BACKGROUND: Vocal biomarkers, derived from acoustic analysis of vocal characteristics, offer noninvasive avenues for medical screening, diagnostics, and monitoring. Previous research demonstrated the feasibility of predicting type 2 diabetes mellitus through acoustic analysis of smartphone-recorded speech. Building upon this work, this study explores the impact of audio data compression on acoustic vocal biomarker development, which is critical for broader applicability in health care.
OBJECTIVE: The objective of this research is to analyze how common audio compression algorithms (MP3, M4A, and WMA) applied by 3 different conversion tools at 2 bitrates affect features crucial for vocal biomarker detection.
METHODS: The impact of audio data compression on acoustic vocal biomarker development was investigated using uncompressed voice samples converted into MP3, M4A, and WMA formats at 2 bitrates (320 and 128 kbps) with MediaHuman (MH) Audio Converter, WonderShare (WS) UniConverter, and Fast Forward Moving Picture Experts Group (FFmpeg). The data set comprised recordings from 505 participants, totaling 17,298 audio files, collected using a smartphone. Participants recorded a fixed English sentence up to 6 times daily for up to 14 days. Feature extraction, including pitch, jitter, intensity, and Mel-frequency cepstral coefficients (MFCCs), was conducted using Python and Parselmouth. The Wilcoxon signed rank test and the Bonferroni correction for multiple comparisons were used for statistical analysis.
RESULTS: In this study, 36,970 audio files were initially recorded from 505 participants, with 17,298 recordings meeting the fixed sentence criteria after screening. Differences between the audio conversion software, MH, WS, and FFmpeg, were notable, impacting compression outcomes such as constant or variable bitrates. Analysis encompassed diverse data compression formats and a wide array of voice features and MFCCs. Wilcoxon signed rank tests yielded P values, with those below the Bonferroni-corrected significance level indicating significant alterations due to compression. The results indicated feature-specific impacts of compression across formats and bitrates. MH-converted files exhibited greater resilience compared to WS-converted files. Bitrate also influenced feature stability, with 38 cases affected uniquely by a single bitrate. Notably, voice features showed greater stability than MFCCs across conversion methods.
CONCLUSIONS: Compression effects were found to be feature specific, with MH and FFmpeg showing greater resilience. Some features were consistently affected, emphasizing the importance of understanding feature resilience for diagnostic applications. Considering the implementation of vocal biomarkers in health care, finding features that remain consistent through compression for data storage or transmission purposes is valuable. Focused on specific features and formats, future research could broaden the scope to include diverse features, real-time compression algorithms, and various recording methods. This study enhances our understanding of audio compression\'s influence on voice features and MFCCs, providing insights for developing applications across fields. The research underscores the significance of feature stability in working with compressed audio data, laying a foundation for informed voice data use in evolving technological landscapes.

