements. MATERIALS AND METHODS: Forty-one participants were included in this three-phase study. Two groups of subjects were defined according to presence of titanium or zirconia implants (n: 20) or without any implants nor metallic restorations (n:21). Thirteen patients (n: 5 with zirconia implant; n: 3 with titanium implants; n: 5 control group) took part to the first part designed to optimize and validate the method of detecting titanium (Ti) and zirconium (Zr) elements in the oral mucosa and gingival tissues by the Inductively Coupled Plasma Mass Spectrometry (ICPMS). The second phase compared the levels of Ti and Zr concentrations in patients with implants (n: 12) and without implants (n: 6) who were controlled for their intake of titanium dioxide (TiO2). The last step included ten control subjects without any metallic devices to measure the concentration of Ti and Zr before and after having candies containing TiO2. RESULTS: In the first phase, concentrations of Ti and Zr were below the limit of detection (LOD) in most cases, 0.18 µg/L and 0.07 µg/L respectively. In the titanium group, two out of three subjects displayed concentrations above the LOD, 0.21 µg/L and 0.66 µg/L. Zr element was only found in patients with zirconia implants. After controlling the intake of TiO2, all concentrations of Ti and Zr were below the limit of quantification (LOQ). Moreover, in patients with no implants, the Ti concentration in gingiva cells was superior for 75% of the samples after having a TiO2 diet. CONCLUSIONS: Zirconium was only found in patients with zirconia implants, whereas titanium was detected in all groups even in subjects with no titanium implants. Zirconium and titanium elements were not detected in patients who were controlled for their intake of food and their use of toothpaste irrespective of the presence of implants or not. For 70% of the patients, the titanium detection was directly influenced by the intake of TiO2 contained candies. CLINICAL RELEVANCE: When analyzing titanium particles, it is necessary to pay attention to the risk of contamination bias brought by external products. When this parameter was controlled, no titanium particles were detected around clinically healthy implants.

Testing perceptual flexibility in speech through the categorization of whistled Spanish consonants by French speakers.

Whistled speech is a form of modified speech where, in non-tonal languages, vowels and consonants are augmented and transposed to whistled frequencies, simplifying their timbre. According to previous studies, these transformations maintain some level of vowel recognition for naive listeners. Here, in a behavioral experiment, naive listeners' capacities for the categorization of four whistled consonants (/p/, /k/, /t/, and /s/) were analyzed. Results show patterns of correct responses and confusions that provide new insights into whistled speech perception, highlighting the importance of frequency modulation cues, transposed from phoneme formants, as well as the perceptual flexibility in processing these cues.

Opioid prescribing practices in trauma patients at discharge: An exploratory retrospective chart analysis.

This study examined the opioid prescribing patterns at discharge in the trauma center of a major Canadian hospital and compared them to the guidelines provided by the Illinois surgical quality improvement collaborative (ISQIC), a framework that has been recognized as being associated with reduced risk. This was a retrospective chart review of patient data from the trauma registry between January 1, 2018, and October 31, 2019. A total of 268 discharge charts of naïve opioid patients were included in the analysis. A Morphine Milligram Equivalents per day (MME/day) was computed for each patient who was prescribed opioids and compared with standard practice guidelines. About 75% of patients were prescribed opioids. More males (75%) than females (25%) were prescribed opioids to patients below 65 years old (91%). Best practice guidelines were followed in most cases. Only 16.6% of patients were prescribed over 50 mg MME/day, the majority (80.9%) were prescribed opioids for =<3 days and only 1% for >7 days. Only 7.5% were prescribed extended-release opioids and none were strong like fentanyl. Patients received a multimodal approach with alternatives to opioids in 88.9% of cases and 82.9% had a plan for opioid discontinuation. However, only 23.6% received an acute pain service referral. The majority of the prescriptions provided adhered to the best practice guidelines outlined by the ISQIC framework. These results are encouraging with respect to the feasibility of implementing opioid prescription guidelines effectively. However, routine monitoring is necessary to ensure that adherence is maintained.

Mental health support for Canadian postsecondary students during COVID-19 pandemic: An environmental scan.

