AIDS is a severe medical condition caused by the human immunodeficiency virus (HIV) that primarily attacks the immune system, specifically CD4+ T lymphocytes: which are a type of white blood cell that plays a crucial role in the immune response by helping to coordinate the activity of other immune cells monocyte macrophages, and dendritic cells (1). The global impact of HIV/AIDS is a significant concern, affecting individuals from all backgrounds and nations. Yet, it presents an even more significant challenge in underdeveloped countries, including countries within Sub-Saharan Africa (SSA), where over two-thirds of global infections are prevalent (2). Research indicates that following an HIV-positive diagnosis, it is crucial to ensure effective linkage to care (3). Currently, there is no cure for HIV/AIDS, and the only means of treatment to extend lifespan and enhance quality of life is through anti-retroviral therapy (ART) (4). The primary symptom of AIDS is a progressive loss of immune response, leaving the body vulnerable to opportunistic infections, tumors, and abnormalities (5). The Human Immunodeficiency Virus (HIV) is a highly infectious disease that has become a serious public health concern worldwide (WHO, 2022) (6). This disease has significant health and socio-economic implications and is one of the primary causes of illness and death globally (7). HIV-positive individuals, particularly those with AIDS, can transmit the virus to others through bodily fluids such as blood, semen, vaginal fluids, and breast milk, as well as through contaminated needles and syringes (8). Despite significant efforts, there are few effective drugs available for the treatment of HIV/AIDS, making it one of the leading causes of morbidity and mortality around the world (9). This presents enormous global challenges for public health and population wellness (10). According to According to the Joint United Nations Program on HIV/AIDS (UNAIDS) data from 2022, an average of 39 million people globally are currently living with HIV/AIDS and more than 600,000 people have already died from AIDS-related illnesses. In SSA countries, non-compliance to ART is prevalent, which is why the disease burden remains high within the region (11).

Cameroon, like most SSA countries, has experienced a rise in the number of new HIV cases. According to the National Institute of Statistics in Yaoundé, Cameroon, the prevalence of HIV among the Cameroonian population is 2.9%, with a higher prevalence among women (3.1%) compared to men (2.6%) (12). In 2022, an estimated 1.4% of pregnant women in Cameroon were living with HIV, and the vertical transmission rate was 1.2% (12). These data highlight the importance of targeted interventions, particularly for pregnant women and their partners, to prevent mother-to-child transmission of HIV. This places Cameroon among the countries in SSA with the highest death toll from HIV/AIDS (13). In the South West Region of Cameroon, the prevalence of HIV is estimated at 3.2% with urban areas being the most affected (14). Healthcare workers in this region have acknowledged that the ongoing political turmoil has drastically hindered the advancement of a successful response to the HIV/AIDS crisis in the Southwest region of Cameroon. Collaborative endeavors are required to fortify the healthcare sector in crucial aspects, including decentralizing HIV healthcare, enhancing the supply chain, and safeguarding healthcare workers from political entanglements. These initiatives are imperative to alleviate the effects of the social and political turmoil on the response to HIV/AIDS and the larger healthcare domain. Tracking and analyzing the rate of HIV over time is essential for effective public health planning, resource allocation, and implementation of targeted interventions. To date, it appears that no epidemiological studies have concentrated on projecting future occurrences of HIV infection within the Kumba Health District in the Southwest Region.

This study employs time-series modeling (Auto-Regressive Integrated Moving Average: ARIMA) using Kumba District Hospital HIV/AIDS data. With one decade of reliable data, this technique proves to be a viable approach to predict the incidence of health-related problems like HIV/AIDS. The methodology used in this research follows the Umunna (2020) approach, which used the Box-Jenkins forecasting method to predict new HIV cases in Mina Niger state, Nigeria (15).

The ARIMA methodology has been utilized in various studies to model epidemic incidence. One of these studies predicted yearly cases of Human Immunodeficiency Syndrome (HIV) using this methodology in Nairobi Kenya (16), while another study focused on forecasting monthly cases of HIV in the Philippines (17). These researchers used advanced statistical techniques to build the ARIMA model, employing the univariate Box-Jenkins method to forecast HIV cases. Furthermore, a study conducted by Abuya used a seasonal autoregressive integrated moving average (SARIMA) model to analyze the time series of malaria cases in the Kenya (18). Another study by Patel used a Bayesian vector autoregression (BVAR) model to analyze the time series of HIV/AIDS cases in South Africa (19). These studies demonstrate the effectiveness of time series models in analyzing the dynamics of infectious diseases and identifying trends and patterns that can inform public health policy.

By conducting a time series analysis, this research seeks to identify any significant changes in HIV rates over the next 4 years in the Kumba District Hospital, and provide valuable insights to inform evidence-based decision-making and strategies for preventing and controlling HIV within the Kumba Health District.

