A review of evidence of health benefit from artificial neural networks in medical intervention

Artificial neural networks: Current status in cardiovascular medicine

Background and Purpose —Cerebrovascular events (CVE) in patients with prosthetic heart valves (PHV) have remained a severe and frequent complication despite oral anticoagulation with or without aspirin. We studied the possible pathophysiological involvement of platelet-derived microparticles (PMP) as a contributing factor for the increased incidence of CVE in patients with PHV.

Methods —We compared in a retrospective, case-control study the clinical outcome after the implantation of the PHV with several different independent morphological and functional methods, including simultaneous transcranial Doppler monitoring of both middle cerebral arteries, PMP detection by flow cytometry with use of platelet-specific antibodies, coagulation markers, and determination of the procoagulant activity by Russell’s viper venom time, a phospholipid-dependent coagulation assay.

Results —Eight of 26 patients with PHV had 9 CVE during 136 person-years of observation. Transcranial Doppler monitoring revealed an increased frequency of microembolic signals recorded over a 30-minute period in patients with CVE (75±25; median, 55; range, 27 to 248) compared with those without CVE (23±12; median, 7; range, 0 to 153; P <0.05) or with control subjects (0; P <0.001). Flow cytometry analysis showed increased levels of PMP in patients with compared to those without CVE (4.1±0.6% versus 2.4±0.4% of all fluorescence-positive events gated; P <0.05). Increased procoagulant activity was documented by the shortened Russell’s viper venom time expressed as an increased level of platelet equivalents per microliter of plasma in patients compared with control subjects (+24.7±14.9%; P <0.01). Subgroup analysis revealed that patients with CVE had a higher excess of platelet equivalents per microliter of plasma than patients without CVE in relation to the controls (+68.7±36.7%; P <0.05). Mildly elevated thrombin–antithrombin III complexes (2.9±0.7; median, 2.3; normal, <2.0 μg/L) suggested incompletely suppressed thrombin formation, and fibrin generation (fibrinopeptide A) was in the upper normal range (2.1±0.2; median, 1.8; normal, <2.0 ng/mL), despite adequate anticoagulation (INR=3.6±0.1).

Conclusions —Our data show increased microembolic signals, platelet microparticles, and procoagulant activity in symptomatic patients with PHV and provide a potential pathophysiological explanation of CVE.

Mechanisms of Cerebrovascular Events as Assessed by Procoagulant Activity, Cerebral Microemboli, and Platelet Microparticles in Patients With Prosthetic Heart Valves

Background and Purpose —High-intensity transient signals (HITS) during cardiac surgery are capable of causing encephalopathy and cognitive deficits. This study was undertaken to determine whether intraoperative HITS cause alterations of neuropsychological function (NPF) and/or cerebral glucose metabolism (CMRGlc), even in a low-risk patient group, and whether induced changes are interrelated.

Methods —Eighteen patients without signs of cerebrovascular disease underwent elective coronary artery bypass grafting (CABG), and two of these additionally underwent valve replacement in normothermia. Intraoperatively, HITS were recorded by means of transcranial Doppler ultrasonography (TCD). Perioperatively, NPF and CMRGlc were assessed using a standardized complex test battery and positron emission tomography with 18F-2-fluoro-2-deoxy-d-glucose (FDG-PET), respectively.

Results —Intraoperatively, the number of HITS ranged from 90 to 1710 per patient and hemisphere, more on the right side than on the left ( P <.05). HITS occurred primarily during cardiopulmonary bypass (71.3%) and, to a lesser extent, during aortic manipulation (22.2%). Changes in global and regional CMRGlc between first (one day preoperatively) and second (8 to 12 days postoperatively) FDG-PET scans were mild. No correlations were found between the number of HITS, age of patient, duration of cardiac ischemia or cardiopulmonary bypass and the changes in CMRGlc. In patients with recorded HITS and a postoperative decrease of regional CMRGlc (n=11), the maximal decrease of rCMRGlc in each hemisphere below the individual global change of CMRGlc correlated with the number of HITS ( r =−0.46, P <.05). Limitations in NPF occurred 8 to 12 days postoperatively, resolved within 3 months, and were not found to be correlated to the absolute number of HITS or changes in CMRGlc.

Conclusions —HITS during cardiac surgery can cause alterations of both NPF and CMRGlc, even in a low-risk patient group. However, the number of HITS and changes in NPF and CMRGlc are not necessarily interrelated, which indicates that (1) the location of brain damage related to HITS is more important for the development of NPF than is the absolute number of HITS, and (2) factors in addition to HITS might contribute to surgery-related brain damage.

