Thoracic Aortic Aneurysm Risk Assessment: A Machine Learning Approach.

Background: Traditional methods of risk assessment for thoracic aortic aneurysm (TAA) based on aneurysm size alone have been called into question as being unreliable in predicting complications. Biomechanical function of aortic tissue may be a better predictor of risk, but it is difficult to determine in vivo. Objectives: This study investigates using a machine learning (ML) model as a correlative measure of energy loss, a measure of TAA biomechanical function. Methods: Biaxial tensile testing was performed on resected TAA tissue collected from patients undergoing surgery. The energy loss of the tissue was calculated and used as the representative output. Input parameters were collected from clinical assessments including observations from medical scans and genetic paneling. Four ML algorithms including Gaussian process regression were trained in Matlab. Results: A total of 158 patients were considered (mean age 62 years, range 22-89 years, 78% male), including 11 healthy controls. The mean ascending aortic diameter was 47 ± 10 mm, with 46% having a bicuspid aortic valve. The best-performing model was found to give a greater correlative measure to energy loss (R2 = 0.63) than the surprisingly poor performance of aortic diameter (R2 = 0.26) and indexed aortic size (R2 = 0.32). An echocardiogram-derived stiffness metric was investigated on a smaller subcohort of 67 patients as an additional input, improving the correlative performance from R2 = 0.46 to R2 = 0.62. Conclusions: A preliminary set of models demonstrated the ability of a ML algorithm to improve prediction of the mechanical function of TAA tissue. This model can use clinical data to provide additional information for risk stratification.

Seasonal to multiannual marine ecosystem prediction with a global Earth system model.

Climate variations have a profound impact on marine ecosystems and the communities that depend upon them. Anticipating ecosystem shifts using global Earth system models (ESMs) could enable communities to adapt to climate fluctuations and contribute to long-term ecosystem resilience. We show that newly developed ESM-based marine biogeochemical predictions can skillfully predict satellite-derived seasonal to multiannual chlorophyll fluctuations in many regions. Prediction skill arises primarily from successfully simulating the chlorophyll response to the El Niño-Southern Oscillation and capturing the winter reemergence of subsurface nutrient anomalies in the extratropics, which subsequently affect spring and summer chlorophyll concentrations. Further investigations suggest that interannual fish-catch variations in selected large marine ecosystems can be anticipated from predicted chlorophyll and sea surface temperature anomalies. This result, together with high predictability for other marine-resource-relevant biogeochemical properties (e.g., oxygen, primary production), suggests a role for ESM-based marine biogeochemical predictions in dynamic marine resource management efforts.

Comment on "Multiyear prediction of monthly mean Atlantic Meridional Overturning Circulation at 26.5°N".

Matei et al. (Reports, 6 January 2012, p. 76) claim to show skillful multiyear predictions of the Atlantic Meridional Overturning Circulation (AMOC). However, these claims are not justified, primarily because the predictions of AMOC transport do not outperform simple reference forecasts based on climatological annual cycles. Accordingly, there is no justification for the "confident" prediction of a stable AMOC through 2014.