Clinicopathologic Heterogeneity and Glial Activation Patterns in Alzheimer Disease

Importance

Factors associated with clinical heterogeneity in Alzheimer disease (AD) lay along a continuum hypothesized to associate with tangle distribution and are relevant for understanding glial activation considerations in therapeutic advancement.

Objectives

To examine clinicopathologic and neuroimaging characteristics of disease heterogeneity in AD along a quantitative continuum using the corticolimbic index (CLix) to account for individuality of spatially distributed tangles found at autopsy.

Design, Setting, and Participants

This cross-sectional study was a retrospective medical record review performed on the Florida Autopsied Multiethnic (FLAME) cohort accessioned from 1991 to 2020. Data were analyzed from December 2022 to December 2023. Structural magnetic resonance imaging (MRI) and tau positron emission tomography (PET) were evaluated in an independent neuroimaging group. The FLAME cohort includes 2809 autopsied individuals; included in this study were neuropathologically diagnosed AD cases (FLAME-AD). A digital pathology subgroup of FLAME-AD cases was derived for glial activation analyses.

Main Outcomes and Measures

Clinicopathologic factors of heterogeneity that inform patient history and neuropathologic evaluation of AD; CLix score (lower, relative cortical predominance/hippocampal sparing vs higher, relative cortical sparing/limbic predominant cases); neuroimaging measures (ie, structural MRI and tau-PET).

Results

Of the 2809 autopsied individuals in the FLAME cohort, 1361 neuropathologically diagnosed AD cases were evaluated. A digital pathology subgroup included 60 FLAME-AD cases. The independent neuroimaging group included 93 cases. Among the 1361 FLAME-AD cases, 633 were male (47%; median [range] age at death, 81 [54-96] years) and 728 were female (53%; median [range] age at death, 81 [53-102] years). A younger symptomatic onset (Spearman ρ = 0.39, P < .001) and faster decline on the Mini-Mental State Examination (Spearman ρ = 0.27; P < .001) correlated with a lower CLix score in FLAME-AD series. Cases with a nonamnestic syndrome had lower CLix scores (median [IQR], 13 [9-18]) vs not (median [IQR], 21 [15-27]; P < .001). Hippocampal MRI volume (Spearman ρ = -0.45; P < .001) and flortaucipir tau-PET uptake in posterior cingulate and precuneus cortex (Spearman ρ = -0.74; P < .001) inversely correlated with CLix score. Although AD cases with a CLix score less than 10 had higher cortical tangle count, we found lower percentage of CD68-activated microglia/macrophage burden (median [IQR], 0.46% [0.32%-0.75%]) compared with cases with a CLix score of 10 to 30 (median [IQR], 0.75% [0.51%-0.98%]) and on par with a CLix score of 30 or greater (median [IQR], 0.40% [0.32%-0.57%]; P = .02).

Conclusions and Relevance

Findings show that AD heterogeneity exists along a continuum of corticolimbic tangle distribution. Reduced CD68 burden may signify an underappreciated association between tau accumulation and microglia/macrophages activation that should be considered in personalized therapy for immune dysregulation.

Cancer Detection Rate and Abnormal Interpretation Rate of Prostate MRI in Patients With Low-Grade Cancer

PURPOSE

The aim of this study was to evaluate the utility of cancer detection rate (CDR) and abnormal interpretation rate (AIR) in prostate MRI for patients with low-grade prostate cancer (PCa).

METHODS

This three-center retrospective study included patients who underwent prostate MRI from 2017 to 2021 with known low-grade PCa (Gleason score 6) without prior treatment. Patient-level highest Prostate Imaging Reporting & Data System (PI-RADS®) score and pathologic diagnosis within 1 year after MRI were used to evaluate the diagnostic performance of prostate MRI in detecting clinically significant PCa (csPCa; Gleason score ≥ 7). The metrics AIR, CDR, and CDR adjusted for pathologic confirmation rate were calculated. Radiologist-level AIR-CDR plots were shown. Simulation AIR-CDR lines were created to assess the effects of different diagnostic performances of prostate MRI and the prevalence of csPCa.

RESULTS

A total of 3,207 examinations were interpreted by 33 radiologists. Overall AIR, CDR, and CDR adjusted for pathologic confirmation rate at PI-RADS 3 to 5 (PI-RADS 4 and 5) were 51.7% (36.5%), 22.1% (18.8%), and 30.7% (24.6%), respectively. Radiologist-level AIR and CDR at PI-RADS 3 to 5 (PI-RADS 4 and 5) were in the 36.8% to 75.6% (21.9%-57.5%) range and the 16.3%-28.7% (10.9%-26.5%) range, respectively. In the simulation, changing parameters of diagnostic performance or csPCa prevalence shifted the AIR-CDR line.

CONCLUSIONS

The authors propose CDR and AIR as performance metrics in prostate MRI and report reference performance values in patients with known low-grade PCa. There was variability in radiologist-level AIR and CDR. Combined use of AIR and CDR could provide meaningful feedback for radiologists to improve their performance by showing relative performance to other radiologists.

Cancer Detection Rate and Abnormal Interpretation Rate of Prostate MRI Performed for Clinical Suspicion of Prostate Cancer

PURPOSE

To report cancer detection rate (CDR) and abnormal interpretation rate (AIR) in prostate MRI performed for clinical suspicion of prostate cancer (PCa).

MATERIALS AND METHODS

This retrospective single-institution, three-center study included patients who underwent MRI for clinical suspicion of PCa between 2017 and 2021. Patients with known PCa were excluded. Patient-level Prostate Imaging-Reporting and Data System (PI-RADS) score was extracted from the radiology report. AIR was defined as number of abnormal MRI (PI-RADS score 3-5) / total number of MRIs. CDR was defined as number of clinically significant PCa (csPCa: Gleason score ≥7) detected at abnormal MRI / total number of MRI. AIR, CDR, and CDR adjusted for pathology confirmation rate were calculated for each of three centers and pre-MRI biopsy status (biopsy-naive and previous negative biopsy).

RESULTS

A total of 9,686 examinations (8,643 unique patients) were included. AIR, CDR, and CDR adjusted for pathology confirmation rate were 45.4%, 23.8%, and 27.6% for center I; 47.2%, 20.0%, and 22.8% for center II; and 42.3%, 27.2%, and 30.1% for center III, respectively. Pathology confirmation rate ranged from 81.6% to 88.0% across three centers. AIR and CDR for biopsy-naive patients were 45.5% to 52.6% and 24.2% to 33.5% across three centers, respectively, and those for previous negative biopsy were 27.2% to 39.8% and 11.7% to 14.2% across three centers, respectively.

CONCLUSION

We reported CDR and AIR in prostate MRI for clinical suspicion of PCa. CDR needs to be adjusted for pathology confirmation rate and pre-MRI biopsy status for interfacility comparison.

Photon-Counting Detector Computed Tomography Versus Energy-Integrating Detector Computed Tomography for Coronary Artery Calcium Quantitation

OBJECTIVES

Photon-counting detector (PCD) computed tomography (CT) offers improved spatial and contrast resolution, which can impact quantitative measurements. This work aims to determine in human subjects the effect of dual-source PCD-CT on the quantitation of coronary artery calcification (CAC) compared with dual-source energy-integrating detector (EID) CT in both 1- and 3-mm images.

METHODS

This prospective study enrolled patients receiving a clinical EID-CT CAC examination to undergo a research PCD-CT CAC examination. Axial images were reconstructed with a 512 × 512 matrix, 200-mm field of view, 3-mm section thickness/1.5-mm interval using a quantitative kernel (Qr36). Sharper kernels (Qr56/QIR strength 4 for PCD and Qr49/ADMIRE strength 5 for EID) were used to reconstruct images with 1-mm section thickness/0.5-mm interval. Pooled analysis was performed for all calcifications with nonzero values, and volume and Agatston scores were compared between EID-CT and PCD-CT. A Wilcoxon signed-rank test was performed with P < 0.05 considered statistically significant.

RESULTS

In 21 subjects (median age, 58 years; range, 50-75 years; 13 male [62%]) with a total of 42 calcified arteries detected at 3 mm and 46 calcified arteries at 1-mm images, EID-CT CAC volume and Agatston scores were significantly lower than those of PCD-CT ( P ≤ 0.001). At 3-mm thickness, the mean (standard deviation) volume and Agatston score for EID-CT were 55.5 (63.4) mm 3 and 63.8 (76.9), respectively, and 61.5 (69.4) mm 3 and 70.4 (85.3) for PCD-CT ( P = 0.0001 and P = 0.0013). At 1-mm thickness, the mean (standard deviation) volume and score for EID-CT were 50.0 (56.3) mm 3 and 61.1 (69.3), respectively, and 59.5 (63.9) mm 3 and 72.5 (79.9) for PCD-CT ( P < 0.0001 for both). The applied radiation dose (volume CT dose index) for the PCD-CT scan was 2.1 ± 0.6 mGy, which was 13% lower than for the EID-CT scan (2.4 ± 0.7 mGy, P < 0.001).

CONCLUSIONS

Relative to EID-CT, PCD-CT demonstrated a small but significant increase in coronary artery calcium volume and Agatston score.

