Université de Notre-Dame du Kasai

Managing continuous inventory represents a major challenge for commercial enterprises, as it requires ensuring product availability while controlling the costs associated with stockouts and overstocking. Traditional approaches, such as the Wilson model (EOQ), allow the determination of the economic order quantity; however, they remain limited when dealing with dynamic demand fluctuations. This study proposes a hybrid approach that combines the principles of mathematical inventory management with supervised machine learning models, including Random Forest, Support Vector Machine, and Gradient Boosting, integrated within a stacking framework to improve demand forecasting.The experiments are conducted using a dataset extracted from an inventory management system of a large commercial enterprise available on the Kaggle platform. The dataset includes information related to products, sales transactions, orders, dates, and replenishment statuses. The performance of the models is evaluated using statistical metrics such as the coefficient of determination (R²), Mean Absolute Error (MAE), and Root Mean Squared Error (RMSE), enabling an objective assessment of forecasting accuracy. The results demonstrate that the combination of classifiers significantly improves prediction accuracy compared with individual models. The developed models are integrated into a responsive web-based business intelligence application that provides inventory managers with real-time visualization of key indicators, including products at risk of stockouts, optimal order quantities, and variations in average stock levels. This decision-support interface facilitates inventory monitoring and enables more proactive supply planning. Overall, the results indicate that the proposed approach improves the reliability of demand forecasts and supports more efficient replenishment decisions while reducing operational costs associated with stock shortages and excess inventory.

This study delves into the design and integration of event-driven architectures (EDA) within intelligent Internet of Things (IoT) systems, aiming to address the growing demands of real-time processing for the vast and heterogeneous data streams generated by connected devices. It is situated within an ongoing trajectory of innovation that seeks to enhance the responsiveness, reliability, and efficiency of next-generation IoT infrastructures. The primary objective is to identify and assess the most suitable middleware solutions (such as Kafka, MQTT, and RabbitMQ) capable of optimizing latency, ensuring data consistency, and maintaining the resilience of distributed environments. Beyond its technological dimension, the study advances a conceptual model that intertwines event-processing, edge computing, and distributed intelligence, fostering a fluid and adaptive orchestration of digital resources. This model endows IoT systems with heightened decision-making autonomy and strengthened robustness in the face of failures, congestion, and fluctuating data flows. The anticipated outcomes provide a comprehensive methodological and technical framework for the design of intelligent, scalable, and reliable IoT systems, while simultaneously deepening the theoretical understanding of event-driven paradigms in highly dynamic data environments and opening new avenues for scientific and industrial innovation.

This article delves into the significant challenges facing agriculture in the Democratic Republic of Congo (DRC) as a result of climate change. Climate-related shifts such as altered rainfall patterns, rising temperatures, and the increasing frequency of extreme weather events are having devastating effects on agricultural productivity, food security, and the sustainability of agricultural systems in the country. The primary objective of this research is to explore and assess the impact of green technologies as a solution to promote sustainable agriculture in the DRC. The study aims to identify the most effective green technologies, such as sustainable irrigation, agroforestry, and the use of biofertilizers, to enhance the resilience of agricultural systems in the face of climate change while preserving natural resources. The solution proposed by this study is the widespread adoption and integration of green technologies into agricultural practices in the DRC. These technologies have the potential to reduce the carbon footprint of agriculture, improve agricultural productivity, and strengthen the resilience of rural communities against climate-related challenges. The study advocates for immediate action to encourage the adoption of these technologies, supported by enhanced public policies, accessible financing, and capacity-building initiatives for farmers.

pelvic organ prolapse is a pathology of ligamentous connective tissues and matrix metalloproteinases are the main actors responsible for tissue remodeling by degrading connective tissue. The objective of this present study is to determine the expression rate of matrix metalloproteinases-1, -2 and -9 in prolapsed round ligaments and identify the types of matrix metalloproteinases most determining in the appearance of pelvic organs prolapse in in two pilot hospitals of Saint-Georges and of Bon-Berger of the city of Kananga in the Democratic Republic of Congo. we conducted an analytical experimental study based on immunohistochemical examination of round ligaments of 100 consenting patients divided in two groups with and without pelvic organ prolapse treated in the gynecology departments of Bon-Berger hospitals in Tshikaji and Saint-Georges in Katoka in city of Kananga, from January 1st to July 31st, 2023. Non-probability convenience sampling helped us select cases. The ANOVA test, the Chi-square test, and the logistic regression with adjustment are used in the statistical analyses. the average age of our patients with pelvic organ prolapse was 57.18 (SD: 8.17) years, and their average parity was 7.76 (SD: 1.04) delivery. This average parity was significantly increased compared to those of patients without prolapse. The expression rate of matrix metalloproteinases-1, -2, and -9 is significantly high in prolapsed round ligaments with a respective mean immunoreactive of 44.10± 22.04% (P=0.001), 39.46± 24.10% (P=0.001), and 39.34± 20.89% (P=0.001). Positive immunoreactivities to matrix metalloproteinases-1, -2, and -9 are significantly noted in patients with prolapse. There was a significant association between positive immunoreactivities to matrix metalloproteinase-1 (AOR 5.40, 95% CI: 0.981-29.794, P: 0.044) and matrix metalloproteinase-9 (AOR: 6.205, 95% CI: 1.467-26.239, P: 0.013) with the appearance of pelvic organs prolapses in the city of Kananga. the expression level of matrix metalloproteinases is increased in patients with pelvic organ prolapse and is associated with this condition, matrix metalloproteinases-1 and -9 are associated with the occurrence of pelvic organ prolapse. These results will serve as a basis for experimental research studies of inhibitory evidence of estrogens and progesterone on these matrix metalloproteinases in our city with a view to adding these hormones as a means of preventing pelvic organs prolapse in women at risk in our city of Kananga.

