Voice EHR: introducing multimodal audio data for health

Introduction

Artificial intelligence (AI) models trained on audio data may have the potential to rapidly perform clinical tasks, enhancing medical decision-making and potentially improving outcomes through early detection. Existing technologies depend on limited datasets collected with expensive recording equipment in high-income countries, which challenges deployment in resource-constrained, high-volume settings where audio data may have a profound impact on health equity.

Methods

This report introduces a novel protocol for audio data collection and a corresponding application that captures health information through guided questions.

Results

To demonstrate the potential of Voice EHR as a biomarker of health, initial experiments on data quality and multiple case studies are presented in this report. Large language models (LLMs) were used to compare transcribed Voice EHR data with data (from the same patients) collected through conventional techniques like multiple choice questions. Information contained in the Voice EHR samples was consistently rated as equally or more relevant to a health evaluation.

Discussion

The HEAR application facilitates the collection of an audio electronic health record ("Voice EHR") that may contain complex biomarkers of health from conventional voice/respiratory features, speech patterns, and spoken language with semantic meaning and longitudinal context-potentially compensating for the typical limitations of unimodal clinical datasets.

The doctor will polygraph you now: ethical concerns with AI for fact-checking patients

Artificial intelligence (AI) methods have been proposed for the prediction of social behaviors which could be reasonably understood from patient-reported information. This raises novel ethical concerns about respect, privacy, and control over patient data. Ethical concerns surrounding clinical AI systems for social behavior verification can be divided into two main categories: (1) the potential for inaccuracies/biases within such systems, and (2) the impact on trust in patient-provider relationships with the introduction of automated AI systems for "fact-checking", particularly in cases where the data/models may contradict the patient. Additionally, this report simulated the misuse of a verification system using patient voice samples and identified a potential LLM bias against patient-reported information in favor of multi-dimensional data and the outputs of other AI methods (i.e., "AI self-trust"). Finally, recommendations were presented for mitigating the risk that AI verification methods will cause harm to patients or undermine the purpose of the healthcare system.

The doctor will polygraph you now

Artificial intelligence (AI) methods have been proposed for the prediction of social behaviors that could be reasonably understood from patient-reported information. This raises novel ethical concerns about respect, privacy, and control over patient data. Ethical concerns surrounding clinical AI systems for social behavior verification can be divided into two main categories: (1) the potential for inaccuracies/biases within such systems, and (2) the impact on trust in patient-provider relationships with the introduction of automated AI systems for "fact-checking", particularly in cases where the data/models may contradict the patient. Additionally, this report simulated the misuse of a verification system using patient voice samples and identified a potential LLM bias against patient-reported information in favor of multi-dimensional data and the outputs of other AI methods (i.e., "AI self-trust"). Finally, recommendations were presented for mitigating the risk that AI verification methods will cause harm to patients or undermine the purpose of the healthcare system.

Evaluation of a Cascaded Deep Learning-based Algorithm for Prostate Lesion Detection at Biparametric MRI