Inorganic Nitrite to Amplify the Benefits and Tolerability of Exercise Training in Heart Failure With Preserved Ejection Fraction: The INABLE-Training Trial

OBJECTIVE

To determine whether nitrite can enhance exercise training (ET) effects in heart failure with preserved ejection fraction (HFpEF).

METHODS

In this multicenter, double-blind, placebo-controlled, randomized trial conducted at 1 urban and 9 rural outreach centers between November 22, 2016, and December 9, 2021, patients with HFpEF underwent ET along with inorganic nitrite 40 mg or placebo 3 times daily. The primary end point was peak oxygen consumption (VO2). Secondary end points included Kansas City Cardiomyopathy Questionnaire overall summary score (KCCQ-OSS, range 0 to 100; higher scores reflect better health status), 6-minute walk distance, and actigraphy.

RESULTS

Of 92 patients randomized, 73 completed the trial because of protocol modifications necessitated by loss of drug availability. Most patients were older than 65 years (80%), were obese (75%), and lived in rural settings (63%). At baseline, median peak VO2 (14.1 mL·kg-1·min-1) and KCCQ-OSS (63.7) were severely reduced. Exercise training improved peak VO2 (+0.8 mL·kg-1·min-1; 95% CI, 0.3 to 1.2; P<.001) and KCCQ-OSS (+5.5; 95% CI, 2.5 to 8.6; P<.001). Nitrite was well tolerated, but treatment with nitrite did not affect the change in peak VO2 with ET (nitrite effect, -0.13; 95% CI, -1.03 to 0.76; P=.77) or KCCQ-OSS (-1.2; 95% CI, -7.2 to 4.9; P=.71). This pattern was consistent across other secondary outcomes.

CONCLUSION

For patients with HFpEF, ET administered for 12 weeks in a predominantly rural setting improved exercise capacity and health status, but compared with placebo, treatment with inorganic nitrite did not enhance the benefit from ET.

TRIAL REGISTRATION

ClinicalTrials.gov identifier: NCT02713126.

Targeted Training Reduces Search Errors but Not Classification Errors for Hepatic Metastasis Detection at Contrast-Enhanced CT

RATIONALE AND OBJECTIVES

Methods are needed to improve the detection of hepatic metastases. Errors occur in both lesion detection (search) and decisions of benign versus malignant (classification). Our purpose was to evaluate a training program to reduce search errors and classification errors in the detection of hepatic metastases in contrast-enhanced abdominal computed tomography (CT).

MATERIALS AND METHODS

After Institutional Review Board approval, we conducted a single-group prospective pretest-posttest study. Pretest and posttest were identical and consisted of interpreting 40 contrast-enhanced abdominal CT exams containing 91 liver metastases under eye tracking. Between pretest and posttest, readers completed search training with eye-tracker feedback and coaching to increase interpretation time, use liver windows, and use coronal reformations. They also completed classification training with part-task practice, rating lesions as benign or malignant. The primary outcome was metastases missed due to search errors (<2 seconds gaze under eye tracker) and classification errors (>2 seconds). Jackknife free-response receiver operator characteristic (JAFROC) analysis was also conducted.

RESULTS

A total of 31 radiologist readers (8 abdominal subspecialists, 8 nonabdominal subspecialists, 15 senior residents/fellows) participated. Search errors were reduced (pretest 11%, posttest 8%, difference 3% [95% confidence interval, 0.3%-5.1%], P = .01), but there was no difference in classification errors (difference 0%, P = .97) or in JAFROC figure of merit (difference -0.01, P = .36). In subgroup analysis, abdominal subspecialists demonstrated no evidence of change.

CONCLUSION

Targeted training reduced search errors but not classification errors for the detection of hepatic metastases at contrast-enhanced abdominal CT. Improvements were not seen in all subgroups.

Machine Learning for Diagnosis of Pulmonary Hypertension by Echocardiography

OBJECTIVE

To evaluate a machine learning (ML)-based model for pulmonary hypertension (PH) prediction using measurements and impressions made during echocardiography.

METHODS

A total of 7853 consecutive patients with right-sided heart catheterization and transthoracic echocardiography performed within 1 week from January 1, 2012, through December 31, 2019, were included. The data were split into training (n=5024 [64%]), validation (n=1275 [16%]), and testing (n=1554 [20%]). A gradient boosting machine with enumerated grid search for optimization was selected to allow missing data in the boosted trees without imputation. The training target was PH, defined by right-sided heart catheterization as mean pulmonary artery pressure above 20 mm Hg; model performance was maximized relative to area under the receiver operating characteristic curve using 5-fold cross-validation.

RESULTS

Cohort age was 64±14 years; 3467 (44%) were female, and 81% (6323/7853) had PH. The final trained model included 19 characteristics, measurements, or impressions derived from the echocardiogram. In the testing data, the model had high discrimination for the detection of PH (area under the receiver operating characteristic curve, 0.83; 95% CI, 0.80 to 0.85). The model's accuracy, sensitivity, positive predictive value, and negative predictive value were 82% (1267/1554), 88% (1098/1242), 89% (1098/1241), and 54% (169/313), respectively.

CONCLUSION

By use of ML, PH could be predicted on the basis of clinical and echocardiographic variables, without tricuspid regurgitation velocity. Machine learning methods appear promising for identifying patients with low likelihood of PH.

Artificial intelligence-enabled ECG for left ventricular diastolic function and filling pressure

Assessment of left ventricular diastolic function plays a major role in the diagnosis and prognosis of cardiac diseases, including heart failure with preserved ejection fraction. We aimed to develop an artificial intelligence (AI)-enabled electrocardiogram (ECG) model to identify echocardiographically determined diastolic dysfunction and increased filling pressure. We trained, validated, and tested an AI-enabled ECG in 98,736, 21,963, and 98,763 patients, respectively, who had an ECG and echocardiographic diastolic function assessment within 14 days with no exclusion criteria. It was also tested in 55,248 patients with indeterminate diastolic function by echocardiography. The model was evaluated using the area under the curve (AUC) of the receiver operating characteristic curve, and its prognostic performance was compared to echocardiography. The AUC for detecting increased filling pressure was 0.911. The AUCs to identify diastolic dysfunction grades ≥1, ≥2, and 3 were 0.847, 0.911, and 0.943, respectively. During a median follow-up of 5.9 years, 20,223 (20.5%) died. Patients with increased filling pressure predicted by AI-ECG had higher mortality than those with normal filling pressure, after adjusting for age, sex, and comorbidities in the test group (hazard ratio (HR) 1.7, 95% CI 1.645-1.757) similar to echocardiography and in the indeterminate group (HR 1.34, 95% CI 1.298-1.383). An AI-enabled ECG identifies increased filling pressure and diastolic function grades with a good prognostic value similar to echocardiography. AI-ECG is a simple and promising tool to enhance the detection of diseases associated with diastolic dysfunction and increased diastolic filling pressure.

Peer review of clinical and translational research manuscripts: Perspectives from statistical collaborators

Research articles in the clinical and translational science literature commonly use quantitative data to inform evaluation of interventions, learn about the etiology of disease, or develop methods for diagnostic testing or risk prediction of future events. The peer review process must evaluate the methodology used therein, including use of quantitative statistical methods. In this manuscript, we provide guidance for peer reviewers tasked with assessing quantitative methodology, intended to complement guidelines and recommendations that exist for manuscript authors. We describe components of clinical and translational science research manuscripts that require assessment including study design and hypothesis evaluation, sampling and data acquisition, interventions (for studies that include an intervention), measurement of data, statistical analysis methods, presentation of the study results, and interpretation of the study results. For each component, we describe what reviewers should look for and assess; how reviewers should provide helpful comments for fixable errors or omissions; and how reviewers should communicate uncorrectable and irreparable errors. We then discuss the critical concepts of transparency and acceptance/revision guidelines when communicating with responsible journal editors.

Comparison of Photon-counting Detector and Energy-integrating Detector CT for Visual Estimation of Coronary Percent Luminal Stenosis

Background Compared with energy-integrating detector (EID) CT, the improved resolution of photon-counting detector (PCD) CT coupled with high-energy virtual monoenergetic images (VMIs) has been shown to decrease calcium blooming on images in phantoms and cadaveric specimens. Purpose To determine the impact of dual-source PCD CT on visual and quantitative estimation of percent diameter luminal stenosis compared with dual-source EID CT in patients. Materials and Methods This prospective study recruited consecutive adult patients from an outpatient facility between January and March 2022. Study participants underwent clinical dual-source EID coronary CT angiography followed by a research dual-source PCD CT examination. For PCD CT, multienergy data were used to create VMIs at 50 and 100 keV. Two readers independently reviewed EID CT images followed by PCD CT images after a washout period. Readers visually graded the most severe stenosis in terms of percent diameter luminal stenosis for the left main, left anterior descending, right, and circumflex coronary arteries, unblinded to scanner type. Quantitative measures of percent stenosis were made using commercial software. Visual and quantitative estimates of percent stenosis were compared between EID CT and PCD CT using the Wilcoxon signed-rank test. Results A total of 25 participants (median age, 59 years [range, 18-78 years]; 16 male participants) were enrolled. On EID CT images, readers 1 and 2 identified 39 and 32 luminal stenoses, respectively, with a percent diameter luminal stenosis greater than 0%. Visual estimates of percent stenosis were lower on PCD CT images than EID CT images (reader 1: median 20.6% [IQR, 8.8%-61.2%] vs 31.8% [IQR, 12.9%-69.7%], P < .001; reader 2: 6.5% [IQR, 0.4%-54.1%] vs 22.9% [IQR, 1.8%-67.4%], P = .002). No difference was observed between EID CT and PCD CT for quantitative measures of percent stenosis (median difference, -1.5% [95% CI: -3.0%, 2.5%]; P = .51). Conclusion Relative to using EID CT, using PCD CT led to decreases in visual estimates of percent stenosis. © RSNA, 2023 See also the editorial by Murphy and Donnelly in this issue.