Alterations of Neuropsychological Function and Cerebral Glucose Metabolism After Cardiac Surgery Are Not Related Only to Intraoperative Microembolic Events

It is 5 years since Spencer and colleagues1 described in this journal the detection of embolic signals thought to represent solid material released from carotid plaques during the dissection phase of carotid endarterectomy. There has been a rapid spread of interest in this technique. A number of reports have demonstrated the detection of embolic signals in patients with a wide variety of potential embolic sources, and it has been suggested that this detection may already form an important clinical investigational tool. Others have cautioned skepticism.2 

The principles underlying ultrasonic detection of cerebral emboli are relatively simple. Being both larger than the surrounding red blood cells and of a different material with different acoustic impedance than the surrounding blood, the incident ultrasound beam is both reflected and scattered at the interface between the embolus and blood. This results in an increase in the intensity of the received signal which, as the embolus is in the sample volume for a short time only, is of short duration. It has been clearly demonstrated in both animal models3 4 and flow models5 that platelet, thrombus, atheroma, and fat emboli result in the expected short-duration, high-intensity signal, usually within the Doppler flow spectrum. In these experimental studies, emboli smaller than 200 to 400 μm could not be reliably introduced, but it is likely that much smaller emboli can be detected using this technique. The intensity increase tends to be unidirectional, and frequency or velocity focused. In contrast, artifact results in predominantly bidirectional signals that can usually, but not always, be easily distinguished.6 

Preliminary studies have reported the detection of similar signals in patients with carotid stenosis,7 8 9 10 11 12 prosthetic cardiac valves,13 14 15 16 myocardial infarction,17 atrial fibrillation,18 19 and native cardiac valve …

Microembolic Signal Detection Using Ultrasound

Background and Purpose The purpose of this study was the evaluation of intraobserver, interobserver, and intrasubject variability in the Doppler detection of microembolic signals in patients with mechanical prosthetic valves. Simultaneously, the feasibility of automated embolus detection by means of a neuronal network was investigated.

Methods From 25 patients with mechanical prosthetic heart valves, single transcranial Doppler monitoring sessions of 30 minutes’ duration were recorded on videotape, randomized, and subsequently analyzed by eight independent trained observers from three centers. Three observers evaluated these tapes on three separate occasions, blinded to their previous results. An additional 48 patients with prosthetic heart valves were repetitively monitored with transcranial Doppler ultrasonography for 30 minutes three times within 1 year to examine the long-term variability in the occurrence of microembolic signals. Finally, in an effort to assess the short-term intrasubject variability, 20 patients were examined for 90 minutes, and the results of the three 30-minute periods were compared. The interobserver, intraobserver, and intrasubject (both short- and long-term) variability was evaluated.

Results No significant differences in microembolic signal counts were found among the different observers, between the human observers and the neuronal network, or among the three separate evaluations of stored data by the same observer. The same was true for repeat examinations of the same patient ( P >.05, Student’s two-paired t test and Friedman’s test).

Conclusions The detection of microembolic signals in patients with prosthetic cardiac valves is a reproducible technique. The reliable performance of the neuronal network argues for a broader use of this device. The intrasubject stability of the microembolic rate over 1 year supports the concept that the underlying emboligenic process is associated with intrinsic mechanical properties of the valve implant and not due to a thromboembolic process in the heart.

Variability of Doppler Microembolic Signal Counts in Patients With Prosthetic Cardiac Valves

Handle everyday research tasks with reliable, citation-backed results

Your personal Research Agent to handle research tasks with citation-backed results

Popular Tasks used by Researchers

How can I help with your research?

Meet SciSpace

Get more enhanced response by uploading the PDFs you want me to reference.

No relevant PDFs in your library

SciSpace is the AI research assistant for academics. Run systematic literature reviews on 280M+ papers, and write papers with cited sources. Trusted by 1M+ students, PhDs & researchers.

SciSpace | AI for Research

Analyze PDFs

Code & Manuscripts

Funding & Grants

Literature & Patents

Medical & Clinical Data

Systematic Review

Visualize & Present

Web & Data

Build a Google Scholar-like website for your research.

Build a website

Create charts and images for your research

Create a Chart

Write a paper for submission to a journal

Draft a manuscript

Patent Search

Design eye-catching scientific posters in minutes.

Scientific Poster Generation

Systematic Literature Review

One task is running at the moment. Your messages will be shown right after.

Drag and drop or click here to browse

Loved by <highlight>1 million+</highlight> researchers

Extract a list of specific topics and their sources from unstructured text

Topics

Compare and analyze relevant papers that matches with your search

Papers

Get insights from PDFs and bookmarked papers from your library

My library

Recent searches

Try searching for:

Catch AI-generated content in scholarly and non-scholarly content

{ai} Detector

Ai Writer

Get PDF Summaries, highlighted text explanations 

Chat with PDF

Effortlessly create in-text citations and bibliographies in APA and 2,500 other formats

Citation generator

Get explanations, summaries, and answers on academic papers

Ease up your research workflow with {scispace}'s cohort of exciting AI tools

Elevate your academic writing skills and convey your ideas the way you want

Paraphraser

Explore our range of reading and writing tools

Your file is being prepared and should be ready in a few minutes. If it's a large file, it might take a bit longer. You can close this window, and we'll email you the file when it's done.

You have reached a maximum limit of <strong>{limit}</strong> columns in the table. Remove at least <strong>1</strong> column to add or create another one.

P. Zunker

Author Tools

Chat about Author

Papers

Variability of Doppler Microembolic Signal Counts in Patients With Prosthetic Cardiac Valves