Computational intelligence in early diabetes diagnosis: a review

The development of an effective diabetes diagnosis system by taking advantage of computational intelligence is regarded as a primary goal nowadays. Many approaches based on artificial network and machine learning algorithms have been developed and tested against diabetes datasets, which were mostly related to individuals of Pima Indian origin. Yet, despite high accuracies of up to 99% in predicting the correct diabetes diagnosis, none of these approaches have reached clinical application so far. One reason for this failure may be that diabetologists or clinical investigators are sparsely informed about, or trained in the use of, computational diagnosis tools. Therefore, this article aims at sketching out an outline of the wide range of options, recent developments, and potentials in machine learning algorithms as diabetes diagnosis tools. One focus is on supervised and unsupervised methods, which have made significant impacts in the detection and diagnosis of diabetes at primary and advanced stages. Particular attention is paid to algorithms that show promise in improving diabetes diagnosis. A key advance has been the development of a more in-depth understanding and theoretical analysis of critical issues related to algorithmic construction and learning theory. These include trade-offs for maximizing generalization performance, use of physically realistic constraints, and incorporation of prior knowledge and uncertainty. The review presents and explains the most accurate algorithms, and discusses advantages and pitfalls of methodologies. This should provide a good resource for researchers from all backgrounds interested in computational intelligence-based diabetes diagnosis methods, and allows them to extend their knowledge into this kind of research.     

Incidence and time course of early recovery of pulmonary vein conduction after catheter ablation of atrial fibrillation

Background: Although it is well recognized that recovery of pulmonary vein (PV) conduction is common among patients who fail atrial fibrillation (AF) ablation, little is known about the precise time course of recurrence.
Objective: To determine the incidence and time course of early recurrence of conduction after PV isolation during AF ablation.
Methods: The patient population was composed of 14 consecutive patients (9 men [64%]; age 56 ± 7 years) with AF who underwent radiofrequency catheter ablation via circumferential ablation with PV isolation, determined by a circular mapping catheter. After successful isolation of the PVs, repeat circular electrode recordings from each PV were obtained at 30 and 60 minutes.
Results: After complete isolation of all PVs, early PV recurrence was observed in 13 (93%) patients and 26 veins (50%). Seventeen veins (33%) showed a first recurrence at 30 minutes, while nine veins (17%) showed a first recurrence at 60 minutes.
Conclusion: The results reveal an extremely high rate of early recurrence of PV conduction following AF ablation. It is particularly notable that about one-fifth of the veins remained isolated at 30 minutes, but subsequently developed recurrence between 30 and 60 minutes. Of the veins that showed early recurrence, one-third developed a first recurrence at 60 minutes. These findings suggest that AF ablation procedures should incorporate a 60-minute waiting period after initial isolation in order to detect early recurrence of conduction.     

Benign and malignant lesions in the human breast depicted with ultrahigh resolution and three-dimensional optical coherence tomography

Institutional review board approval at the participating institutions was obtained. Informed consent was waived for this HIPAA-compliant study. The study purpose was to establish the correspondence of optical coherence tomographic (OCT) image findings with histopathologic findings to understand which features characteristic of breast lesions can be visualized with OCT. Imaging was performed in 119 specimens from 35 women aged 29-81 years with 3.5-microm axial resolution and 6-microm transverse resolution at 1.1-microm wavelength on freshly excised specimens of human breast tissue. Three-dimensional imaging was performed in 43 specimens from 23 patients. Microstructure of normal breast parenchyma, including glands, lobules, and lactiferous ducts, and stromal changes associated with infiltrating cancer were visible. Fibrocystic changes and benign fibroadenomas were identified. Imaging of ductal carcinoma in situ, infiltrating cancer, and microcalcifications correlated with corresponding histopathologic findings. OCT is potentially useful for visualization of breast lesions at a resolution greater than that of currently available clinical imaging methods.     

Routine chemoprophylaxis for deep venous thrombosis in Indian patients: Is it really justified?

Background:

Venous thromboembolism (VTE), which consists of deep vein thrombosis (DVT) and pulmonary embolism, is a potentially fatal disease. According to the Western literature, DVT of lower limb veins is one of the most common complications following total hip and knee arthroplasty and surgeries for lower limb fractures. Very few studies have been published from India on the subject and very little is known about the true incidence of the condition. The issue has acquired greater significance in Indian subjects in recent times as there is a manifold increase in the number of joint replacement surgeries and surgeries for lower limb fractures. There are no clear guidelines regarding the prophylaxis for VTE for Indian patients.

Materials and Methods:

We carried out a prospective study to determine the incidence of DVT. Present study included 125 patients undergoing total knee and hip joint arthroplasty and surgeries for fractures of the lower limb over a three-year period. All the patients underwent duplex ultrasonography between the seventh and 14^th postoperative day. No mechanical or chemical form of DVT prophylaxis was used.

Results:

Only nine patients (7.2%) showed sonographic evidence of DVT and the majority of them resolved without treatment. There was no case of pulmonary embolism.