Impact of biological sex and sex hormones on molecular signatures of skeletal muscle at rest and in response to distinct exercise training modes

Substantial divergence in cardio-metabolic risk, muscle size, and performance exists between men and women. Considering the pivotal role of skeletal muscle in human physiology, we investigated and found, based on RNA sequencing (RNA-seq), that differences in the muscle transcriptome between men and women are largely related to testosterone and estradiol and much less related to genes located on the Y chromosome. We demonstrate inherent unique, sex-dependent differences in muscle transcriptional responses to aerobic, resistance, and combined exercise training in young and older cohorts. The hormonal changes with age likely explain age-related differential expression of transcripts. Furthermore, in primary human myotubes we demonstrate the profound but distinct effects of testosterone and estradiol on amino acid incorporation to multiple individual proteins with specific functions. These results clearly highlight the potential of designing exercise programs tailored specifically to men and women and have implications for people who change gender by altering their hormone profile.

Retrospective Evaluation of Neuropathologic Proxies of the Minimal Atrophy Subtype Compared With Corticolimbic Alzheimer Disease Subtypes

BACKGROUND AND OBJECTIVES

Alzheimer disease (AD) is neuropathologically classified into 3 corticolimbic subtypes based on the neurofibrillary tangle distribution throughout the hippocampus and association cortices: limbic predominant, typical, and hippocampal sparing. In vivo, a fourth subtype, dubbed "minimal atrophy," was identified using structural MRI. The objective of this study was to identify a neuropathologic proxy for the neuroimaging-defined minimal atrophy subtype.

METHODS

We applied 2 strategies in the Florida Autopsied Multi-Ethnic (FLAME) cohort to evaluate a neuropathologic proxy for the minimal atrophy subtype. In the first strategy, we selected AD cases with a Braak tangle stage IV (Braak IV) because of the relative paucity of neocortical tangle involvement compared with Braak >IV. Braak IV cases were compared with the 3 AD subtypes. In the alternative strategy, typical AD was stratified by brain weight and cases having a relatively high brain weight (>75th percentile) were defined as minimal atrophy.

RESULTS

Braak IV cases (n = 37) differed from AD subtypes (limbic predominant [n = 174], typical [n = 986], and hippocampal sparing [n = 187] AD) in having the least years of education (median 12 years, group-wise p < 0.001) and the highest brain weight (median 1,140 g, p = 0.002). Braak IV cases most resembled the limbic predominant cases owing to their high proportion of APOE ε4 carriers (75%, p < 0.001), an amnestic syndrome (100%, p < 0.001), as well as older age of cognitive symptom onset and death (median 79 and 85 years, respectively, p < 0.001). Only 5% of Braak IV cases had amygdala-predominant Lewy bodies (the lowest frequency observed, p = 0.017), whereas 32% had coexisting pathology of Lewy body disease, which was greater than the other subtypes (p = 0.005). Nearly half (47%) of the Braak IV samples had coexisting limbic predominant age-related TAR DNA-binding protein 43 encephalopathy neuropathologic change. Cases with a high brain weight (n = 201) were less likely to have amygdala-predominant Lewy bodies (14%, p = 0.006) and most likely to have Lewy body disease (31%, p = 0.042) compared with those with middle (n = 455) and low (n = 203) brain weight.

DISCUSSION

The frequency of Lewy body disease was increased in both neuropathologic proxies of the minimal atrophy subtype. We hypothesize that Lewy body disease may underlie cognitive decline observed in minimal atrophy cases.

Demystifying Statistics and Machine Learning in Analysis of Structured Tabular Data

Electronic health records have facilitated the extraction and analysis of a vast amount of data with many variables for clinical care and research. Conventional regression-based statistical methods may not capture all the complexities in high-dimensional data analysis. Therefore, researchers are increasingly using machine learning (ML)-based methods to better handle these more challenging datasets for the discovery of hidden patterns in patients' data and for classification and predictive purposes. This article describes commonly used ML methods in structured data analysis with examples in orthopedic surgery. We present practical considerations in starting an ML project and appraising published studies in this field.

Rates Among Hospitalized Patients With COVID-19 Treated With Convalescent Plasma: A Systematic Review and Meta-Analysis

Objective

To examine the association of COVID-19 convalescent plasma transfusion with mortality and the differences between subgroups in hospitalized patients with COVID-19.

Patients and Methods

On October 26, 2022, a systematic search was performed for clinical studies of COVID-19 convalescent plasma in the literature from January 1, 2020, to October 26, 2022. Randomized clinical trials and matched cohort studies investigating COVID-19 convalescent plasma transfusion compared with standard of care treatment or placebo among hospitalized patients with confirmed COVID-19 were included. The electronic search yielded 3841 unique records, of which 744 were considered for full-text screening. The selection process was performed independently by a panel of 5 reviewers. The study followed the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. Data were extracted by 5 independent reviewers in duplicate and pooled using an inverse-variance random effects model. The prespecified end point was all-cause mortality during hospitalization.

Results

Thirty-nine randomized clinical trials enrolling 21,529 participants and 70 matched cohort studies enrolling 50,160 participants were included in the systematic review. Separate meta-analyses reported that transfusion of COVID-19 convalescent plasma was associated with a decrease in mortality compared with the control cohort for both randomized clinical trials (odds ratio [OR], 0.87; 95% CI, 0.76-1.00) and matched cohort studies (OR, 0.76; 95% CI, 0.66-0.88). The meta-analysis of subgroups revealed 2 important findings. First, treatment with convalescent plasma containing high antibody levels was associated with a decrease in mortality compared with convalescent plasma containing low antibody levels (OR, 0.85; 95% CI, 0.73 to 0.99). Second, earlier treatment with COVID-19 convalescent plasma was associated with a decrease in mortality compared with the later treatment cohort (OR, 0.63; 95% CI, 0.48 to 0.82).

Conclusion

During COVID-19 convalescent plasma use was associated with a 13% reduced risk of mortality, implying a mortality benefit for hospitalized patients with COVID-19, particularly those treated with convalescent plasma containing high antibody levels treated earlier in the disease course.

Screening for peripartum cardiomyopathies using artificial intelligence in Nigeria (SPEC-AI Nigeria): Clinical trial rationale and design

BACKGROUND

Artificial intelligence (AI), and more specifically deep learning, models have demonstrated the potential to augment physician diagnostic capabilities and improve cardiovascular health if incorporated into routine clinical practice. However, many of these tools are yet to be evaluated prospectively in the setting of a rigorous clinical trial-a critical step prior to implementing broadly in routine clinical practice.

OBJECTIVES

To describe the rationale and design of a proposed clinical trial aimed at evaluating an AI-enabled electrocardiogram (AI-ECG) for cardiomyopathy detection in an obstetric population in Nigeria.

DESIGN

The protocol will enroll 1,000 pregnant and postpartum women who reside in Nigeria in a prospective randomized clinical trial. Nigeria has the highest reported incidence of peripartum cardiomyopathy worldwide. Women aged 18 and older, seen for routine obstetric care at 6 sites (2 Northern and 4 Southern) in Nigeria will be included. Participants will be randomized to the study intervention or control arm in a 1:1 fashion. This study aims to enroll participants representative of the general obstetric population at each site. The primary outcome is a new diagnosis of cardiomyopathy, defined as left ventricular ejection fraction (LVEF) < 50% during pregnancy or within 12 months postpartum. Secondary outcomes will include the detection of impaired left ventricular function (at different LVEF cut-offs), and exploratory outcomes will include the effectiveness of AI-ECG tools for cardiomyopathy detection, new diagnosis of cardiovascular disease, and the development of composite adverse maternal cardiovascular outcomes.

SUMMARY

This clinical trial focuses on the emerging field of cardio-obstetrics and will serve as foundational data for the use of AI-ECG tools in an obstetric population in Nigeria. This study will gather essential data regarding the utility of the AI-ECG for cardiomyopathy detection in a predominantly Black population of women and pave the way for clinical implementation of these models in routine practice.

TRIAL REGISTRATION

Clinicaltrials.gov: NCT05438576.