OBJECTIVE: This study explored how Canada's postsecondary institutions have informed students about campus mental health (MH) services via websites and social media during the COVID-19 pandemic. METHODS: We conducted a Web-based environmental scan of 20 universities and 24 colleges across the province of Ontario, Canada, between October 2020 and July 2021. RESULTS: 91% of the institutions offered virtual counseling services and 84% offered general psychoeducational resources, whereas only 55% had COVID-19 specific MH resources. Larger institutions had more MH support to students than small schools. There was a trend toward outsourcing counseling and emergency services to external professionals via apps and hotlines. Limited MH information was available for out-of-province and international students. CONCLUSION: It is vital for equitable campus MH services to address unique MH challenges associated with the crisis and intentional outreach to students with special circumstances. Schools can leverage peer support and self-help to promote student mental well-being.

Impact of artificial intelligence on pathologists' decisions: an experiment.

OBJECTIVE: The accuracy of artificial intelligence (AI) in medicine and in pathology in particular has made major progress but little is known on how much these algorithms will influence pathologists' decisions in practice. The objective of this paper is to determine the reliance of pathologists on AI and to investigate whether providing information on AI impacts this reliance. MATERIALS AND METHODS: The experiment using an online survey design. Under 3 conditions, 116 pathologists and pathology students were tasked with assessing the Gleason grade for a series of 12 prostate biopsies: (1) without AI recommendations, (2) with AI recommendations, and (3) with AI recommendations accompanied by information about the algorithm itself, specifically algorithm accuracy rate and algorithm decision-making process. RESULTS: Participant responses were significantly more accurate with the AI decision aids than without (92% vs 87%, odds ratio 13.30, P < .01). Unexpectedly, the provision of information on the algorithm made no significant difference compared to AI without information. The reliance on AI correlated with general beliefs on AI's usefulness but not with particular assessments of the AI tool offered. Decisions were made faster when AI was provided. DISCUSSION: These results suggest that pathologists are willing to rely on AI regardless of accuracy or explanations. Generalization beyond the specific tasks and explanations provided will require further studies. CONCLUSION: This study suggests that the factors that influence the reliance on AI differ in practice from beliefs expressed by clinicians in surveys. Implementation of AI in prospective settings should take individual behaviors into account.

Smartphone Alcohol Use Disorder Recovery Apps: Cross-sectional Survey of Behavioral Intention to Use.

BACKGROUND: Alcohol use disorder (AUD) carries a huge health and economic cost to society. Effective interventions exist but numerous challenges limit their adoption, especially in a pandemic context. AUD recovery apps (AUDRA) have emerged as a potential complement to in-person interventions. They are easy to access and show promising results in terms of efficacy. However, they rely on individual adoption decisions and remain underused. OBJECTIVE: The aim of this survey study is to explore the beliefs that determine the intention to use AUDRA. METHODS: We conducted a cross-sectional survey study of people with AUD. We used the Unified Theory of Acceptance and Use of Technology, which predicts use and behavioral intention to use based on performance expectancy, effort expectancy, social influence, and facilitating conditions. Participants were recruited directly from 2 sources; first, respondents at addiction treatment facilities in Ontario, Canada, were contacted in person, and they filled a paper form; second, members from AUD recovery support groups on social media were contacted and invited to fill an internet-based survey. The survey was conducted between October 2019 and June 2020. RESULTS: The final sample comprised 159 participants (124 involved in the web-based survey and 35 in the paper-based survey) self-identifying somewhat or very much with AUD. Most participants (n=136, 85.5%) were aware of AUDRA and those participants scored higher on performance expectancy, effort expectancy, and social influence. Overall, the model explains 35.4% of the variance in the behavioral intention to use AUDRA and 11.1% of the variance in use. Social influence (P=.31), especially for women (P=.23), and effort expectancy (P=.25) were key antecedents of behavioral intention. Facilitating conditions were not significant overall but were moderated by age (P=.23), suggesting that it matters for older participants. Performance expectancy did not predict behavioral intention, which is unlike many other technologies but confirms other findings associated with mobile health (mHealth). Open-ended questions suggest that privacy concerns may significantly influence the use of AUDRA. CONCLUSIONS: This study suggests that unlike many other technologies, the adoption of AUDRA is not mainly determined by utilitarian factors such as performance expectancy. Rather, effort expectancy and social influence play a key role in determining the intention to use AUDRA.