Conclusion:

DVT following total joint arthroplasty and surgery for lower limb fractures in Indian patients is not as common as reported in the Western literature. A high level of suspicion and close clinical monitoring is mandatory, routine chemoprophylaxis is perhaps not justified in every patient undergoing lower limb surgery in our opinion. More trials involving a larger number of patients and at multi centers, in future, would be required to confirm the findings of our study.     

Association of Holter-based measures including T-wave alternans with risk of sudden cardiac death in the community-dwelling elderly: the Cardiovascular Health Study

Background

Sudden cardiac death (SCD) can be the first manifestation of cardiovascular disease. Development of screening methods for higher/lower risk is critical.

Methods

The Cardiovascular Health Study is a population-based study of risk factors for coronary heart disease and stroke those 65 years or older. Forty-nine (of 1649) with usable Holters and in normal sinus rhythm had SCD during follow-up and were matched with 2 controls, alive at the time of death of the case and not experiencing SCD on follow-up. Univariate and multivariate conditional logistic regression determined the association of Holter-based information and SCD.

Results

In univariate models, the upper half of ventricular premature contraction (VPC) counts, abnormal heart rate turbulence, decreased normalized low-frequency power, increased T-wave alternans (TWA), and decreased the short-term fractal scaling exponent (DFA₁) were associated with SCD, but time domain heart rate variability was not. In multivariate models, the upper half of VPC counts (odds ratio [OR], 6.6) and having TWA of 37 μV or greater on channel 2 (OR, 4.8) were independently associated with SCD. Also, the upper half of VPC counts (OR, 6.9) and having a DFA₁ of less than 1.05 (OR, 5.0) were independently associated with SCD. When additive effects were explored, having both higher VPCs and higher TWA was associated with an OR of 8.2 for SCD compared with 2.6 for having either. Also, having both higher VPCs and lower DFA₁ was associated with an OR of 9.6 for SCD compared with 3.1 for having either.

Conclusions

Results support a potential role for 24-hour Holter recordings to identify older adults at increased or lower risk of SCD.     

Progressive dilation of the ascending aorta in children with isolated bicuspid aortic valve

Although patients with bicuspid aortic valves (BAVs) are predisposed to ascending aortic (AA) dilation, stenosis, and dissection, the development of aortic disease in children with BAVs is poorly described. The purposes of this study were to determine the rate of change of AA diameter in children with BAVs and to identify risk factors for the development of aortic dilation. The echocardiograms of 276 children aged<19 years (mean 8.5+/-5.3) with isolated BAVs were reviewed. Aortic measurements were normalized to z scores on the basis of body surface area. In a subset of 112 patients with serial examinations, aortic growth rates were calculated and risk factors for more rapid aortic growth determined. At presentation, 33 patients (12%) demonstrated marked AA dilation (z>4), and 70 (25%) were moderately abnormal (z between 2 and 4). The mean+/-SD AA diameter increased more than expected, at a rate of 0.18+/-0.30 z score per year (p<0.0001). In 61 patients with normal AA diameters on initial study, 22 (36%) had abnormal diameters, with z scores>2, at follow-up. Univariate analysis demonstrated right-noncoronary commissural fusion (p<0.02) and aortic valve gradient on initial examination (p<0.02) as significant predictors of AA growth. In multivariate analysis, however, the significance of gradient and valve morphology was diminished (p = 0.06 for both). In conclusion, the progression of AA diameter in patients with normal z scores on initial examination suggests that serial echocardiograms are required to screen for the development of significant aortic dilation.     

Evolving role of multidetector computed tomography in evaluation of arrhythmogenic right ventricular dysplasia/cardiomyopathy

The purpose of this study was to report 1 center's experience with multidetector computed tomography (MDCT) in the evaluation of patients suspected to have arrhythmogenic right ventricular (RV) dysplasia/cardiomyopathy (ARVD/C). RV dilatation/dysfunction is 1 of the most important criteria for establishing the diagnosis of ARVD/C. Cardiac magnetic resonance imaging (MRI) is the most preferred imaging modality for the diagnosis of ARVD/C. However, many patients with suspected ARVD/C have implantable cardioverter-defibrillators, prohibiting the use of MRI. Thirty-one patients (19 men; mean age 41 +/- 12 years) referred for evaluation of known or suspected ARVD/C had a complete reevaluation including contrast-enhanced cardiac MDCT at the center. Two patients underwent both cardiac MRI and MDCT. Seventeen of 31 patients met Task Force criteria for ARVD/C and were confirmed to have ARVD/C. Multidetector computed tomographic images were analyzed for qualitative and quantitative characteristic findings of ARVD/C. Increased RV trabeculation (p <0.001), RV intramyocardial fat (p <0.001), and scalloping (p <0.001) were significantly associated with the final diagnosis of ARVD/C. RV volumes, RV inlet dimensions, and RV outflow tract surface area were increased in patients with ARVD/C compared with patients who did not meet the criteria. RV and left ventricular functional analysis was performed in 2 patients. In conclusion, cardiac MDCT has a strong potential to detect many qualitative and quantitative abnormalities of the right ventricle in patients with ARVD/C. Limitations include implantable cardioverter-defibrillators and motion artifacts, along with well-known radiation and contrast-induced reaction.