5th International Conference on Medical Sciences (MEDS 2022)

December 17~ 18, 2022, Dubai, UAE

Accepted Papers

A New Gamma Mining Procedure Case Study: Breast Cancer Tumor Diagnosis

S. Abd El-Badie, IT Sector, Man Power & Immigration Directorate, Tanta, Egypt


In this paper, a new Statistical Data Mining (SDM) technique is proposed using Gamma Mining Procedure (GMP) contributing a novel classifier & predictor by applying very effective stages on the training and testing data depending on Gamma (G) correlation matrix and Gamma absorption process. Linking the previous stages with the Misclassification Error (MError) as precision measures for initiating a new classifier and a new predictor, then using the new predictor for attributes and objects mining of the test data. Applying the last GMP stage by using the contributed predictor attributes with Naive Bayes technique for prediction. The proposed GMP technique is applied and examined on a Breast Cancer Tumor diagnosis to demonstrate its applicability. Two SDM validation tools are used with the new SDM technique, the 1st versus cross validation with bootstrapping using Rapid Miner as a DM tool, and the 2nd versus two step cluster analysis, using SPSS Modeler.


Gamma, Predictor, Classifier, Nave Bayes, Rapid Miner.

Challenges at Rural hospital of Altekaina, North Sudan

Aseel Imad Taha Magzoub, University of gezira graduate, Sudan


Rural hospitals are always neglected by the government due to the low population of people it serves in Sudan and few resources. The paper discused the challenges faced at the rural hospital. Comparison between rural and urban hospital through observations and interviews with patients and staff at the rural hospital to determine the drawbacks of the local hospitals. Results revealed that there are few employees at the hospital. Most them are not employed by ministry of health and work part time at the hospital .However, the environment is much better than in urban hospitals as they have less patients so less stress. However the hospital has been neglected amd there¡Çs poor infection control and low protective measures. They also have less equipment and resources to work with. Making it impossible to help all the ill patients. People from Altekaina travel to the nearest cities for health care because the residents do not approve that the hospital provides the best services. The staff are not well qualified and need training. Attention should be given to rural hospital to improve the health and wellbeing of people living away from good health services and reduce the high mortality in rural areas . Rural and remote health should be emphasized.


rural, hospitals, health, urban hospitals, health care, workforce, patients, challenges.

Perioperative Kidney Anatomic Vascular Aspects (KAVA) for Prediction of Possible Complications Related to Nephron-sparing Surgery

Cristian Nicolae Manea2, Ottavio de Cobelli1, Deliu Victor Matei1, Cristian Mihai Dragoș3, Bogdan Feciche2, Ioan Coman2 and Nicolae Crisan2, 1 Division of Urology, European Institute of Oncology, Milan, Italy, 2 Division of Urology, Robotic Surgery Center, Clinical Municipal Hospital, “Iuliu Hatieganu” University of Medicine and Pharmacy, Cluj-Napoca, Romania, 3 Department of Statistics, Babes-Bolyai University, Cluj Napoca, Romania.


Background: In-depth knowledge of renal vascular pedicle anatomy is essential for ensuringthe feasibility of elective nephron-sparing surgery (NSS). Objectives: For a consistent approach to NSS and easier interpretation of possible perioperative complications, we propose an original score = the kidney anatomic vascular aspects (KAVA) score = based on analysis of anatomic particularities of the renal vascular system and constants of possible complications (ischaemia, haemorrhage, and anaemia). When correlated with the PADUA score, the KAVA score provides information on prognosis and severity of postoperative complications.Design, setting, and participants: We retrospectively evaluated 272 patients who underwent NSS for clinical stage 1 renal tumours, in two surgical centres between May 2018 and September 2021. Intervention: Open and robot-assisted NSS. Outcome Measurements and Statistical Analysis: The following anatomic features describe renal vascularisation: simplest vascular pedicle, supernumerary arteries and veins, early branching vessels, and precaval right renal artery. To predict the risk of complications, we generated an algorithm (KAVA score). All data were analysed with the STATA v.9.1 software, and a p-value < 0.05 was considered statistically significant.Results and limitations: Constants of complications are statistically significant for the degradation of renal function in the context of surgical trauma. Using multivariate analysis, KAVA score indicates the severity of postoperative consequences depending on risk factors, and the degree of renal function deterioration.Limitations of this study include the number of patients, the lack of preoperative evaluation of potential renal vascular potential for some patients, and the lack of calculation of the volume of the resected specimen relative to the total volume of the kidney. Further external validation of the KAVA score is needed. Conclusions: The current study is the first to assess the relationship of kidney vascular variants, tumour anatomy, and constants of possible complications in patients with elective indication for NSS. The KAVA score translates into details of the surgery and possible incidents that may occur perioperatively. It demonstrates that assessing the vascular capital of the renal unit is crucial for safe NSS, especially with a laparoscopic or robot-assisted approach.


Kidney vascular variants; Renal tumour; Anatomic classification; Complication.

Machine Learning Algorithms for Prediction of Anaemia

Sukriti Hans1 and Aarushi Punj2, 1Department of Electronics and Communication Engineering, IGDTUW, 2Department of Electronics and Communication Engineering, IGDTUW.


This project aims to help those with anaemia or anaemic symptoms in diagnosing the disease with the use of machine learning as a data analyzing and diagnosing tool. Furthermore, this project will facilitate our understanding of the disease and how advanced technologies like machine learning can aid in faster and more accurate results of medical diagnosis and scan reports. A hospital-based cross-sectional study was conducted in 2022. This project applies ML algorithms such as k-nearest neighbors (K-NN), random forest (RF) and logistic regression (LR) for prediction of anemia status in Delhi. Among the older population and the people who cannot afford quality food and healthcare anaemia can be fatal. This project has the potential to be utilized as an early-diagnosis, thus saving many lives.