Using AI to Detect Pain through Facial Expressions: A Review

Pain assessment is a complex task largely dependent on the patient's self-report. Artificial intelligence (AI) has emerged as a promising tool for automating and objectifying pain assessment through the identification of pain-related facial expressions. However, the capabilities and potential of AI in clinical settings are still largely unknown to many medical professionals. In this literature review, we present a conceptual understanding of the application of AI to detect pain through facial expressions. We provide an overview of the current state of the art as well as the technical foundations of AI/ML techniques used in pain detection. We highlight the ethical challenges and the limitations associated with the use of AI in pain detection, such as the scarcity of databases, confounding factors, and medical conditions that affect the shape and mobility of the face. The review also highlights the potential impact of AI on pain assessment in clinical practice and lays the groundwork for further study in this area.

Machine learning-based risk stratification for mortality in patients with severe aortic regurgitation

Aims

The current guidelines recommend aortic valve intervention in patients with severe aortic regurgitation (AR) with the onset of symptoms, left ventricular enlargement, or systolic dysfunction. Recent studies have suggested that we might be missing the window of early intervention in a significant number of patients by following the guidelines.

Methods and results

The overarching goal was to determine if machine learning (ML)-based algorithms could be trained to identify patients at risk for death from AR independent of aortic valve replacement (AVR). Models were trained with five-fold cross-validation on a dataset of 1035 patients, and performance was reported on an independent dataset of 207 patients. Optimal predictive performance was observed with a conditional random survival forest model. A subset of 19/41 variables was selected for inclusion in the final model. Variable selection was performed with 10-fold cross-validation using random survival forest model. The top variables included were age, body surface area, body mass index, diastolic blood pressure, New York Heart Association class, AVR, comorbidities, ejection fraction, end-diastolic volume, and end-systolic dimension, and the relative variable importance averaged across five splits of cross-validation in each repeat were evaluated. The concordance index for predicting survival of the best-performing model was 0.84 at 1 year, 0.86 at 2 years, and 0.87 overall, respectively.

Conclusion

Using common echocardiographic parameters and patient characteristics, we successfully trained multiple ML models to predict survival in patients with severe AR. This technique could be applied to identify high-risk patients who would benefit from early intervention, thereby improving patient outcomes.

A Review of Voice-Based Pain Detection in Adults Using Artificial Intelligence

Pain is a complex and subjective experience, and traditional methods of pain assessment can be limited by factors such as self-report bias and observer variability. Voice is frequently used to evaluate pain, occasionally in conjunction with other behaviors such as facial gestures. Compared to facial emotions, there is less available evidence linking pain with voice. This literature review synthesizes the current state of research on the use of voice recognition and voice analysis for pain detection in adults, with a specific focus on the role of artificial intelligence (AI) and machine learning (ML) techniques. We describe the previous works on pain recognition using voice and highlight the different approaches to voice as a tool for pain detection, such as a human effect or biosignal. Overall, studies have shown that AI-based voice analysis can be an effective tool for pain detection in adult patients with various types of pain, including chronic and acute pain. We highlight the high accuracy of the ML-based approaches used in studies and their limitations in terms of generalizability due to factors such as the nature of the pain and patient population characteristics. However, there are still potential challenges, such as the need for large datasets and the risk of bias in training models, which warrant further research.

A training program to reduce reader search errors for liver metastasis detection in CT

Detection of low contrast liver metastases varies between radiologists. Training may improve performance for lower-performing readers and reduce inter-radiologist variability. We recruited 31 radiologists (15 trainees, 8 non-abdominal staff, and 8 abdominal staff) to participate in four separate reading sessions: pre-test, search training, classification training, and post-test. In the pre-test, each radiologist interpreted 40 liver CT exams containing 91 metastases, circumscribed suspected hepatic metastases while under eye tracker observation, and rated confidence. In search training, radiologists interpreted a separate set of 30 liver CT exams while receiving eye tracker feedback and after coaching to increase use of coronal reformations, interpretation time, and use of liver windows. In classification training, radiologists interpreted up to 100 liver CT image patches, most with benign or malignant lesions, and compared their annotations to ground truth. Post-test was identical to pre-test. Between pre- and post-test, sensitivity increased by 2.8% (p = 0.01) but AUC did not change significantly. Missed metastases were classified as search errors (<2 seconds gaze time) or classification errors (>2 seconds gaze time) using the eye tracker. Out of 2775 possible detections, search errors decreased (10.8% to 8.1%; p < 0.01) but classification errors were unchanged (5.7% vs 5.7%). When stratified by difficulty, easier metastases showed larger reductions in search errors: for metastases with average sensitivity of 0-50%, 50-90%, and 90-100%, reductions in search errors were 16%, 35%, and 58%, respectively. The training program studied here may be able to improve radiologist performance by reducing errors but not classification errors.

The Role of Telemedicine in Prehospital Traumatic Hand Injury Evaluation

Unnecessary ED visits and transfers to hand clinics raise treatment costs and patient burden at trauma centers. In the present COVID-19 pandemic, needless transfers can increase patients' risk of viral exposure. Therefore, this review analyzes different aspects of the remote diagnosis and triage of traumatic hand injuries. The most common file was photography, with the most common devices being cell phone cameras. Treatment, triage, diagnosis, cost, and time outcomes were assessed, showing concordance between teleconsultation and face-to-face patient evaluations. We conclude that photography and video consultations are feasible surrogates for ED visits in patients with traumatic hand injuries. These technologies should be leveraged to decrease treatment costs and potentially decrease the time to definitive treatment after initial evaluation.

Non-invasive detection of cardiac allograft rejection among heart transplant recipients using an electrocardiogram based deep learning model

Aims

Current non-invasive screening methods for cardiac allograft rejection have shown limited discrimination and are yet to be broadly integrated into heart transplant care. Given electrocardiogram (ECG) changes have been reported with severe cardiac allograft rejection, this study aimed to develop a deep-learning model, a form of artificial intelligence, to detect allograft rejection using the 12-lead ECG (AI-ECG).

Methods and results

Heart transplant recipients were identified across three Mayo Clinic sites between 1998 and 2021. Twelve-lead digital ECG data and endomyocardial biopsy results were extracted from medical records. Allograft rejection was defined as moderate or severe acute cellular rejection (ACR) based on International Society for Heart and Lung Transplantation guidelines. The extracted data (7590 unique ECG-biopsy pairs, belonging to 1427 patients) was partitioned into training (80%), validation (10%), and test sets (10%) such that each patient was included in only one partition. Model performance metrics were based on the test set (n = 140 patients; 758 ECG-biopsy pairs). The AI-ECG detected ACR with an area under the receiver operating curve (AUC) of 0.84 [95% confidence interval (CI): 0.78-0.90] and 95% (19/20; 95% CI: 75-100%) sensitivity. A prospective proof-of-concept screening study (n = 56; 97 ECG-biopsy pairs) showed the AI-ECG detected ACR with AUC = 0.78 (95% CI: 0.61-0.96) and 100% (2/2; 95% CI: 16-100%) sensitivity.

Conclusion

An AI-ECG model is effective for detection of moderate-to-severe ACR in heart transplant recipients. Our findings could improve transplant care by providing a rapid, non-invasive, and potentially remote screening option for cardiac allograft function.

Accuracy of Wearable Sensor Technology in Hand Goniometry: A Systematic Review

BACKGROUND

Wearable devices and sensor technology provide objective, unbiased range of motion measurements that help health care professionals overcome the hindrances of protractor-based goniometry. This review aims to analyze the accuracy of existing wearable sensor technologies for hand range of motion measurement and identify the most accurate one.

METHODS

We performed a systematic review by searching PubMed, CINAHL, and Embase for studies evaluating wearable sensor technology in hand range of motion assessment. Keywords used for the inquiry were related to wearable devices and hand goniometry.

RESULTS

Of the 71 studies, 11 met the inclusion criteria. Ten studies evaluated gloves and 1 evaluated a wristband. The most common types of sensors used were bend sensors, followed by inertial sensors, Hall effect sensors, and magnetometers. Most studies compared wearable devices with manual goniometry, achieving optimal accuracy. Although most of the devices reached adequate levels of measurement error, accuracy evaluation in the reviewed studies might be subject to bias owing to the use of poorly reliable measurement techniques for comparison of the devices.

CONCLUSION

Gloves using inertial sensors were the most accurate. Future studies should use different comparison techniques, such as infrared camera-based goniometry or virtual motion tracking, to evaluate the performance of wearable devices.

Composite nerve conduction scores and signs for diagnosis and somatic staging of diabetic polyneuropathy: Mid North American ethnic cohort survey

INTRODUCTION/AIMS

In the Diabetes Control and Complications Trial (DCCT), the minimal nerve conduction (NC) criterion for diabetic sensorimotor polyneuropathy (DSPN) was abnormality of NC in more than one peripheral nerve without specifying the attributes of NCs to be evaluated. In the present study, we assess individual and composite scores of NCs meeting the DCCT criterion and signs for improved diagnosis and assessment of DSPN severity.

METHODS

Evaluated were 13 attributes and 6 composite NC scores and signs and symptoms in 395 healthy subjects (HS) and 388 persons with diabetes (DM).