BACKGROUND: The use of artificial intelligence (AI) can revolutionize health care, but this raises risk concerns. It is therefore crucial to understand how clinicians trust and accept AI technology. Gastroenterology, by its nature of being an image-based and intervention-heavy specialty, is an area where AI-assisted diagnosis and management can be applied extensively.
OBJECTIVE: This study aimed to study how gastroenterologists or gastrointestinal surgeons accept and trust the use of AI in computer-aided detection (CADe), computer-aided characterization (CADx), and computer-aided intervention (CADi) of colorectal polyps in colonoscopy.
METHODS: We conducted a web-based questionnaire from November 2022 to January 2023, involving 5 countries or areas in the Asia-Pacific region. The questionnaire included variables such as background and demography of users; intention to use AI, perceived risk; acceptance; and trust in AI-assisted detection, characterization, and intervention. We presented participants with 3 AI scenarios related to colonoscopy and the management of colorectal polyps. These scenarios reflect existing AI applications in colonoscopy, namely the detection of polyps (CADe), characterization of polyps (CADx), and AI-assisted polypectomy (CADi).
RESULTS: In total, 165 gastroenterologists and gastrointestinal surgeons responded to a web-based survey using the structured questionnaire designed by experts in medical communications. Participants had a mean age of 44 (SD 9.65) years, were mostly male (n=116, 70.3%), and mostly worked in publicly funded hospitals (n=110, 66.67%). Participants reported relatively high exposure to AI, with 111 (67.27%) reporting having used AI for clinical diagnosis or treatment of digestive diseases. Gastroenterologists are highly interested to use AI in diagnosis but show different levels of reservations in risk prediction and acceptance of AI. Most participants (n=112, 72.72%) also expressed interest to use AI in their future practice. CADe was accepted by 83.03% (n=137) of respondents, CADx was accepted by 78.79% (n=130), and CADi was accepted by 72.12% (n=119). CADe and CADx were trusted by 85.45% (n=141) of respondents and CADi was trusted by 72.12% (n=119). There were no application-specific differences in risk perceptions, but more experienced clinicians gave lesser risk ratings.
CONCLUSIONS: Gastroenterologists reported overall high acceptance and trust levels of using AI-assisted colonoscopy in the management of colorectal polyps. However, this level of trust depends on the application scenario. Moreover, the relationship among risk perception, acceptance, and trust in using AI in gastroenterology practice is not straightforward.

OBJECTIVE: Few studies have evaluated the adenoma detection rate (ADR) of colonoscopy with texture and color enhancement imaging (TXI), a novel image-enhancing technology. This study compares the detection of colorectal polyps using TXI to that using white light imaging (WLI).
METHODS: This single-center retrospective study used propensity-matched scoring based on the patients\' baseline characteristics (age, sex, indication, bowel preparation, endoscopist, colonoscope type, and withdrawal time) to compare the results of patients who underwent chromoendoscopy using WLI or TXI at the Toyoshima Endoscopy Clinic. The differences in polyp detection rates and the mean number of detected polyps per colonoscopy were determined between the TXI and WLI groups.
RESULTS: After propensity score matching, 1970 patients were enrolled into each imaging modality group. The mean patient age was 57.2 ± 12.5 years, and 44.5% of the cohort were men. The ADR was higher in the TXI group than in the WLI group (55.0% vs 49.4%, odds ratio: 1.25). High-risk ADR were more common in the TXI group than in the WLI group (17.6% vs 12.8%; OR: 1.45). The mean number of adenomas per colonoscopy (APC) was higher in the TXI group than in the WLI group (1.187 vs 0.943, OR: 1.12). APC with a flat morphology (1.093 vs 0.848, OR: 1.14) and APC of <6 mm (0.992 vs 0.757, OR: 1.16) were higher in the TXI group than in the WLI group.
CONCLUSIONS: Compared to WLI, TXI improved the ADR in patients who underwent chromoendoscopy based on actual clinical data.