Machine learning in renal pathology.

Introduction: When assessing kidney biopsies, pathologists use light microscopy, immunofluorescence, and electron microscopy to describe and diagnose glomerular lesions and diseases. These methods can be laborious, costly, fraught with inter-observer variability, and can have delays in turn-around time. Thus, computational approaches can be designed as screening and/or diagnostic tools, potentially relieving pathologist time, healthcare resources, while also having the ability to identify novel biomarkers, including subvisual features. Methods: Here, we implement our recently published biomarker feature extraction (BFE) model along with 3 pre-trained deep learning models (VGG16, VGG19, and InceptionV3) to diagnose 3 glomerular diseases using PAS-stained digital pathology images alone. The BFE model extracts a panel of 233 explainable features related to underlying pathology, which are subsequently narrowed down to 10 morphological and microstructural texture features for classification with a linear discriminant analysis machine learning classifier. 45 patient renal biopsies (371 glomeruli) from minimal change disease (MCD), membranous nephropathy (MN), and thin-basement membrane nephropathy (TBMN) were split into training/validation and held out sets. For the 3 deep learningmodels, data augmentation and Grad-CAM were used for better performance and interpretability. Results: The BFE model showed glomerular validation accuracy of 67.6% and testing accuracy of 76.8%. All deep learning approaches had higher validation accuracies (most for VGG16 at 78.5%) but lower testing accuracies. The highest testing accuracy at the glomerular level was VGG16 at 71.9%, while at the patient-level was InceptionV3 at 73.3%. Discussion: The results highlight the potential of both traditional machine learning and deep learning-based approaches for kidney biopsy evaluation.

User Reviews of Depression App Features: Sentiment Analysis.

BACKGROUND: Mental health in general, and depression in particular, remain undertreated conditions. Mobile health (mHealth) apps offer tremendous potential to overcome the barriers to accessing mental health care and millions of depression apps have been installed and used. However, little is known about the effect of these apps on a potentially vulnerable user population and the emotional reactions that they generate, even though emotions are a key component of mental health. App reviews, spontaneously posted by the users on app stores, offer up-to-date insights into the experiences and emotions of this population and are increasingly decisive in influencing mHealth app adoption. OBJECTIVE: This study aims to investigate the emotional reactions of depression app users to different app features by systematically analyzing the sentiments expressed in app reviews. METHODS: We extracted 3261 user reviews of depression apps. The 61 corresponding apps were categorized by the features they offered (psychoeducation, medical assessment, therapeutic treatment, supportive resources, and entertainment). We then produced word clouds by features and analyzed the reviews using the Linguistic Inquiry Word Count 2015 (Pennebaker Conglomerates, Inc), a lexicon-based natural language analytical tool that analyzes the lexicons used and the valence of a text in 4 dimensions (authenticity, clout, analytic, and tone). We compared the language patterns associated with the different features of the underlying apps. RESULTS: The analysis highlighted significant differences in the sentiments expressed for the different features offered. Psychoeducation apps exhibited more clout but less authenticity (ie, personal disclosure). Medical assessment apps stood out for the strong negative emotions and the relatively negative ratings that they generated. Therapeutic treatment app features generated more positive emotions, even though user feedback tended to be less authentic but more analytical (ie, more factual). Supportive resources (connecting users to physical services and people) and entertainment apps also generated fewer negative emotions and less anxiety. CONCLUSIONS: Developers should be careful in selecting the features they offer in their depression apps. Medical assessment features may be riskier as users receive potentially disturbing feedback on their condition and may react with strong negative emotions. In contrast, offering information, contacts, or even games may be safer starting points to engage people with depression at a distance. We highlight the necessity to differentiate how mHealth apps are assessed and vetted based on the features they offer. Methodologically, this study points to novel ways to investigate the impact of mHealth apps and app features on people with mental health issues. mHealth apps exist in a rapidly changing ecosystem that is driven by user satisfaction and adoption decisions. As such, user perceptions are essential and must be monitored to ensure adoption and avoid harm to a fragile population that may not benefit from traditional health care resources.