RESULTS

Percent abnormality between subjects with DM and HS was remarkably different among individual attributes and the six composite NC scores. For diagnosis of DSPN using the DCCT criterion, assessment of conduction velocities (CVs) and distal latencies (DLs) provided sensitive diagnoses of DSPN. NC amplitudes provided stronger measures of severity. In studied cohorts, DSPN was staged: N0, no NC abnormality using NC score 2 (CVs and DLs), 60.0%; N1, NC abnormality only, 18.4%; N2, NC abnormality and signs of feet or legs, 16.3%; and N3, NC abnormality and signs of thighs, 5.3%.

DISCUSSION

For sensitive and standard diagnosis of DSPN using the DCCT NC criterion, specifically defined composite scores of CVs and DLs, e.g., score 2, is recommended. A composite score of amplitudes, e.g., score 4, provides a stronger measure of neuropathy severity. Also, provided are HS reference values of evaluated attributes of NCs and estimates of staged severity of DSPN of mid North American DM cohorts.

Understanding Reader Variability: A 25-Radiologist Study on Liver Metastasis Detection at CT

Background Substantial interreader variability exists for common tasks in CT imaging, such as detection of hepatic metastases. This variability can undermine patient care by leading to misdiagnosis. Purpose To determine the impact of interreader variability associated with (a) reader experience, (b) image navigation patterns (eg, eye movements, workstation interactions), and (c) eye gaze time at missed liver metastases on contrast-enhanced abdominal CT images. Materials and Methods In a single-center prospective observational trial at an academic institution between December 2020 and February 2021, readers were recruited to examine 40 contrast-enhanced abdominal CT studies (eight normal, 32 containing 91 liver metastases). Readers circumscribed hepatic metastases and reported confidence. The workstation tracked image navigation and eye movements. Performance was quantified by using the area under the jackknife alternative free-response receiver operator characteristic (JAFROC-1) curve and per-metastasis sensitivity and was associated with reader experience and image navigation variables. Differences in area under JAFROC curve were assessed with the Kruskal-Wallis test followed by the Dunn test, and effects of image navigation were assessed by using the Wilcoxon signed-rank test. Results Twenty-five readers (median age, 38 years; IQR, 31-45 years; 19 men) were recruited and included nine subspecialized abdominal radiologists, five nonabdominal staff radiologists, and 11 senior residents or fellows. Reader experience explained differences in area under the JAFROC curve, with abdominal radiologists demonstrating greater area under the JAFROC curve (mean, 0.77; 95% CI: 0.75, 0.79) than trainees (mean, 0.71; 95% CI: 0.69, 0.73) (P = .02) or nonabdominal subspecialists (mean, 0.69; 95% CI: 0.60, 0.78) (P = .03). Sensitivity was similar within the reader experience groups (P = .96). Image navigation variables that were associated with higher sensitivity included longer interpretation time (P = .003) and greater use of coronal images (P < .001). The eye gaze time was at least 0.5 and 2.0 seconds for 71% (266 of 377) and 40% (149 of 377) of missed metastases, respectively. Conclusion Abdominal radiologists demonstrated better discrimination for the detection of liver metastases on abdominal contrast-enhanced CT images. Missed metastases frequently received at least a brief eye gaze. Higher sensitivity was associated with longer interpretation time and greater use of liver display windows and coronal images. © RSNA, 2022 Online supplemental material is available for this article.

Perceived Age as a Mortality and Comorbidity Predictor: A Systematic Review

INTRODUCTION

Perceived age is defined as how old a person looks to external evaluators. It reflects the underlying biological age, which is a measure based on physical and physiological parameters reflecting a person's aging process more accurately than chronological age. People with a higher biological age have shorter lives compared to those with a lower biological age with the same chronological age. Our review aims to find whether increased perceived age is a risk factor for overall mortality risk or comorbidities.

METHODS

A literature search of three databases was conducted following the PRISMA guidelines for studies analyzing perceived age or isolated facial characteristics of old age and their relationship to mortality risk or comorbidity outcomes. Data on the number of patients, type and characteristics of evaluation methods, evaluator characteristics, mean chronologic age, facial characteristics studied, measured outcomes, and study results were collected.

RESULTS

Out of 977 studies, 15 fulfilled the inclusion criteria. These studies found an increase in mortality risk of 6-51% in older-looking people compared to controls (HR 1.06-1.51, p < 0.05). In addition, perceived age and some facial characteristics of old age were also associated with cardiovascular risk and myocardial infarction, cognitive function, bone mineral density, and chronic obstructive pulmonary disease (COPD).

CONCLUSION

Perceived age promises to be a clinically useful predictor of overall mortality and cardiovascular, pulmonary, cognitive, and osseous comorbidities.

LEVEL OF EVIDENCE III

This journal requires that authors assign a level of evidence to each article. For a full description of these Evidence-Based Medicine ratings, please refer to the Table of Contents or the online Instructions to Authors www.springer.com/00266 .

Assessment of surgeons' attitude towards awake spine surgery under spinal anesthesia

BACKGROUND

General anesthesia (GA) and spinal anesthesia (SA) have been adopted for lumbar spine surgery (LSS), but GA is used far more widely. We conducted a survey of spine surgeons to explore their attitudes and preferences regarding awake spine surgery under SA.

METHODS

A survey was emailed to 150 spine surgeons. Exposure and attitudes towards spine surgery under SA were elicited. A five-point Likert scale of agreement examined perceptions of SA, while attitudes towards SA were recorded by categorizing free text into themes.

RESULTS

Seventy-five surgeons completed the survey, 50 % response rate. Only 27 % said they perform LSS under SA. Most surgeons, 83 %, would recommend GA to a healthy patient undergoing lumbar laminectomy. Only 41 % believes SA to be as safe as GA, and only 30 % believes SA is associated with better postoperative pain control. The most common reasons why SA is not favored was lack of proven benefits over GA (65 %). When asked if a randomized trial finds SA to lead to less postoperative fatigue, 50 % said they would be more likely to offer SA, a significant increase from the baseline response of 27 % (p = 0.002).

CONCLUSIONS

Our survey indicates that the low adoption of SA for LSS is due to lack of surgeons' belief in the benefits of SA over GA, and that a randomized patient-centered trial has the potential of changing surgeons' perspective and increasing adoption of SA for LSS.

Perceived Age in Patients Exposed to Distinct UV Indexes: A Systematic Review

Photodamage is caused by chronic sun exposure and ultraviolet radiation and presents as wrinkles, sagging, and pigmented spots. An increase in the ultraviolet index can increase a person's perceived age by worsening skin photodamage. However, since the ultraviolet index varies considerably between geographical regions, perceived age might vary substantially among them. This review aims to describe the differences in chronological and perceived age in regions of the world with different ultraviolet indexes. A literature search of three databases was conducted for studies analyzing perceived age and its relationship to sun exposure. Ultraviolet indexes from the included studies were retrieved from the National Weather Service and the Tropospheric Emission Monitoring Internet Service. Out of 104 studies, seven fulfilled the inclusion criteria. Overall, 3,352 patients were evaluated for perceived age. All studies found that patients with the highest daily sun exposures had the highest perceived ages for their chronological age (p < 0.05). People with high sun exposure behaviors living in regions with high ultraviolet indexes will look significantly older than same-aged peers living in lower ultraviolet index regions.

Rates of Asymptomatic COVID-19 Infection and Associated Factors in Olmsted County, Minnesota, in the Prevaccination Era

Objective

To estimate rates and identify factors associated with asymptomatic COVID-19 in the population of Olmsted County during the prevaccination era.

Patients and Methods

We screened first responders (n=191) and Olmsted County employees (n=564) for antibodies to SARS-CoV-2 from November 1, 2020 to February 28, 2021 to estimate seroprevalence and asymptomatic infection. Second, we retrieved all polymerase chain reaction (PCR)-confirmed COVID-19 diagnoses in Olmsted County from March 2020 through January 2021, abstracted symptom information, estimated rates of asymptomatic infection and examined related factors.

Results

Twenty (10.5%; 95% CI, 6.9%-15.6%) first responders and 38 (6.7%; 95% CI, 5.0%-9.1%) county employees had positive antibodies; an additional 5 (2.6%) and 10 (1.8%) had prior positive PCR tests per self-report or medical record, but no antibodies detected. Of persons with symptom information, 4 of 20 (20%; 95% CI, 3.0%-37.0%) first responders and 10 of 39 (26%; 95% CI, 12.6%-40.0%) county employees were asymptomatic. Of 6020 positive PCR tests in Olmsted County with symptom information between March 1, 2020, and January 31, 2021, 6% (n=385; 95% CI, 5.8%-7.1%) were asymptomatic. Factors associated with asymptomatic disease included age (0-18 years [odds ratio {OR}, 2.3; 95% CI, 1.7-3.1] and >65 years [OR, 1.40; 95% CI, 1.0-2.0] compared with ages 19-44 years), body mass index (overweight [OR, 0.58; 95% CI, 0.44-0.77] or obese [OR, 0.48; 95% CI, 0.57-0.62] compared with normal or underweight) and tests after November 20, 2020 ([OR, 1.35; 95% CI, 1.13-1.71] compared with prior dates).