BACKGROUND: Testing for SARS-CoV-2 is essential to provide early COVID-19 treatment for people at high risk of severe illness and to limit the spread of infection in society. Proper upper respiratory specimen collection is the most critical step in the diagnosis of the SARS-CoV-2 virus in public settings, and throat swabs were the preferred specimens used for mass testing in many countries during the COVID-19 pandemic. However, there is still a discussion about whether throat swabs have a high enough sensitivity for SARS-CoV-2 diagnostic testing, as previous studies have reported a large variability in the sensitivity from 52% to 100%. Many previous studies exploring the diagnostic accuracy of throat swabs lack a detailed description of the sampling technique, which makes it difficult to compare the different diagnostic accuracy results. Some studies perform a throat swab by only collecting specimens from the posterior oropharyngeal wall, while others also include a swab of the palatine tonsils for SARS-CoV-2 testing. However, studies suggest that the palatine tonsils could have a tissue tropism for SARS-CoV-2 that may improve the SARS-CoV-2 detection during sampling. This may explain the variation of sensitivity reported, but no clinical studies have yet explored the differences in sensitivity and patient discomfort whether the palatine tonsils are included during the throat swab or not.
OBJECTIVE: The objective of this study is to examine the sensitivity and patient discomfort of a throat swab including the palatine tonsils compared to only swabbing the posterior oropharyngeal wall in molecular testing for SARS-CoV-2.
METHODS: We will conduct a randomized controlled study to compare the molecular detection rate of SARS-CoV-2 by a throat swab performed from the posterior oropharyngeal wall and the palatine tonsils (intervention group) or the posterior oropharyngeal wall only (control group). Participants will be randomized in a 1:1 ratio. All participants fill out a baseline questionnaire upon enrollment in the trial, examining their reason for being tested, symptoms, and previous tonsillectomy. A follow-up questionnaire will be sent to participants to explore the development of symptoms after testing.
RESULTS: A total of 2315 participants were enrolled in this study between November 10, 2022, and December 22, 2022. The results from the follow-up questionnaire are expected to be completed at the beginning of 2024.
CONCLUSIONS: This randomized clinical trial will provide us with information about whether throat swabs including specimens from the palatine tonsils will improve the diagnostic sensitivity for SARS-CoV-2 molecular detection. These results can, therefore, be used to improve future testing recommendations and provide additional information about tissue tropism for SARS-CoV-2.
BACKGROUND: ClinicalTrials.gov NCT05611203; https://clinicaltrials.gov/study/NCT05611203.
UNASSIGNED: DERR1-10.2196/47446.

BACKGROUND: This multicenter, double-blinded, randomized controlled trial (RCT) aims to assess the impact of an artificial intelligence (AI)-based model on the efficacy of intracranial aneurysm detection in CT angiography (CTA) and its influence on patients\' short-term and long-term outcomes.
METHODS: Study design: Prospective, multicenter, double-blinded RCT.
METHODS: The model was designed for the automatic detection of intracranial aneurysms from original CTA images.
METHODS: Adult inpatients and outpatients who are scheduled for head CTA scanning. Randomization groups: (1) Experimental Group: Head CTA interpreted by radiologists with the assistance of the True-AI-integrated intracranial aneurysm diagnosis strategy (True-AI arm). (2) Control Group: Head CTA interpreted by radiologists with the assistance of the Sham-AI-integrated intracranial aneurysm diagnosis strategy (Sham-AI arm).
METHODS: Block randomization, stratified by center, gender, and age group.
METHODS: Coprimary outcomes of superiority in patient-level sensitivity and noninferiority in specificity for the True-AI arm to the Sham-AI arm in intracranial aneurysms.
RESULTS: Diagnostic performance for other intracranial lesions, detection rates, workload of CTA interpretation, resource utilization, treatment-related clinical events, aneurysm-related events, quality of life, and cost-effectiveness analysis.
METHODS: Study participants and participating radiologists will be blinded to the intervention.
METHODS: Based on our pilot study, the patient-level sensitivity is assumed to be 0.65 for the Sham-AI arm and 0.75 for the True-AI arm, with specificities of 0.90 and 0.88, respectively. The prevalence of intracranial aneurysms for patients undergoing head CTA in the hospital is approximately 12%. To establish superiority in sensitivity and noninferiority in specificity with a margin of 5% using a one-sided α = 0.025 to ensure that the power of coprimary endpoint testing reached 0.80 and a 5% attrition rate, the sample size was determined to be 6450 in a 1:1 allocation to True-AI or Sham-AI arm.
CONCLUSIONS: The study will determine the precise impact of the AI system on the detection performance for intracranial aneurysms in a double-blinded design and following the real-world effects on patients\' short-term and long-term outcomes.
BACKGROUND: This trial has been registered with the NIH, U.S. National Library of Medicine at ClinicalTrials.gov, ID: NCT06118840 . Registered 11 November 2023.