Evaluation of an Online System for Routine Outcome Monitoring: Cross-sectional Survey Study.

BACKGROUND: The use of routine outcome monitoring (ROM) in the treatment of mental health has emerged as a method of improving psychotherapy treatment outcomes. Despite this, very few clinicians regularly use ROM in clinical practice. Online ROM has been suggested as a solution to increase adoption. OBJECTIVE: The aim of this study is to identify the influence of moving ROM online on client completion rates of self-reported outcome measures and to identify implementation and utilization barriers to online ROM by assessing clinicians' views on their experience using the online system over previous paper-based methods. METHODS: Client completion rates of self-reported outcome measures were compared pre- and postimplementation of an online system of ROM. In addition, a survey questionnaire was administered to 324 mental health service providers regarding their perception of the benefits with an online system of ROM. RESULTS: Client completion rates of self-reported measures increased from 15.62% (427/2734) to 53.98% (1267/2347) after they were moved online. Furthermore, 57% (56/98) of service providers found the new system less time-consuming than the previous paper-based ROM, and 64% (63/98) found that it helped monitor clients. However, the perceived value of the system remains in doubt as only 23% (23/98) found it helped them identify clients at risk for treatment failure, and only 18% (18/98) found it strengthened the therapeutic alliance. CONCLUSIONS: Although the current study suggests mixed results regarding service providers' views on their experience using an online system for ROM, it has identified barriers and challenges that are actionable for improvement.

The Relevance of Human Whistled Languages for the Analysis and Decoding of Dolphin Communication.

Humans use whistled communications, the most elaborate of which are commonly called "whistled languages" or "whistled speech" because they consist of a natural type of speech. The principle of whistled speech is straightforward: people articulate words while whistling and thereby transform spoken utterances by simplifying them, syllable by syllable, into whistled melodies. One of the most striking aspects of this whistled transformation of words is that it remains intelligible to trained speakers, despite a reduced acoustic channel to convey meaning. It constitutes a natural traditional means of telecommunication that permits spoken communication at long distances in a large diversity of languages of the world. Historically, birdsong has been used as a model for vocal learning and language. But conversely, human whistled languages can serve as a model for elucidating how information may be encoded in dolphin whistle communication. In this paper, we elucidate the reasons why human whistled speech and dolphin whistles are interesting to compare. Both are characterized by similar acoustic parameters and serve a common purpose of long distance communication in natural surroundings in two large brained social species. Moreover, their differences - e.g., how they are produced, the dynamics of the whistles, and the types of information they convey - are not barriers to such a comparison. On the contrary, by exploring the structure and attributes found across human whistle languages, we highlight that they can provide an important model as to how complex information is and can be encoded in what appears at first sight to be simple whistled modulated signals. Observing details, such as processes of segmentation and coarticulation, in whistled speech can serve to advance and inform the development of new approaches for the analysis of whistle repertoires of dolphins, and eventually other species. Human whistled languages and dolphin whistles could serve as complementary test benches for the development of new methodologies and algorithms for decoding whistled communication signals by providing new perspectives on how information may be encoded structurally and organizationally.

An evaluation of cleaning practices at a teaching hospital.

BACKGROUND: The COVID-19 outbreak has highlighted the role of hospital-acquired infections in spreading epidemics. Adequately cleaning surfaces in patient rooms is an essential part of this fight to reduce the spread. Traditional audits, however, are insufficient. This study assesses surface cleaning practices using ultravoilet (UV) marker technology and the extent to which this technology can help improve cleaning audits and practices. METHODS: One hundred and forty-four audits (1,235 surfaces) were retrieved. UV-marker cleaning audits conducted at a major teaching hospital in 2018 after implementing a new cleaning protocol. In addition, semi-structured interviews were conducted with cleaning staff and supervisors. RESULTS: On average, 63% of surfaces were appropriately cleaned. Toilet handles (80%) and toilet seats underside (83%) scored highest while main room sink fixtures (54%), light switch (55%), and bedrails (56%) scored lowest. Training, staffing and time constraints may play a role in low cleaning rates. DISCUSSION: The high-touch patient surfaces in the bedroom remain neglected and a potential source of infections. UV marker audits provided an objective measure of cleaning practices that managers and staff were unaware of. CONCLUSIONS: UV-markers audits can play a key role in revealing deficiencies in cleaning practices and help in raising awareness of these deficiencies and improving cleaning practices.