Conclusion

Asymptomatic rates in Olmsted County before COVID-19 vaccine rollout ranged from 6% to 25%, and younger age, normal weight, and later tests dates were associated with asymptomatic infection.

Deep learning for dermatologists: Part I. Fundamental concepts

Artificial intelligence is generating substantial interest in the field of medicine. One form of artificial intelligence, deep learning, has led to rapid advances in automated image analysis. In 2017, an algorithm demonstrated the ability to diagnose certain skin cancers from clinical photographs with the accuracy of an expert dermatologist. Subsequently, deep learning has been applied to a range of dermatology applications. Although experts will never be replaced by artificial intelligence, it will certainly affect the specialty of dermatology. In this first article of a 2-part series, the basic concepts of deep learning will be reviewed with the goal of laying the groundwork for effective communication between clinicians and technical colleagues. In part 2 of the series, the clinical applications of deep learning in dermatology will be reviewed and limitations and opportunities will be considered.

Deep learning for dermatologists: Part II. Current applications

Because of a convergence of the availability of large data sets, graphics-specific computer hardware, and important theoretical advancements, artificial intelligence has recently contributed to dramatic progress in medicine. One type of artificial intelligence known as deep learning has been particularly impactful for medical image analysis. Deep learning applications have shown promising results in dermatology and other specialties, including radiology, cardiology, and ophthalmology. The modern clinician will benefit from an understanding of the basic features of deep learning to effectively use new applications and to better gauge their utility and limitations. In this second article of a 2-part series, we review the existing and emerging clinical applications of deep learning in dermatology and discuss future opportunities and limitations. Part 1 of this series offered an introduction to the basic concepts of deep learning to facilitate effective communication between clinicians and technical experts.

Prospective evaluation of smartwatch-enabled detection of left ventricular dysfunction

Although artificial intelligence (AI) algorithms have been shown to be capable of identifying cardiac dysfunction, defined as ejection fraction (EF) ≤ 40%, from 12-lead electrocardiograms (ECGs), identification of cardiac dysfunction using the single-lead ECG of a smartwatch has yet to be tested. In the present study, a prospective study in which patients of Mayo Clinic were invited by email to download a Mayo Clinic iPhone application that sends watch ECGs to a secure data platform, we examined patient engagement with the study app and the diagnostic utility of the ECGs. We digitally enrolled 2,454 unique patients (mean age 53 ± 15 years, 56% female) from 46 US states and 11 countries, who sent 125,610 ECGs to the data platform between August 2021 and February 2022; 421 participants had at least one watch-classified sinus rhythm ECG within 30 d of an echocardiogram, of whom 16 (3.8%) had an EF ≤ 40%. The AI algorithm detected patients with low EF with an area under the curve of 0.885 (95% confidence interval 0.823-0.946) and 0.881 (0.815-0.947), using the mean prediction within a 30-d window or the closest ECG relative to the echocardiogram that determined the EF, respectively. These findings indicate that consumer watch ECGs, acquired in nonclinical environments, can be used to identify patients with cardiac dysfunction, a potentially life-threatening and often asymptomatic condition.

Estimating the Clinical Impact of Photon-Counting-Detector CT in Diagnosing Usual Interstitial Pneumonia

OBJECTIVE

The aim of this study was to evaluate the clinical impact of a higher spatial resolution, full field-of-view investigational photon-counting detector computed tomography (PCD-CT) on radiologist confidence in imaging findings and diagnosis of usual interstitial pneumonia (UIP) compared with conventional energy-integrating detector CT (EID-CT).

MATERIALS AND METHODS

Patients suspected of interstitial lung disease were scanned on a PCD-CT system after informed consent and a clinically indicated EID-CT. In 2 sessions, 3 thoracic radiologists blinded to clinical history and scanner type evaluated CT images of the right and left lungs separately on EID- or PCD-CT, reviewing each lung once/session, rating confidence in imaging findings of reticulation, traction bronchiectasis, honeycombing, ground-glass opacities (GGOs), mosaic pattern, and lower lobe predominance (100-point scale: 0-33, likely absent; 34-66, indeterminate; 67-100, likely present). Radiologists also rated confidence for the probability of UIP (0-20, normal; 21-40, inconsistent with UIP; 41-60, indeterminate UIP; 61-81; probable UIP; 81-100, definite UIP) and graded image quality. Because a confidence scale of 50 represented completely equivocal findings, magnitude score (the absolute value of confidence scores from 50) was used for analysis (higher scores were more confident). Image noise was measured for each modality. The magnitude score was compared using linear mixed effects regression. The consistency of findings and diagnosis between 2 scanners were evaluated using McNemar test and weighted κ statistics, respectively.

RESULTS

A total of 30 patients (mean age, 68.8 ± 11.0 years; M:F = 18:12) underwent conventional EID-CT (median CTDI vol , 7.88 mGy) and research PCD-CT (median CTDI vol , 6.49 mGy). The magnitude scores in PCD-CT were significantly higher than EID-CT for imaging findings of reticulation (40.7 vs 38.3; P = 0.023), GGO (34.4 vs 31.7; P = 0.019), and mosaic pattern (38.6 vs 35.9; P = 0.013), but not for other imaging findings ( P ≥ 0.130) or confidence in UIP (34.1 vs 22.2; P < 0.059). Magnitude score of probability of UIP in PCD-CT was significantly higher than EID-CT in one reader (26.0 vs 21.5; P = 0.009). Photon-counting detector CT demonstrated a decreased number of indeterminate GGO (17 vs 26), an increased number of unlikely GGO (74 vs 50), and an increased number of likely reticulations (140 vs 130) relative to EID-CT. Interobserver agreements among 3 readers for imaging findings and probability of UIP were similar between PCD-CT and EID-CT (intraclass coefficient: 0.507-0.818 vs 0.601-0.848). Photon-counting detector CT had higher scores in overall image quality (4.84 ± 0.38) than those in EID-CT (4.02 ± 0.40; P < 0.001) despite increased image noise (mean 85.5 vs 36.1 HU).

CONCLUSIONS

Photon-counting detector CT provided better image quality and improved the reader confidence for presence or absence of imaging findings of reticulation, GGO, and mosaic pattern with idiosyncratic improvement in confidence in UIP presence.

Estimating the Clinical Impact of Photon-Counting-Detector CT in Diagnosing Usual Interstitial Pneumonia

OBJECTIVE

The aim of this study was to evaluate the clinical impact of a higher spatial resolution, full field-of-view investigational photon-counting detector computed tomography (PCD-CT) on radiologist confidence in imaging findings and diagnosis of usual interstitial pneumonia (UIP) compared with conventional energy-integrating detector CT (EID-CT).

MATERIALS AND METHODS

Patients suspected of interstitial lung disease were scanned on a PCD-CT system after informed consent and a clinically indicated EID-CT. In 2 sessions, 3 thoracic radiologists blinded to clinical history and scanner type evaluated CT images of the right and left lungs separately on EID- or PCD-CT, reviewing each lung once/session, rating confidence in imaging findings of reticulation, traction bronchiectasis, honeycombing, ground-glass opacities (GGOs), mosaic pattern, and lower lobe predominance (100-point scale: 0-33, likely absent; 34-66, indeterminate; 67-100, likely present). Radiologists also rated confidence for the probability of UIP (0-20, normal; 21-40, inconsistent with UIP; 41-60, indeterminate UIP; 61-81; probable UIP; 81-100, definite UIP) and graded image quality. Because a confidence scale of 50 represented completely equivocal findings, magnitude score (the absolute value of confidence scores from 50) was used for analysis (higher scores were more confident). Image noise was measured for each modality. The magnitude score was compared using linear mixed effects regression. The consistency of findings and diagnosis between 2 scanners were evaluated using McNemar test and weighted κ statistics, respectively.

RESULTS

A total of 30 patients (mean age, 68.8 ± 11.0 years; M:F = 18:12) underwent conventional EID-CT (median CTDI vol , 7.88 mGy) and research PCD-CT (median CTDI vol , 6.49 mGy). The magnitude scores in PCD-CT were significantly higher than EID-CT for imaging findings of reticulation (40.7 vs 38.3; P = 0.023), GGO (34.4 vs 31.7; P = 0.019), and mosaic pattern (38.6 vs 35.9; P = 0.013), but not for other imaging findings ( P ≥ 0.130) or confidence in UIP (34.1 vs 22.2; P &lt; 0.059). Magnitude score of probability of UIP in PCD-CT was significantly higher than EID-CT in one reader (26.0 vs 21.5; P = 0.009). Photon-counting detector CT demonstrated a decreased number of indeterminate GGO (17 vs 26), an increased number of unlikely GGO (74 vs 50), and an increased number of likely reticulations (140 vs 130) relative to EID-CT. Interobserver agreements among 3 readers for imaging findings and probability of UIP were similar between PCD-CT and EID-CT (intraclass coefficient: 0.507-0.818 vs 0.601-0.848). Photon-counting detector CT had higher scores in overall image quality (4.84 ± 0.38) than those in EID-CT (4.02 ± 0.40; P &lt; 0.001) despite increased image noise (mean 85.5 vs 36.1 HU).