Aphid infestations are one of the primary causes of extensive damage to wheat and sorghum fields and are one of the most common vectors for plant viruses, resulting in significant agricultural yield losses. To address this problem, farmers often employ the inefficient use of harmful chemical pesticides that have negative health and environmental impacts. As a result, a large amount of pesticide is wasted on areas without significant pest infestation. This brings to attention the urgent need for an intelligent autonomous system that can locate and spray sufficiently large infestations selectively within the complex crop canopies. We have developed a large multi-scale dataset for aphid cluster detection and segmentation, collected from actual sorghum fields and meticulously annotated to include clusters of aphids. Our dataset comprises a total of 54,742 image patches, showcasing a variety of viewpoints, diverse lighting conditions, and multiple scales, highlighting its effectiveness for real-world applications. In this study, we trained and evaluated four real-time semantic segmentation models and three object detection models specifically for aphid cluster segmentation and detection. Considering the balance between accuracy and efficiency, Fast-SCNN delivered the most effective segmentation results, achieving 80.46% mean precision, 81.21% mean recall, and 91.66 frames per second (FPS). For object detection, RT-DETR exhibited the best overall performance with a 61.63% mean average precision (mAP), 92.6% mean recall, and 72.55 on an NVIDIA V100 GPU. Our experiments further indicate that aphid cluster segmentation is more suitable for assessing aphid infestations than using detection models.

UNASSIGNED: Delirium is a serious neuropsychiatric syndrome with adverse outcomes, which is common but often undiagnosed in terminally ill people. The 4 \'A\'s test or 4AT (www.the4AT.com), a brief delirium detection tool, is widely used in general settings, but validation studies in terminally ill people are lacking.
UNASSIGNED: To determine the diagnostic accuracy of the 4AT in detecting delirium in terminally ill people, who are hospice inpatients.
UNASSIGNED: A diagnostic test accuracy study in which participants underwent the 4AT and a reference standard based on the fifth edition of the Diagnostic and Statistical Manual of Mental Disorders. The reference standard was informed by Delirium Rating Scale Revised-98 and tests assessing arousal and attention. Assessments were conducted in random order by pairs of independent raters, blinded to the results of the other assessment.
UNASSIGNED: Two hospice inpatient units in Scotland, UK. Participants were 148 hospice inpatients aged ⩾18 years.
UNASSIGNED: A total of 137 participants completed both assessments. Three participants had an indeterminate reference standard diagnosis and were excluded, yielding a final sample of 134. Mean age was 70.3 (SD = 10.6) years. About 33% (44/134) had reference standard delirium. The 4AT had a sensitivity of 89% (95% CI 79%-98%) and a specificity of 94% (95% CI 90%-99%). The area under the receiver operating characteristic curve was 0.97 (95% CI 0.94-1).
UNASSIGNED: The results of this validation study support use of the 4AT as a delirium detection tool in hospice inpatients, and add to the literature evaluating methods of delirium detection in palliative care settings.
UNASSIGNED: ISCRTN 97417474.

UNASSIGNED: Peritonitis is the leading complication of peritoneal dialysis (PD). Patients are instructed to seek care promptly for signs (cloudy effluent) or symptoms (abdominal pain), and earlier treatment improves outcomes. The CloudCath Peritoneal Dialysis Drain Set Monitoring (CloudCath) system monitors turbidity in dialysis effluent and sends notifications of changes signaling possible peritonitis.
UNASSIGNED: We conducted this single-arm, open-label, multicenter study of CloudCath system use during PD. We deactivated system notifications to participants and investigators, who followed standard-of-care for peritonitis signs and symptoms. Effectiveness endpoints measured time between CloudCath system notifications and peritonitis events using International Society of Peritoneal Dialysis (ISPD) criteria.
UNASSIGNED: Two hundred forty-three participants used the CloudCath system for 178.8 patient-years. Of 71 potential peritonitis events, 51 events (0.29 per patient-year) met ISPD white blood cell (WBC) count criteria. The system triggered notifications for 41 of 51 events (80.4%), with a median lead time of 2.6 days (10%-90% range, -1.0 to 15.7; P < 0.0001). Excluding 6 peritonitis events that occurred when the system was not in use, the system triggered notifications for 41 of 45 events (91.1%), with a median lead time of 3.0 days (10%-90% range, -0.5 to 18.8; P < 0.0001). Of the 0.78 notifications per patient-year, the majority were peritonitis events or nonperitonitis events such as exit site and tunnel infections or catheter/cycler issues.
UNASSIGNED: The CloudCath system detected peritonitis events during PD several days earlier than the current standard-of-care and has the capacity to send notifications that could expedite peritonitis diagnosis and treatment.

