Search

Aims. To demonstrate the coexistence of skin disorders and diabetes mellitus (DM) in women with poor obstetric history. Methodology. This retrospective study comprised 69 women having poor obstetric history and skin disorders. The patients were grouped as control group (51 women without type 2 DM, with 84 skin disorders in total) and study group (18 women with type 2 DM, with 30 skin disorders in total). Skin disorders were grouped as follows: herpes zoster, viral warts, fungal diseases, melanocytic nevi, bacterial infections, hidradenitis suppurativa, dermatitis, psoriasis, lichen planus, urticaria, hair and nail disorders, acneiform diseases, epidermal cyst, melanine hyperpigmentation, hypertrophic disorders of the skin, mycosis fungoides and vitiligo. Beksaç Obstetric Index (BOI), which is “(the number of living child + π/10)/gravida”, was used for the evaluation of obstetric history. Results. The rate of DM was found to be 26.1% in this specific study population. We have demonstrated multiple skin disorders in 50% (9/18) of DM (+) women, while this rate was 37.3% (19/51) in the DM (-) women (p=0.504). A total of 114 skin disorders in 69 women were evaluated, and the rates of the dermatitis (38.9% versus 19.6%) and acneiform diseases (27.8% versus 13.7%) were found to be more frequent in DM (+) patients compared to DM (-) women (p>0.05, for all). Conclusions. Skin disorders are easy to detect in medical examinations and can be used as a remark for the investigation of DM, especially in women with poor obstetric history. [ABSTRACT FROM AUTHOR]

Aim. The validation of an artificial intelligent system (AIS) - Ankara System Version 5.0 - for the interpretation of antepartum fetal heart rate (FHR) tracings. Methodology. This study consisted of 3100 assuring FHR tracings obtained from normal pregnancies and 467 non-assuring FHR tracings (13.09% of all cases) obtained from pregnancies with various types of maternal health risk factors and/or obstetric complications. Assuring tracings from complicated pregnancies and non-assuring tracings from normal pregnancies were not included in the study, in order to have a qualified database. All tracings were evaluated twice by a single expert. The first evaluation took place just after data acquisition and the second occurred two weeks later without knowledge of the clinical characteristics of the patient (unmatched tracing evaluations were not included in the database). A total of 3032 of them were used for the training of the algorithms, while 535 of them were used for testing and validation. A Doppler ultrasound fetal heart rate monitor with autocorrelation (Hewlett Packard, 8040A) was connected to a computer system by a special frame grabber. Ten-minute recordings were kept in a special file for pattern recognition and decision making. Wavelet transformation was used for feature extraction as the first step of pattern recognition. Unsupervised and supervised artificial neural networks (vector quantization and backpropagation learning algorithm, respectively), the second step of pattern recognition, were used as the classification steps of the hybrid AIS. Results. The testing group consisted of 480 assuring and 55 non-assuring tracings. The sensitivity and specificity of the Ankara System (Version 5.0) were found to be 61.25% and 98.68%, respectively, while the positive predictive value and negative predictive value were calculated to be 89.1% and 93.5%, respectively. Conclusions. This hybrid AIS (Ankara System Version 5.0) might be an effective alternative decision-making tool in the routine practice for the interpretation of FHR tracings. [ABSTRACT FROM AUTHOR]