Background Multiparametric MRI (mpMRI) improves prostate cancer (PCa) detection compared with systematic biopsy, but its interpretation is prone to interreader variation, which results in performance inconsistency. Artificial intelligence (AI) models can assist in mpMRI interpretation, but large training data sets and extensive model testing are required. Purpose To evaluate a biparametric MRI AI algorithm for intraprostatic lesion detection and segmentation and to compare its performance with radiologist readings and biopsy results. Materials and Methods This secondary analysis of a prospective registry included consecutive patients with suspected or known PCa who underwent mpMRI, US-guided systematic biopsy, or combined systematic and MRI/US fusion-guided biopsy between April 2019 and September 2022. All lesions were prospectively evaluated using Prostate Imaging Reporting and Data System version 2.1. The lesion- and participant-level performance of a previously developed cascaded deep learning algorithm was compared with histopathologic outcomes and radiologist readings using sensitivity, positive predictive value (PPV), and Dice similarity coefficient (DSC). Results A total of 658 male participants (median age, 67 years [IQR, 61-71 years]) with 1029 MRI-visible lesions were included. At histopathologic analysis, 45% (294 of 658) of participants had lesions of International Society of Urological Pathology (ISUP) grade group (GG) 2 or higher. The algorithm identified 96% (282 of 294; 95% CI: 94%, 98%) of all participants with clinically significant PCa, whereas the radiologist identified 98% (287 of 294; 95% CI: 96%, 99%; P = .23). The algorithm identified 84% (103 of 122), 96% (152 of 159), 96% (47 of 49), 95% (38 of 40), and 98% (45 of 46) of participants with ISUP GG 1, 2, 3, 4, and 5 lesions, respectively. In the lesion-level analysis using radiologist ground truth, the detection sensitivity was 55% (569 of 1029; 95% CI: 52%, 58%), and the PPV was 57% (535 of 934; 95% CI: 54%, 61%). The mean number of false-positive lesions per participant was 0.61 (range, 0-3). The lesion segmentation DSC was 0.29. Conclusion The AI algorithm detected cancer-suspicious lesions on biparametric MRI scans with a performance comparable to that of an experienced radiologist. Moreover, the algorithm reliably predicted clinically significant lesions at histopathologic examination. ClinicalTrials.gov Identifier: NCT03354416 © RSNA, 2024 Supplemental material is available for this article.

A Novel Magnetic Resonance Imaging/Ultrasound Fusion Prostate Biopsy Technique Using Transperineal Ultrasound: An Initial Experience

OBJECTIVE

To report an initial experience with a novel, "fully" transperineal (TP) prostate fusion biopsy using an unconstrained ultrasound transducer placed on the perineal skin to guide biopsy needles inserted via a TP approach.

METHODS

Conventional TP prostate biopsies for detection of prostate cancer have been performed with transrectal ultrasound, requiring specialized hardware, imposing limitations on needle trajectory, and contributing to patient discomfort. Seventy-six patients with known or suspected prostate cancer underwent 78 TP biopsy sessions in an academic center between June 2018 and April 2022 and were included in this study. These patients underwent TP prostate fusion biopsy using a grid or freehand device with transrectal ultrasound as well as TP prostate fusion biopsy using TP ultrasound in the same session. Per-session and per-lesion cancer detection rates were compared for conventional and fully TP biopsies using Fisher exact and McNemar's tests.

RESULTS

After a refinement period in 30 patients, 92 MRI-visible prostate lesions were sampled in 46 subsequent patients, along with repeat biopsies in 2 of the 30 patients from the refinement period. Grade group ≥2 cancer was diagnosed in 24/92 lesions (26%) on conventional TP biopsy (17 lesions with grid, 7 with freehand device), and in 25/92 lesions (27%) on fully TP biopsy (P = 1.00), with a 73/92 (79%) rate of agreement for grade group ≥2 cancer between the two methods.

CONCLUSION

Fully TP biopsy is feasible and may detect prostate cancer with detection rates comparable to conventional TP biopsy.

Deep Learning-Based T2-Weighted MR Image Quality Assessment and Its Impact on Prostate Cancer Detection Rates

BACKGROUND

Image quality evaluation of prostate MRI is important for successful implementation of MRI into localized prostate cancer diagnosis.

PURPOSE

To examine the impact of image quality on prostate cancer detection using an in-house previously developed artificial intelligence (AI) algorithm.

STUDY TYPE

Retrospective.

SUBJECTS

615 consecutive patients (median age 67 [interquartile range [IQR]: 61-71] years) with elevated serum PSA (median PSA 6.6 [IQR: 4.6-9.8] ng/mL) prior to prostate biopsy.

FIELD STRENGTH/SEQUENCE

3.0T/T2-weighted turbo-spin-echo MRI, high b-value echo-planar diffusion-weighted imaging, and gradient recalled echo dynamic contrast-enhanced.