OBJECTIVE: Postcolonoscopy colorectal cancer incidence and mortality rates are higher for endoscopists with low polyp detection rates. Using the UK\'s National Endoscopy Database (NED), which automatically captures real-time data, we assessed if providing feedback of case-mix-adjusted mean number of polyps (aMNP), as a key performance indicator, improved endoscopists\' performance. Feedback was delivered via a theory-informed, evidence-based audit and feedback intervention.
METHODS: This multicenter, prospective, NED Automated Performance Reports to Improve Quality Outcomes Trial randomized National Health Service endoscopy centers to intervention or control. Intervention-arm endoscopists were e-mailed tailored monthly reports automatically generated within NED, informed by qualitative interviews and behavior change theory. The primary outcome was endoscopists\' aMNP during the 9-month intervention.
RESULTS: From November 2020 to July 2021, 541 endoscopists across 36 centers (19 intervention; 17 control) performed 54,770 procedures during the intervention, and 15,960 procedures during the 3-month postintervention period. Comparing the intervention arm with the control arm, endoscopists during the intervention period: aMNP was nonsignificantly higher (7%; 95% CI, -1% to 14%; P = .08). The unadjusted MNP (10%; 95% CI, 1%-20%) and polyp detection rate (10%; 95% CI, 4%-16%) were significantly higher. Differences were not maintained in the postintervention period. In the intervention arm, endoscopists accessing NED Automated Performance Reports to Improve Quality Outcomes Trial webpages had a higher aMNP than those who did not (aMNP, 118 vs 102; P = .03).
CONCLUSIONS: Although our automated feedback intervention did not increase aMNP significantly in the intervention period, MNP and polyp detection rate did improve significantly. Engaged endoscopists benefited most and improvements were not maintained postintervention; future work should address engagement in feedback and consider the effectiveness of continuous feedback.
BACKGROUND:  www.isrctn.org ISRCTN11126923 .

BACKGROUND: Early disease detection is emphasized within ophthalmology now more than ever, and as a result, clinicians and innovators turn to deep learning to expedite accurate diagnosis and mitigate treatment delay. Efforts concentrate on the creation of deep learning systems that analyze clinical image data to detect disease-specific features with maximum sensitivity. Moreover, these systems hold promise of early accurate diagnosis and treatment of patients with common progressive diseases. DenseNet, ResNet, and VGG-16 are among a few of the deep learning Convolutional Neural Network (CNN) algorithms that have been introduced and are being investigated for potential application within ophthalmology.
METHODS: In this study, the authors sought to create and evaluate a novel ensembled deep learning CNN model that analyzes a dataset of shuffled retinal color fundus images (RCFIs) from eyes with various ocular disease features (cataract, glaucoma, diabetic retinopathy). Our aim was to determine (1) the relative performance of our finalized model in classifying RCFIs according to disease and (2) the diagnostic potential of the finalized model to serve as a screening test for specific diseases (cataract, glaucoma, diabetic retinopathy) upon presentation of RCFIs with diverse disease manifestations.
RESULTS: We found adding convolutional layers to an existing VGG-16 model, which was named as a proposed model in this article that, resulted in significantly increased performance with 98% accuracy (p<0.05), including good diagnostic potential for binary disease detection in cataract, glaucoma, diabetic retinopathy.
CONCLUSIONS: The proposed model was found to be suitable and accurate for a decision support system in Ophthalmology Clinical Framework.