Search

Abstract Blood pressure variability (BPV) and heart rate variability (HRV) have been associated with Alzheimer’s Disease and Related Dementias (ADRD) in rigorously controlled studies. However, the extent to which BPV and HRV may offer predictive information in real-world, routine clinical care is unclear. In a retrospective cohort study of 48,204 adults (age 54.9 ± 17.5 years, 60% female) receiving continuous care at a single center, we derived BPV and HRV from routinely collected clinical data. We use multivariable Cox models to evaluate the association of BPV and HRV, separately and in combination, with incident ADRD. Over a median 3 [2.4, 3.0] years, there were 443 cases of new-onset ADRD. We found that clinically derived measures of BPV, but not HRV, were consistently associated with incident ADRD. In combined analyses, only patients in both the highest quartile of BPV and lowest quartile of HRV had increased ADRD risk (HR 2.34, 95% CI 1.44–3.81). These results indicate that clinically derived BPV, rather than HRV, offers a consistent and readily available metric for ADRD risk assessment in a real-world patient care setting. Thus, implementation of BPV as a widely accessible tool could allow clinical providers to efficiently identify patients most likely to benefit from comprehensive ADRD screening.

Abstract Background Undiagnosed chronic kidney disease (CKD) is a common and usually asymptomatic disorder that causes a high burden of morbidity and early mortality worldwide. We developed a deep learning model for CKD screening from routinely acquired ECGs. Methods We collected data from a primary cohort with 111,370 patients which had 247,655 ECGs between 2005 and 2019. Using this data, we developed, trained, validated, and tested a deep learning model to predict whether an ECG was taken within one year of the patient receiving a CKD diagnosis. The model was additionally validated using an external cohort from another healthcare system which had 312,145 patients with 896,620 ECGs between 2005 and 2018. Results Using 12-lead ECG waveforms, our deep learning algorithm achieves discrimination for CKD of any stage with an AUC of 0.767 (95% CI 0.760–0.773) in a held-out test set and an AUC of 0.709 (0.708–0.710) in the external cohort. Our 12-lead ECG-based model performance is consistent across the severity of CKD, with an AUC of 0.753 (0.735–0.770) for mild CKD, AUC of 0.759 (0.750–0.767) for moderate-severe CKD, and an AUC of 0.783 (0.773–0.793) for ESRD. In patients under 60 years old, our model achieves high performance in detecting any stage CKD with both 12-lead (AUC 0.843 [0.836–0.852]) and 1-lead ECG waveform (0.824 [0.815–0.832]). Conclusions Our deep learning algorithm is able to detect CKD using ECG waveforms, with stronger performance in younger patients and more severe CKD stages. This ECG algorithm has the potential to augment screening for CKD.

Background: Laboratory testing is routinely used to assay blood biomarkers to provide information on physiologic state beyond what clinicians can evaluate from interpreting medical imaging. We hypothesized that deep learning interpretation of echocardiogram videos can provide additional value in understanding disease states and can evaluate common biomarkers results. Methods: We developed EchoNet-Labs, a video-based deep learning algorithm to detect evidence of anemia, elevated B-type natriuretic peptide (BNP), troponin I, and blood urea nitrogen (BUN), as well as values of ten additional lab tests directly from echocardiograms. We included patients (n = 39,460) aged 18 years or older with one or more apical-4-chamber echocardiogram videos (n = 70,066) from Stanford Healthcare for training and internal testing of EchoNet-Lab's performance in estimating the most proximal biomarker result. Without fine-tuning, the performance of EchoNet-Labs was further evaluated on an additional external test dataset (n = 1,301) from Cedars-Sinai Medical Center. We calculated the area under the curve (AUC) of the receiver operating characteristic curve for the internal and external test datasets. Findings: On the held-out test set of Stanford patients not previously seen during model training, EchoNet-Labs achieved an AUC of 0.80 (0.79-0.81) in detecting anemia (low hemoglobin), 0.86 (0.85-0.88) in detecting elevated BNP, 0.75 (0.73-0.78) in detecting elevated troponin I, and 0.74 (0.72-0.76) in detecting elevated BUN. On the external test dataset from Cedars-Sinai, EchoNet-Labs achieved an AUC of 0.80 (0.77-0.82) in detecting anemia, of 0.82 (0.79-0.84) in detecting elevated BNP, of 0.75 (0.72-0.78) in detecting elevated troponin I, and of 0.69 (0.66-0.71) in detecting elevated BUN. We further demonstrate the utility of the model in detecting abnormalities in 10 additional lab tests. We investigate the features necessary for EchoNet-Labs to make successful detection and identify potential mechanisms for each biomarker using well-known and novel explainability techniques. Interpretation: These results show that deep learning applied to diagnostic imaging can provide additional clinical value and identify phenotypic information beyond current imaging interpretation methods. Funding: J.W.H. and B.H. are supported by the NSF Graduate Research Fellowship. D.O. is supported by NIH K99 HL157421-01. J.Y.Z. is supported by NSF CAREER 1942926, NIH R21 MD012867-01, NIH P30AG059307 and by a Chan-Zuckerberg Biohub Fellowship.

An EDGE deep crustal seismic reflection transect of the eastern Aleutian arc-trench traces oceanic crust and Moho more than 200 km beneath the accretionary prism to depths of more than 30 km. These horizons project beneath a prominent sequence of layered reflectors that extends from about 9 to 35 km beneath the Mesozoic core of the prism. Earthquake hypocenters imply continuity of the downgoing lithosphere from the base of the layered reflectors to beneath and beyond the active Augustine volcano. Rapid lateral growth of the prism in Eocene-Oligocene time coincided with uplift of the Mesozoic core of the prism. During lateral growth, maintenance of critical taper requires thickening, either by internal deformation or underplating. Because exposed rocks show only modest postemplacement shortening, thickening most likely occurred by underplating, probably of the layered reflectors. The overall geometry of the layered reflectors is reminiscent of nappe structures, and their emplacement may represent crustal-scale duplexing associated with underplating. The EDGE reflection data and borehole results indicate that the shelf edge is marked by an active out-of-sequence thrust that separates the Paleogene and Neogene prisms. This thrust apparently developed in response to the prism's need to maintain critical taper and demonstrates that contrasts in lithology can result from mechanisms other than terrane emplacement.