CONCLUSIONS

Photon-counting detector CT provided better image quality and improved the reader confidence for presence or absence of imaging findings of reticulation, GGO, and mosaic pattern with idiosyncratic improvement in confidence in UIP presence.

Artificial intelligence-based risk stratification of atrial fibrillation among women with peripartum cardiomyopathy compared to other cardiomyopathies

Background

Atrial fibrillation (AF) is diagnosed in up to 50% of patients with heart failure. However, the prevalence of AF among patients with peripartum cardiomyopathy (PPCM) ranges from only 2–10%, with the lowest rates in Black women. An artificial intelligence enhanced electrocardiogram (AI-ECG) has previously been shown to be effective in detecting AF while in sinus rhythm, and for AF risk prediction in a population-based study.

Purpose

Our objective was to evaluate the use of an AI-ECG for AF risk stratification among women of reproductive age (18 to 49 years) with PPCM compared to other forms of cardiomyopathy.

Methods

We identified 59 reproductive age women with a diagnosis of PPCM between January 2007, and October 2018 and included matched controls in a 3:1 fashion. Matching was performed based on sex, age, race, and left ventricular ejection fraction. We excluded patients with a diagnosis of AF prior to cardiomyopathy diagnosis date. AI-ECG prediction probabilities were generated for ECGs performed within a 30-day window prior to the patient's first cardiomyopathy diagnosis date for the entire study cohort.

Results

A total of 236 patients were included in the final analysis (59 cases, 177 controls). Overall, the median age at cardiomyopathy diagnosis was 31.7 years (IQR: 18.5, 49.4), 76.3% were White, 8.5% were Black, and 15.3% represented other or unknown race. Over the period studied, 3.4% of women with PPCM developed AF compared to 5.6% of women with other cardiomyopathies. The frequency of positive AI-ECG predictions for AF was more common among women with other cardiomyopathies (40.7%) compared to women with PPCM (20.3%). The predicted odds ratio for AF development following a cardiomyopathy diagnosis based on AI-ECG results was 0.37 (95% CI: 0.18, 0.73) for PPCM compared to other cardiomyopathies (p=0.006).

Conclusion

We demonstrated that an AI-ECG model for AF prediction may play a potential role in arrhythmia risk stratification/prediction among young women with PPCM who have a demonstrable lower risk for AF compared to women with other cardiomyopathies. Mechanisms for lower AF risk among patients with PPCM remain unknown. Further studies evaluating mechanistic pathways will be essential.

Funding Acknowledgement

Type of funding sources: None.

Convalescent plasma and COVID-19: Time for a second-second look?

In this short narrative, we highlight some of our experiences leading the US Convalescent Plasma Program at the beginning of the pandemic in the spring and summer of 2020. This includes a brief summary of how the program emerged and high-level lessons we learned. We also share our impressions about why convalescent plasma was used at scale in the United States, early in the pandemic and share ideas that might inform the use of convalescent plasma in future outbreaks of novel infectious diseases.

Sex Differences in the Impact of Aortic Valve Calcium Score on Mortality After Transcatheter Aortic Valve Replacement

BACKGROUND

Transcatheter aortic valve replacement (TAVR) is now an approved alternative to surgical aortic valve replacement for the treatment of severe aortic stenosis. As the clinical adoption of TAVR expands, it remains important to identify predictors of mortality after TAVR. We aimed to evaluate the impact of sex differences in aortic valve calcium score (AVCS) on long-term mortality following TAVR in a large patient sample.

METHODS

We included consecutive patients who successfully underwent TAVR for treatment of severe native aortic valve stenosis from June 2010 to May 2021 across all US Mayo Clinic sites with follow-up through July 2021. AVCS values were obtained from preoperative computed tomography of the chest. Additional clinical data were abstracted from medical records. Kaplan-Meier curves and Cox-proportional hazard regression models were employed to evaluate the effect of AVCS on long-term mortality.

RESULTS

A total of 2543 patients were evaluated in the final analysis. Forty-one percent were women, median age was 82 years (Q1: 76, Q3: 86), 18.4% received a permanent pacemaker following TAVR, and 88.5% received a balloon expandable valve. We demonstrate an increase in mortality risk with higher AVCS after multivariable adjustment (P<0.001). When stratified by sex, every 500-unit increase in AVCS was associated with a 7% increase in mortality risk among women (adjusted hazard ratio, 1.07 [95% CI, 1.02-1.12]) but not in men.

CONCLUSIONS

We demonstrate a notable sex difference in the association between AVCS and long-term mortality in a large TAVR patient sample. This study highlights the potential value of AVCS in preprocedural risk stratification, specifically among women undergoing TAVR. Additional studies are needed to validate this finding.

Diagnosis of Heart Failure With Preserved Ejection Fraction Among Patients With Unexplained Dyspnea

Importance

Diagnosis of heart failure with preserved ejection fraction (HFpEF) among dyspneic patients without overt congestion is challenging. Multiple diagnostic approaches have been proposed but are not well validated against the independent gold standard for HFpEF diagnosis of an elevated pulmonary capillary wedge pressure (PCWP) during exercise.

Objective

To evaluate H2FPEF and HFA-PEFF scores and a PCWP/cardiac output (CO) slope of more than 2 mm Hg/L/min to diagnose HFpEF.

Design, Setting, and Participants

This retrospective case-control study included patients with unexplained dyspnea from 6 centers in the US, the Netherlands, Denmark, and Australia from March 2016 to October 2020. Diagnosis of HFpEF (cases) was definitively ascertained by the presence of elevated PCWP during exertion; control individuals were those with normal rest and exercise hemodynamics.

Main Outcomes and Measures

Logistic regression was used to evaluate the accuracy of HFA-PEFF and H2FPEF scores to discriminate patients with HFpEF from controls.

Results

Among 736 patients, 563 (76%) were diagnosed with HFpEF (mean [SD] age, 69 [11] years; 334 [59%] female) and 173 (24%) represented controls (mean [SD] age, 60 [15] years; 109 [63%] female). H2FPEF and HFA-PEFF scores discriminated patients with HFpEF from controls, but the H2FPEF score had greater area under the curve (0.845; 95% CI, 0.810-0.875) compared with the HFA-PEFF score (0.710; 95% CI, 0.659-0.756) (difference, -0.134; 95% CI, -0.177 to -0.094; P < .001). Specificity was robust for both scores, but sensitivity was poorer for HFA-PEFF, with a false-negative rate of 55% for low-probability scores compared with 25% using the H2FPEF score. Use of the PCWP/CO slope to redefine HFpEF rather than exercise PCWP reclassified 20% (117 of 583) of patients, but patients reclassified from HFpEF to control by this metric had clinical, echocardiographic, and hemodynamic features typical of HFpEF, including elevated resting PCWP in 66% (46 of 70) of reclassified patients.

Conclusions and Relevance

In this case-control study, despite requiring fewer data, the H2FPEF score had superior diagnostic performance compared with the HFA-PEFF score and PCWP/CO slope in the evaluation of unexplained dyspnea and HFpEF in the outpatient setting.

The Pitfalls of Mining for QuantiFERON Gold in Severely Ill COVID-19 Patients

Objective

To assess the proportion of indeterminate QFT-Plus results in patients admitted with severe COVID-19 pneumonia and to evaluate the factors associated with indeterminate QFT-Plus results.

Study design

Retrospective cohort study.

Material & Methods

Data of COVID-19 admissions at Mayo Clinic Florida were extracted between October 13, 2020 and September 20, 2021, and from a pre-pandemic cohort between October 13, 2018 and September 20, 2019. Secondary analysis of the COVID-19 cohort was performed using gradient boosting modeling to generate variable importance and SHAP plots.

Results

Our findings demonstrated more indeterminate QFT-Plus test results among hospitalized patients with severe COVID-19 infection compared to non-COVID patients (139 of 495, 28.1%). Factors associated with indeterminate QFT-Plus tests included elevated C-reactive protein (CRP), ferritin, lactate dehydrogenase (LDH), and interleukin-6 (IL 6), as well as low leukocytes, lymphocytes, and platelets.

Conclusions

Patients with severe COVID-19 had a higher likelihood of indeterminate QFT-Plus results which were associated with elevated inflammatory markers consistent with severe infection. IGRA screening tests are likely confounded by COVID-19 infection itself, limiting the screening ability for LTBI reactivation. Indeterminate QFT-Plus results may also require follow-up QFT-Plus testing, after patient recovery from COVID-19, increasing cost and complexity of medical decision making and management. Additional risk assessments may be needed in this patient population for LTBI screening in severe COVID-19 infected patients.

Real-world performance, long-term efficacy, and absence of bias in the artificial intelligence enhanced electrocardiogram to detect left ventricular systolic dysfunction

Aims

Some artificial intelligence models applied in medical practice require ongoing retraining, introduce unintended racial bias, or have variable performance among different subgroups of patients. We assessed the real-world performance of the artificial intelligence-enhanced electrocardiogram to detect left ventricular systolic dysfunction with respect to multiple patient and electrocardiogram variables to determine the algorithm’s long-term efficacy and potential bias in the absence of retraining.

