Attitudes and practices of private medical providers towards family planning and abortion services in Nigeria

CONTEXT

The study was designed to investigate the attitudes and practices of private medical practitioners towards abortion, postabortion care and postabortion family planning in Nigeria.

METHODS

Three hundred and twenty-three private practitioners who were proprietors of private clinics in three states of the country were interviewed with a structured questionnaire that elicited information on their knowledge and experiences of abortion and postabortion care in the cities.

RESULTS

Twenty-four percent of the doctors reported that they routinely terminate unwanted pregnancies when requested to do so by women, while 82% reported that they frequently treat women who experience complications of unsafe abortion. Over 45% reported that they use manual vacuum aspiration (MVA) for the management of abortion in the first trimester, while 25% use dilatation and curettage (D and C). Nearly 28% reported the use of MVA followed by D and C in the first trimester. Fifty-seven percent reported their lack of expertise in managing second-trimester abortions, while those admitting that they manage second-trimester abortions reported nonstandard methods and procedures. In addition, there was evidence of inadequate counseling of women, lack of institutional protocols and poor use of postabortion family planning by the doctors.

CONCLUSIONS

These results suggest the need for a program of retraining of private practitioners on the principles and practices of safe abortion, postabortion care and family planning in Nigeria and the integration of these topics into medical training curricula in the country.

Cancer of the cervix in Zaria, Northern Nigeria

Objective:

Carcinoma of the cervix is still the most common gynecological malignancy among women in the developing nations. The purpose of this study is to review the pattern of carcinoma of the cervix in Zaria, Northern Nigeria.

Method:

This is a retrospective study of patients seen at the Gynecologic oncology unit of Ahmadu Bello University Teaching Hospital, Zaria, Nigeria between November 2005 and November 2009.

Results:

A total of 406 gynecological cancers were identified during the period under review. Carcinoma of the cervix accounted for 65.7 % (267) of histologically confirmed gynecological cancers. Most of the patients were married 265 (99.2 %) and 40% were in the second order of marriage; 57.1% of these women were in a polygamous setting. Two hundred and two (75.6 %) patients fell in the 40Œ69 year age bracket, with a mean age of 44.5 years. The disease appears to be associated with high parity (range of 0Œ14); grand multiparous patients constituted 145 (68.3%) of the cases. Abnormal vaginal bleeding (219 patients: 82 %), offensive vaginal discharge (120 patients: 44.9%) and post-coital bleeding (56 patients: 20.9%) were the most common symptoms. About 78% of the patients had advanced disease, stage III disease being the commonest stage accounting for 159 (59.5 %). Fifty-six (21%) of these patients presented with vesico-vaginal fistula.

Conclusion:

This study demonstrates that in the northern part of Nigeria 65.7% of all gynecological cancers are carcinoma of the cervix. This high percentage appears to be connected with some detrimental sociocultural practices, such as early onset of sexual activity, which should be addressed. More emphasis should be given to screening programs for women in under-developed countries.

GestroNet: A Framework of Saliency Estimation and Optimal Deep Learning Features Based Gastrointestinal Diseases Detection and Classification

In the last few years, artificial intelligence has shown a lot of promise in the medical domain for the diagnosis and classification of human infections. Several computerized techniques based on artificial intelligence (AI) have been introduced in the literature for gastrointestinal (GIT) diseases such as ulcer, bleeding, polyp, and a few others. Manual diagnosis of these infections is time consuming, expensive, and always requires an expert. As a result, computerized methods that can assist doctors as a second opinion in clinics are widely required. The key challenges of a computerized technique are accurate infected region segmentation because each infected region has a change of shape and location. Moreover, the inaccurate segmentation affects the accurate feature extraction that later impacts the classification accuracy. In this paper, we proposed an automated framework for GIT disease segmentation and classification based on deep saliency maps and Bayesian optimal deep learning feature selection. The proposed framework is made up of a few key steps, from preprocessing to classification. Original images are improved in the preprocessing step by employing a proposed contrast enhancement technique. In the following step, we proposed a deep saliency map for segmenting infected regions. The segmented regions are then used to train a pre-trained fine-tuned model called MobileNet-V2 using transfer learning. The fine-tuned model's hyperparameters were initialized using Bayesian optimization (BO). The average pooling layer is then used to extract features. However, several redundant features are discovered during the analysis phase and must be removed. As a result, we proposed a hybrid whale optimization algorithm for selecting the best features. Finally, the selected features are classified using an extreme learning machine classifier. The experiment was carried out on three datasets: Kvasir 1, Kvasir 2, and CUI Wah. The proposed framework achieved accuracy of 98.20, 98.02, and 99.61% on these three datasets, respectively. When compared to other methods, the proposed framework shows an improvement in accuracy.

SkinNet‐ENDO: Multiclass skin lesion recognition using deep neural network and Entropy‐Normal distribution optimization algorithm with ELM

The early diagnosis of skin cancer through clinical methods reduces the human mortality rate. The manual screening of dermoscopic images is not an efficient procedure; therefore, researchers working in the domain of computer vision employed several algorithms to classify the skin lesion. The existing computerized methods have a few drawbacks, such as low accuracy and high computational time. Therefore, in this work, we proposed a novel deep learning and Entropy‐Normal Distribution Optimization Algorithm with extreme learning machine (NDOEM)‐based architecture for multiclass skin lesion classification. The proposed architecture consists of five fundamental steps. In the first step, two contrast enhancement techniques including hybridization of mathematical formulation and convolutional neural network are implemented prior to data augmentation. In the second step, two pre‐trained deep learning models, EfficientNetB0 and DarkNet19, are fine‐tuned and retrained through the transfer learning. In the third step, features are extracted from the fine‐tuned models and later the most discriminant features are selected based on novel Entropy‐NDOELM algorithm. The selected features are finally fused using a parallel correlation technique in the fourth step to generate the result feature vectors. Finally, the resultant features are again down‐sampled using the proposed algorithm and the resultant features are passed to the extreme learning machine (ELM) for the final classification. The simulations are conducted on three publicly available datasets as HAM10000, ISIC2018, and ISIC2019 to achieving an accuracy of 95.7%, 96.3%, and 94.8% respectively.

Fetal outcome following umbilical cord prolapse in Ahmadu Bello University Teaching Hospital, Kaduna (ABUTHK), northern Nigeria

BACKGROUND

Umbilical cord is a clinical condition that calls for emergency decision making and action especially with a live and mature fetus. The objective of this study is to determine, fetal outcome and how various factors influence it.

METHODS

This is a 12 1/2 year retrospective study of all 34 fetuses who suffered from cord prolapse at Ahmadu Bello University Teaching Hospital.

RESULTS

There were 34 cases of cord prolapse, 23 perinatal deaths and a perinatal mortality rate of 67.64%. About 55% of babies of registered women died, while about 92% of the unregistered died. Eleven babies of the 22 women admitted with cervical dilatations of 7 cm and less, died and all the babies of women with cervical dilatations of 8 cm and above died. All 19 babies delivered vaginally and 3 of the 14 delivered abdominally, died. About eighty eight percent of the low-birth weight, and 37.5% of normal size babies died. Seventeen (51.5%) of the 33 babies delivered, had Apgar score 0. All babies with Apgar scores 1-4 died, 40% with Apgar scores 5-7 and 16.7% with Apgar scores 8-10 died. Maternal age, parity, ethnicity, gestational age, presentation and sex of the fetus did not influence outcome.