ASSESSMENTS

Scans were prospectively evaluated during clinical readout using PI-RADSv2.1 by one genitourinary radiologist with 17 years of experience. For each patient, T2-weighted images (T2WIs) were classified as high-quality or low-quality based on evaluation of both general distortions (eg, motion, distortion, noise, and aliasing) and perceptual distortions (eg, obscured delineation of prostatic capsule, prostatic zones, and excess rectal gas) by a previously developed in-house AI algorithm. Patients with PI-RADS category 1 underwent 12-core ultrasound-guided systematic biopsy while those with PI-RADS category 2-5 underwent combined systematic and targeted biopsies. Patient-level cancer detection rates (CDRs) were calculated for clinically significant prostate cancer (csPCa, International Society of Urological Pathology Grade Group ≥2) by each biopsy method and compared between high- and low-quality images in each PI-RADS category.

STATISTICAL TESTS

Fisher's exact test. Bootstrap 95% confidence intervals (CI). A P value <0.05 was considered statistically significant.

RESULTS

385 (63%) T2WIs were classified as high-quality and 230 (37%) as low-quality by AI. Targeted biopsy with high-quality T2WIs resulted in significantly higher clinically significant CDR than low-quality images for PI-RADS category 4 lesions (52% [95% CI: 43-61] vs. 32% [95% CI: 22-42]). For combined biopsy, there was no significant difference in patient-level CDRs for PI-RADS 4 between high- and low-quality T2WIs (56% [95% CI: 47-64] vs. 44% [95% CI: 34-55]; P = 0.09).

DATA CONCLUSION

Higher quality T2WIs were associated with better targeted biopsy clinically significant cancer detection performance for PI-RADS 4 lesions. Combined biopsy might be needed when T2WI is lower quality.

LEVEL OF EVIDENCE

2 TECHNICAL EFFICACY: Stage 1.

Evaluation of a Deep Learning-based Algorithm for Post-Radiotherapy Prostate Cancer Local Recurrence Detection Using Biparametric MRI

OBJECTIVE

To evaluate a biparametric MRI (bpMRI)-based artificial intelligence (AI) model for the detection of local prostate cancer (PCa) recurrence in patients with radiotherapy history.

MATERIALS AND METHODS

This study included post-radiotherapy patients undergoing multiparametric MRI and subsequent MRI/US fusion-guided and/or systematic biopsy. Histopathology results were used as ground truth. The recurrent cancer detection sensitivity of a bpMRI-based AI model, which was developed on a large dataset to primarily identify lesions in treatment-naïve patients, was compared to a prospective radiologist assessment using the Wald test. Subanalysis was conducted on patients stratified by the treatment modality (external beam radiation treatment [EBRT] and brachytherapy) and the prostate volume quartiles.

RESULTS

Of the 62 patients included (median age = 70 years; median PSA = 3.51 ng/ml; median prostate volume = 27.55 ml), 56 recurrent PCa foci were identified within 46 patients. The AI model detected 40 lesions in 35 patients. The AI model performance was lower than the prospective radiology interpretation (Rad) on a patient-(AI: 76.1% vs. Rad: 91.3%, p = 0.02) and lesion-level (AI: 71.4% vs. Rad: 87.5%, p = 0.01). The mean number of false positives per patient was 0.35 (range: 0-2). The AI model performance was higher in EBRT group both on patient-level (EBRT: 81.5% [22/27] vs. brachytherapy: 68.4% [13/19]) and lesion-level (EBRT: 79.4% [27/34] vs. brachytherapy: 59.1% [13/22]). In patients with gland volumes >34 ml (n = 25), detection sensitivities were 100% (11/11) and 94.1% (16/17) on patient- and lesion-level, respectively.

CONCLUSION

The reported bpMRI-based AI model detected the majority of locally recurrent prostate cancer after radiotherapy. Further testing including external validation of this model is warranted prior to clinical implementation.