A Flute, Musical Bows and Bamboo Clarinets that "Speak" in the Amazon Rainforest; Speech and Music in the Gavião Language of Rondônia.

The Gavião, a native Amazonian group in Rondônia, Brazil, use three different traditional musical instruments that they identify as "speaking" ones and that are characterized by a very tight music-lyric relation through similar pitch patterns: a flute (called kotiráp), a pair of mouth bows (iridináp), and three large bamboo clarinets (totoráp), played by three different players, each one playing a single-note clarinet. They show in different ways the relation of acoustic iconicity which exists between the words of the songs' lyrics and the music played on such instruments to "sing" the songs. Linguistic analysis makes it possible to understand the phonetic and phonological nature of the iconicity. The sung speech form, being intermediate between the spoken and the instrumental forms, is useful for both learning and explaining the musical notes. In a language with distinctive tone and length, such as Gavião of Rondônia, the first question about speech that is played by musical instruments is the relation between the melodies and the supersegmental phonology of the corresponding words in sung speech and in modal spoken speech. It is influenced by the phonological possibilities of the spoken form and by the musical possibilities of the instrumental form. The description and analysis of Gavião instrumental speech and song practices are found to be a noteworthy contribution to the typology of instrumental language surrogates associated with a tone language, one that calls for a reexamination of hypotheses about which aspects of the phonological/phonetic structure can be transposed in instrumental speech and how this can be done. The role of this kind of instrumental sung speech is artistic and also practical as it contributes to maintain the oral heritage. Such practice represents a little-studied and threatened cultural heritage of the traditional substratum of the cultures of Amazonia.

Glucose point-of-care meter operators competency: An assessment checklist.

BACKGROUND AND OBJECTIVES: Glucose point-of-care testing meters are essential technology ubiquitous in hospitals. They are operated by non-specialized staff who are assessed through an auto-recertification process that is dependent on operators successfully producing expected outcomes. Alternatively, we suggest that operator practices be directly observed using a competency assessment checklist. METHOD: We designed a checklist based on literature and manufacturers' instructions and tested it by observing 30 operators at two sites (three hospitals) over two months in 2018. RESULTS: Despite all operators being auto-recertified, the checklist revealed that only 20% met the 80% threshold of compliance to standards. Moreover, the site with a POCT coordinator had a compliance rate of 82% versus 67% for the site that did not. DISCUSSION: The checklist is more reliable than auto-recertification in assessing operators' competence. It also highlights areas for process improvement and provides an opportunity to give personalized feedback to operators.

Loss of NifQ Leads to Accumulation of Porphyrins and Altered Metal-Homeostasis in Nitrogen-Fixing Symbioses.

Symbiotic nitrogen fixation between legumes and rhizobia involves a coordinated expression of many plant and bacterial genes as well as finely tuned metabolic activities of micro- and macrosymbionts. In spite of such complex interactions, symbiotic proficiency remains a resilient process, with host plants apparently capable of compensating for some deficiencies in rhizobia. What controls nodule homeostasis is still poorly understood and probably varies between plant species. In this respect, the promiscuous Sinorhizobium (Ensifer) fredii strain NGR234 has become a model to assess the relative contribution of single gene products to many symbioses. Here, we describe how a deletion in nifQ of NGR234 (strain NGRΔnifQ) makes nodules of Vigna unguiculata, V. radiata, and Macroptilium atropurpureum but not of the mimisoid tree Leucaena leucocephala, purple-red. This peculiar dark-nodule phenotype did not necessarily correlate with a decreased proficiency of NGRΔnifQ but coincided with a 20-fold or more accumulation of coproporphyrin III and uroporphyrin III in V. unguiculata nodules. Porphyrin accumulation was not restricted to plant cells infected with bacteroids but also extended to the nodule cortex. Nodule metal-homeostasis was altered but not sufficiently to prevent assembly and functioning of nitrogenase. Although the role of NifQ in donating molybdenum during assembly of nitrogenase cofactor FeMo-co makes it essential in free-living diazotrophs, our results highlight the dispensability of NifQ in many legume species.