The establishment of a remote administration system in university institutions in the DRC is a relevant development for the scientific community. It makes it possible to solve the problems linked to the democratization and geospatial freedom of communicating entities, while offering transparent and secure access to applications and remote machines, the aim of which, moreover, is to ensure rapid and efficient to data, and improve availability. Nevertheless, in such a system, the advantages are only possible by taking into consideration the use of techniques combining the remote management of a data network and making tasks easy for users... In this article, we propose to carry out a study of the integration of remote administration in the operational and ordinary decision-making of university institutions in the DRC, this maneuver therefore allows all administrators and users of any system to intervene in real time wherever they would be in order to improve performance in terms of response time, the ease of tasks for users as well as the maintenance of the system... Hence the need to resolve any problems related in particular to the vagaries of the conventional administration

The aim of our study is to describe the epidemiological profile and indications for caesarean section at the maternity ward of the Provincial General Hospital of Kananga from January 1st 2014 to December 31st 2020. This is a descriptive study of a series of cases from the medical records of cesarean patients and based on non-probabilistic sampling of suitability for cases selection. The sample of our study is composed of 1395 cases. The frequency of caesarean section is 16.10% with an annual average of 199.30 (SD 18.20) cases per year, the average age of patients is 25.39 years (SD 1.23), the primiparity is the most affected with 27.38 %, hemorrhagic placenta previa is the most common indication in 26.86%, maternal complications is present in 46.73% and the maternal mortality rate due to cesarean section is 531 per 100.000 live births. The practice of caesarean section constitutes a real problem and our results can serve as a basis for in-depth studies on indications and maternal complications of caesarean section in order to reduce the risks associated with the practice of caesarean section in our environment.

.Little is known about the clinical features and outcomes of SARS-CoV-2 infection in Africa. We conducted a retrospective cohort study of patients hospitalized for COVID-19 between March 10, 2020 and July 31, 2020 at seven hospitals in Kinshasa, Democratic Republic of the Congo (DRC). Outcomes included clinical improvement within 30 days (primary) and in-hospital mortality (secondary). Of 766 confirmed COVID-19 cases, 500 (65.6%) were male, with a median (interquartile range [IQR]) age of 46 (34–58) years. One hundred ninety-one (25%) patients had severe/critical disease requiring admission in the intensive care unit (ICU). Six hundred twenty patients (80.9%) improved and were discharged within 30 days of admission. Overall in-hospital mortality was 13.2% (95% CI: 10.9–15.8), and almost 50% among those in the ICU. Independent risk factors for death were age < 20 years (adjusted hazard ratio [aHR] = 6.62, 95% CI: 1.85–23.64), 40–59 years (aHR = 4.45, 95% CI: 1.83–10.79), and ≥ 60 years (aHR = 13.63, 95% CI: 5.70–32.60) compared with those aged 20–39 years, with obesity (aHR = 2.30, 95% CI: 1.24–4.27), and with chronic kidney disease (aHR = 5.33, 95% CI: 1.85–15.35). In marginal structural model analysis, there was no statistically significant difference in odds of clinical improvement (adjusted odds ratio [aOR] = 1.53, 95% CI: 0.88–2.67, P = 0.132) nor risk of death (aOR = 0.65, 95% CI: 0.35–1.20) when comparing the use of chloroquine/azithromycin versus other treatments. In this DRC study, the high mortality among patients aged < 20 years and with severe/critical disease is of great concern, and requires further research for confirmation and targeted interventions.

Background: In the Democratic Republic of Congo (DRC), few studies have focused on treatment-seeking paths selected by caretakers for the management of severe childhood malaria in an urban environment. The present study aims at describing the treatment-seeking paths according to the characteristics of households, as well as the subsequent impact on pre-hospitalisation delay and malarial fatality and on the main syndromes associated with severe childhood malaria. Methods: This descriptive study included data collected at nine hospitals in Kinshasa between January and November 2011. A total of 1,350 children, under 15 years of age and hospitalised for severe malaria, were included in the study. Results: Regarding the management of malaria, 31.5% of households went directly to the health centre or hospital while 68.5% opted for self-medication, church and/or traditional healing therapy. The most frequent first-line option was self-medication, adopted by more than 61.5% of households. Nevertheless, rational self-medication using antimalarial drugs recommended by the WHO (artemisinin-based combinations) was reported for only 5.5% of children. Only 12.5% of households combined 2 or 3 traditional options. The following criteria influenced the choice of a modern vs. traditional path: household socioeconomic level, residential environment, maternal education level and religious beliefs. When caretakers opted for traditional healing therapy, the pre-hospitalisation delay was longer and the occurrence of respiratory distress, severe anaemia and mortality was higher. Conclusion: The implementation of a malaria action plan in the Democratic Republic of Congo should take into account the diversity and pluralistic character of treatment-seeking behaviours in order to promote the most appropriate options (hospital and rational self-medication) and to avoid detrimental outcomes.