Non-Invasive Pulmonary Capillary Wedge Pressure Assessment on Speckle Tracking Echocardiography as a Predictor of New-Onset Non-Valvular Atrial Fibrillation - Four-Year Prospective Study (NIPAF Study)

Radiomics in Echocardiography: Deep Learning and Echocardiographic Analysis

PURPOSE OF REVIEW

Recent development in artificial intelligence (AI) for cardiovascular imaging analysis, involving deep learning, is the start of a new phase in the research field. We review the current state of AI in cardiovascular field and discuss about its potential to improve clinical workflows and accuracy of diagnosis.

RECENT FINDINGS

In the AI cardiovascular imaging field, there are many applications involving efficient image reconstruction, patient triage, and support for clinical decisions. These tools have a role to support repetitive clinical tasks. Although they will be powerful in some situations, these applications may have new potential in the hands of echo cardiologists, assisting but not replacing the human observer. We believe AI has the potential to improve the quality of echocardiography. Someday AI may be incorporated into the daily clinical setting, being an instrumental tool for cardiologists dealing with cardiovascular diseases.

Relationships among pulmonary capillary wedge pressure, dry weight and natriuretic peptide in patients undergoing hemodialysis: a three-dimensional speckle tracking echocardiography study

BACKGROUND

Although the evaluation of fluid status in hemodialysis (HD) patients is useful, relationship among pulmonary capillary wedge pressure (PCWP), dry body weight (DW) and natriuretic peptide has not been elucidated. In addition, there has been no objective marker for instantaneously monitoring hemodynamic improvement in response to HD. We previously reported that PCWP and time constant of left ventricular pressure decline (Tau) can be noninvasively estimated (ePCWP and eTau) by speckle tracking echocardiography (STE). The aim of this study was to elucidate the relationship among ePCWP, eTau, DW and natriuretic peptide in patients undergoing HD.

METHODS

We measured ePCWP and body weight (BW) by STE in 81 patients and ANP and BNP by blood examination in 31 patients just before and after HD during sinus rhythm.

RESULTS

The ePCWP decreased after HD, and this was associated with reductions in ln ANP, eTau and BW (r = 0.523, 0.271 and 0.814, respectively, p < 0.05). The % change in ePCWP was not correlated with the % change in ln BNP (p = 0.47). The change in ePCWP had a stronger correlation with the % change in BW than the change in any other parameters.

CONCLUSIONS

The ePCWP is more sensitive to estimate the change in BW during HD than any other parameters such as ANP and BNP. These results indicated that a substantial amount of excess fluid can be assessed real-time by STE using ePCWP.

Utilization of Artificial Intelligence in Echocardiography

Echocardiography has a central role in the diagnosis and management of cardiovascular disease. Precise and reliable echocardiographic assessment is required for clinical decision-making. Even if the development of new technologies (3-dimentional echocardiography, speckle-tracking, semi-automated analysis, etc.), the final decision on analysis is strongly dependent on operator experience. Diagnostic errors are a major unresolved problem. Moreover, not only can cardiologists differ from one another in image interpretation, but also the same observer may come to different findings when a reading is repeated. Daily high workloads in clinical practice may lead to this error, and all cardiologists require precise perception in this field. Artificial intelligence (AI) has the potential to improve analysis and interpretation of medical images to a new stage compared with previous algorithms. From our comprehensive review, we believe AI has the potential to improve accuracy of diagnosis, clinical management, and patient care. Although there are several concerns about the required large dataset and "black box" algorithm, AI can provide satisfactory results in this field. In the future, it will be necessary for cardiologists to adapt their daily practice to incorporate AI in this new stage of echocardiography.

Left Ventricular Torsion in Hypertension and Hypertensive Heart Failure ― 3-Dimensional Speckle Tracking Echocardiography Assessment ―

Background: Left ventricular (LV) torsion by contraction of inner and outer oblique muscles contributes to EF. Outer muscle plays a predominant role in torsion. We evaluated the impact of LV remodeling by hypertension (HTN) on torsion using 3-dimensional speckle tracking echocardiography (3D-STE).

Methods and Results: LV strain, strain rate during systole (SR-S) and torsion at endocardium, mid-wall and epicardium were assessed on 3D-STE in 53 controls and 186 HTN patients. Torsion was defined as the difference between apical and basal rotation divided by long axis length. LVEF and strain, SR-S and torsion in all 3 layers in HTN without LV hypertrophy (LVH) were similar to those in controls. LV longitudinal strain at endocardium in HTN with LVH decreased, whereas LVEF was similar to that in controls and, which was associated with increased torsion at epicardium. Reduced LVEF in hypertensive HF was associated with reduced strain, SR-S and torsion in all layers and with LV dilation. On multivariate analysis, epicardial torsion was an independent determinant of LVEF. At epicardial torsion cut-off 0.41, the sensitivity and specificity for the identification of HFrEF were 88% and 68%.

Conclusions: Torsion on 3D-STE may represent a compensatory mechanism to maintain LVEF despite reduced endocardial function, suggesting that the deterioration of torsion caused by insult to outer muscle and dilation may lead to HFrEF.