Methods and results

Electrocardiograms acquired in 2019 at Mayo Clinic in Minnesota, Arizona, and Florida with an echocardiogram performed within 14 days were analyzed (n = 44 986 unique patients). The area under the curve (AUC) was calculated to evaluate performance of the algorithm among age groups, racial and ethnic groups, patient encounter location, electrocardiogram features, and over time. The artificial intelligence-enhanced electrocardiogram to detect left ventricular systolic dysfunction had an AUC of 0.903 for the total cohort. Time series analysis of the model validated its temporal stability. Areas under the curve were similar for all racial and ethnic groups (0.90–0.92) with minimal performance difference between sexes. Patients with a ‘normal sinus rhythm’ electrocardiogram (n = 37 047) exhibited an AUC of 0.91. All other electrocardiogram features had areas under the curve between 0.79 and 0.91, with the lowest performance occurring in the left bundle branch block group (0.79).

Conclusion

The artificial intelligence-enhanced electrocardiogram to detect left ventricular systolic dysfunction is stable over time in the absence of retraining and robust with respect to multiple variables including time, patient race, and electrocardiogram features.

Low antispike antibody levels correlate with poor outcomes in COVID-19 breakthrough hospitalizations

BACKGROUND

While COVID-19 immunization programs attempted to reach targeted rates, cases rose significantly since the emergence of the delta variant. This retrospective cohort study describes the correlation between antispike antibodies and outcomes of hospitalized, breakthrough cases during the delta variant surge.

METHODS

All patients with positive SARS-CoV-2 polymerase chain reaction hospitalized at Mayo Clinic Florida from 19 June 2021 to 11 November 2021 were considered for analysis. Cases were analyzed by vaccination status. Breakthrough cases were then analyzed by low and high antibody titers against SARS-CoV-2 spike protein, with a cut-off value of ≥132 U/ml. Outcomes included hospital length of stay (LOS), need for intensive care unit (ICU), mechanical ventilation, and mortality. We used 1:1 nearest neighbor propensity score matching without replacement to assess for confounders.

RESULTS

Among 627 hospitalized patients with COVID-19, vaccine breakthrough cases were older with more comorbidities compared to unvaccinated. After propensity score matching, the unvaccinated patients had higher mortality (27 [28.4%] vs. 12 [12.6%], p = 0.002) and LOS (7 [1.0-57.0] vs. 5 [1.0-31.0] days, p = 0.011). In breakthrough cases, low-titer patients were more likely to be solid organ transplant recipients (16 [34.0%] vs. 9 [12.3%], p = 0.006), with higher need for ICU care (24 [51.1%] vs. 22 [11.0%], p = 0.034), longer hospital LOS (median 6 vs. 5 days, p = 0.013), and higher mortality (10 [21.3%] vs. 5 [6.8%], p = 0.025) than high-titer patients.

CONCLUSIONS

Hospitalized breakthrough cases were more likely to have underlying risk factors than unvaccinated patients. Low-spike antibody titers may serve as an indicator for poor prognosis in breakthrough cases admitted to the hospital.

Early administration of COVID-19 convalescent plasma with high titer antibody content by live viral neutralization assay is associated with modest clinical efficacy

The efficacy of COVID‐19 convalescent plasma (CCP) as a treatment for hospitalized patients with COVID‐19 remains somewhat controversial; however, many studies have not evaluated CCP documented to have high neutralizing antibody titer by a highly accurate assay. To evaluate the correlation of the administration of CCP with titer determined by a live viral neutralization assay with 7‐ and 28‐day death rates during hospitalization, a total of 23 118 patients receiving a single unit of CCP were stratified into two groups: those receiving high titer CCP (>250 50% inhibitory dilution, ID50; n = 13 636) or low titer CCP (≤250 ID50; n = 9482). Multivariable Cox regression was performed to assess risk factors. Non‐intubated patients who were transfused with high titer CCP showed 1.1% and 1.7% absolute reductions in overall 7‐ and 28‐day death rates, respectively, compared to those non‐intubated patients receiving low titer CCP. No benefit of CCP was observed in intubated patients. The relative benefit of high titer CCP was confirmed in multivariable Cox regression. Administration of CCP with high titer antibody content determined by live viral neutralization assay to non‐intubated patients is associated with modest clinical efficacy. Although shown to be only of modest clinical benefit, CCP may play a role in the future should viral variants develop that are not neutralized by other available therapeutics.

Artificial intelligence-electrocardiography to detect atrial fibrillation: trend of probability before and after the first episode

Aims

Artificial intelligence (AI) enabled electrocardiography (ECG) can detect latent atrial fibrillation (AF) in patients with sinus rhythm (SR). However, the change of AI-ECG probability before and after the first AF episode is not well characterized. We sought to characterize the temporal trend of AI-ECG AF probability around the first episode of AF.

Methods and results

We retrospectively studied adults who had at least one ECG in SR prior to an ECG that documented AF. An AI network calculated the AF probability from ECGs during SR (positive defined >8.7%, based on optimal sensitivity and specificity). The AI-ECG probability was reported prior to and after the first episode of AF and stratified by age and CHA₂DS₂-VASc score. Mixed effect models were used to assess the rate of change between time points. A total of 59 212 patients with 544 330 ECGs prior to AF and 413 486 ECGs after AF were included. The mean time between the first positive AI-ECG and first AF was 5.4 ± 5.7 years. The mean AI-ECG probability was 19.8% 2-5 years prior to AF, 23.6% 1-2 years prior to AF, 34.0% 0-3 months prior to AF, 40.9% 0-3 months after AF, 35.2% 1-2 years after AF, and 42.2% 2-5 years after AF (P < 0.001). The rate of increase prior to AF was higher for age >50 years CHA₂DS₂-VASc score ≥4.

Conclusion

The AI-ECG probability progressively increases with time prior to the first AF episode, transiently decreases 1-2 years following AF and continues to increase thereafter.

Clinical and Laboratory Profiles of SARS-CoV-2 Delta Variant Compared to Pre-Delta Variants

BACKGROUND

The emergence of SARS-CoV-2 variants of concern has led to significant phenotypical changes in transmissibility, virulence, and public health measures. Our study used clinical data to compare characteristics between a Delta variant wave and a pre-Delta variant wave of hospitalized patients.

METHODS

This single-center retrospective study defined a wave as an increasing number of COVID-19 hospitalizations, which peaked and later decreased. Data from the United States Department of Health and Human Services was used to identify the waves' primary variant. Wave 1 (08/08/20-04/01/21) was characterized by heterogeneous variants, while Wave 2 (06/26/21-10/18/21) was predominantly Delta variant. Descriptive statistics, regression techniques, and machine learning approaches supported the comparisons between waves.

RESULTS

From the cohort(n=1318), Wave 2 patients(n=665) were more likely to be younger, have fewer comorbidities, require more ICU care, and show an inflammatory profile with higher C-reactive protein, lactate dehydrogenase, ferritin, fibrinogen, prothrombin time, activated thromboplastin time, and INR compared to Wave 1. The gradient boosting model showed an area under the ROC curve of 0.854(sensitivity 86.4%;specificity 61.5%;positive predictive value 73.8%; negative predictive value 78.3%).

CONCLUSIONS

Clinical and laboratory characteristics can be used to estimate the COVID-19 variant regardless of genomic testing availability. This finding has implications for variant-driven treatment protocols and further research.

An artificial intelligence-enabled ECG algorithm for comprehensive ECG interpretation: Can it pass the 'Turing test'?

Objective

To develop an artificial intelligence (AI)–enabled electrocardiogram (ECG) algorithm capable of comprehensive, human-like ECG interpretation and compare its diagnostic performance against conventional ECG interpretation methods.

Methods

We developed a novel AI-enabled ECG (AI-ECG) algorithm capable of complete 12-lead ECG interpretation. It was trained on nearly 2.5 million standard 12-lead ECGs from over 720,000 adult patients obtained at the Mayo Clinic ECG laboratory between 2007 and 2017. We then compared the need for human over-reading edits of the reports generated by the Marquette 12SL automated computer program, AI-ECG algorithm, and final clinical interpretations on 500 randomly selected ECGs from 500 patients. In a blinded fashion, 3 cardiac electrophysiologists adjudicated each interpretation as (1) ideal (ie, no changes needed), (2) acceptable (ie, minor edits needed), or (3) unacceptable (ie, major edits needed).

Results

Cardiologists determined that on average 202 (13.5%), 123 (8.2%), and 90 (6.0%) of the interpretations required major edits from the computer program, AI-ECG algorithm, and final clinical interpretations, respectively. They considered 958 (63.9%), 1058 (70.5%), and 1118 (74.5%) interpretations as ideal from the computer program, AI-ECG algorithm, and final clinical interpretations, respectively. They considered 340 (22.7%), 319 (21.3%), and 292 (19.5%) interpretations as acceptable from the computer program, AI-ECG algorithm, and final clinical interpretations, respectively.

Conclusion

An AI-ECG algorithm outperforms an existing standard automated computer program and better approximates expert over-read for comprehensive 12-lead ECG interpretation.