Reducing language to rhythm: Amazonian Bora drummed language exploits speech rhythm for long-distance communication.

Many drum communication systems around the world transmit information by emulating tonal and rhythmic patterns of spoken languages in sequences of drumbeats. Their rhythmic characteristics, in particular, have not been systematically studied so far, although understanding them represents a rare occasion for providing an original insight into the basic units of speech rhythm as selected by natural speech practices directly based on beats. Here, we analyse a corpus of Bora drum communication from the northwest Amazon, which is nowadays endangered with extinction. We show that four rhythmic units are encoded in the length of pauses between beats. We argue that these units correspond to vowel-to-vowel intervals with different numbers of consonants and vowel lengths. By contrast, aligning beats with syllables, mora or only vowel length yields inconsistent results. Moreover, we also show that Bora drummed messages conventionally select rhythmically distinct markers to further distinguish words. The two phonological tones represented in drummed speech encode only few lexical contrasts. Rhythm thus appears to crucially contribute to the intelligibility of drummed Bora. Our study provides novel evidence for the role of rhythmic structures composed of vowel-to-vowel intervals in the complex puzzle concerning the redundancy and distinctiveness of acoustic features embedded in speech.

The Influence of Telepathology on Coordination Practices.

BACKGROUND: Coordination between physicians and allied professionals is essential to the effective delivery of care services and is associated with positive patient outcomes. As information technology can radically transform how professionals collaborate, both researchers and healthcare accreditation bodies are devoting a growing interest to the means of achieving better coordination. INTRODUCTION: The primary aim of this study is to explain the extent to which and how coordination practices between pathologists, technologists, and surgeons are transformed when telepathology is being implemented. MATERIALS AND METHODS: An interpretive case study was conducted. A total of 60 semistructured interviews with key participants were conducted, in addition to several days of direct observation of telepathology-based intraoperative consultations (IOCs). RESULTS: Three major kinds of transformation of coordination practices were observed. First, the telepathology system itself constrains and disrupts coordination routines, such as the presentation of slides. Second, anticipating IOC, proactively performed by the laboratory personnel in traditional settings, requires more formal requests in a telepathology context. Third, local technologists become more autonomous in performing complex macroscopy manipulations and managing the laboratory tasks traditionally performed by pathologists. CONCLUSIONS: Successful coordination of work in a telepathology-based IOC context requires that significant transformations be anticipated and accounted for. Project managers need to formalize new work processes, support the transformations in professional roles, and mitigate the major hindrances that small material changes may have on work routines.

Categorization of Natural Whistled Vowels by Naïve Listeners of Different Language Background.

Whistled speech in a non-tonal language consists of the natural emulation of vocalic and consonantal qualities in a simple modulated whistled signal. This special speech register represents a natural telecommunication system that enables high levels of sentence intelligibility by trained speakers and is not directly intelligible to naïve listeners. Yet, it is easily learned by speakers of the language that is being whistled, as attested by the current efforts of the revitalization of whistled Spanish in the Canary Islands. To better understand the relation between whistled and spoken speech perception, we look herein at how Spanish, French, and Standard Chinese native speakers, knowing nothing about whistled speech, categorized four Spanish whistled vowels. The results show that the listeners categorized differently depending on their native language. The Standard Chinese speakers demonstrated the worst performance on this task but were still able to associate a tonal whistle to vowel categories. Spanish speakers were the most accurate, and both Spanish and French participants were able to categorize the four vowels, although not as accurately as an expert whistler. These results attest that whistled speech can be used as a natural laboratory to test the perceptual processes of language.