Over the past 10 years (2012–2022), Kumba District Hospital has had a consistent monthly mean number of approximately 40 new cases of HIV, with a standard deviation of 20. The number of positive cases ranges from a minimum of 1 case per month to a maximum of 89 cases per month. This information indicates the prevalence of HIV in the Kumba District and highlights the need for continued efforts toward the prevention and treatment of the disease.

The findings of our study contrast markedly with those reported by Umunna, who indicated an average monthly incidence of 85 cases, ranging from a minimum of 0 to a maximum of 228 cases per month in Minna, Niger State, Nigeria. In comparison, our research revealed a lower average monthly incidence of 40 cases, with a minimum of 1 case and a maximum of 89 cases per month. This discrepancy in results might be attributed to various factors, including differences in population demographics, healthcare access, and the implementation of HIV prevention and treatment programs in the two regions. Further investigation is warranted to uncover the underlying reasons for these differences and to guide the development of targeted interventions to combat the HIV epidemic in diverse contexts (15).

The results highlight the forecasted numbers for each quarter and year, allowing for an analysis of the trends and patterns suggested by the model. Firstly, let us examine the predictions for the quarters in 2023. The ARIMA model forecasted 318 incidence cases of HIV for the second quarter (Jan–June) and 424 incidence cases for the fourth quarter (July–Dec) of that year. This indicates an increase in the predicted number of cases from the second to the fourth quarter, suggesting a potential upward trend. Moving on to (6), the model predicted 469 incidence cases of HIV for both the second and fourth quarters. This suggests a stable number of cases throughout the year, as the predictions for both quarters are the same. This could indicate a plateau or a period of stability in the incidence of HIV during that year. For 2025, the ARIMA model predicts a slight increase in the number of cases. The second quarter is forecasted to have 490 incidence cases, while the fourth quarter is predicted to have 498 incidence cases. This suggests a gradual upward trend in the incidence of HIV over the course of the year. Finally, in 2026, the model predicts a further increase in the number of cases compared to the previous year. The second quarter is forecasted to have 499 incidence cases, and the fourth quarter is predicted to have 502 incidence cases. These numbers indicate a continued upward trend in the incidence of HIV, potentially suggesting a worsening situation. It is important to note that these predictions are based on the assumptions and limitations of the ARIMA model. The accuracy of the model’s forecasts depends on the quality and representativeness of the data used for training and the assumption that the future behavior of the variable being modeled will resemble its past behavior. Additionally, external factors, such as changes in prevention strategies or healthcare interventions, could significantly affect the actual number of HIV cases and deviate from the model’s predictions. Therefore, while the ARIMA model provides valuable insights and trends based on historical data, it is crucial to interpret these predictions with caution and consider other factors that may influence the incidence of HIV in reality.

The ARIMA model (1,0,0) for the Kumba District Hospital was found to be independent of errors and a perfect fit (p = 0.410*) with an R² value of 0.664 (66.4%). This indicates that the model’s predictions aligned well with the observed data, and there were no discernible patterns or biases in the model’s residuals or errors. This model predicted an increase in number of HIV incidence cases for the next 4 years starting from January 2023 to December 2026. This finding is in discordance to that carried out by Nyoni where he predicted future decrease in HIV/AIDS incidence cases among the Zimbabwe population using ARIMA model (1,2,0) (21). Though the target population (children 0–14 years) in his study was different from that in this current study. The main difference between these two models is the order of differencing, which affects the way the data is transformed to achieve stationarity. The ARIMA (1,2,0) model includes a second-order differencing component, which is not present in the ARIMA (1,0,0) model. This difference in model parameters may be responsible for the contrasting predictions made by the two studies. It is important to note that the choice of ARIMA model parameters (e.g., the order of autoregressive, differencing, and moving average components) depends on the specific characteristics of the data and the underlying assumptions of the model. Different studies or analyses may utilize different parameter configurations based on their specific objectives and data characteristics. Discrepancies in findings can arise due to various factors, such as differences in the quality and representativeness of the data, variations in the modeling techniques employed, or the presence of external factors that influence disease dynamics. Additionally, different regions or populations may exhibit diverse HIV/AIDS trends due to variations in healthcare systems, prevention efforts, or socio-cultural factors. Furthermore, the findings are in line with Umunna earlier prediction of an increase in HIV/AIDS cases in Minna, Niger state, Nigeria (15). Our study, which utilized an ARIMA (1,0,0) model, also indicates a similar trend. In contrast, the sentences the ARIMA (1,0,1) model used by Umunna has a moving average component, which is also not present in the ARIMA (1,0,0) model. The moving average component allows the model to capture the autocorrelation in the residuals, which may be important for predicting future trends. However, in this case, the ARIMA (1,0,0) model was still able to capture the underlying patterns and dynamics of HIV/AIDS cases in Kumba, Cameroon. To provide a comprehensive analysis of the statement’s accuracy, further details and access to Umunna specific study are required. Factors such as data quality, model assumptions, model validation, and the study’s context must be considered to evaluate the results’ reliability and generalizability.

Alternatively, this result is in accordance to that gotten by Abogaye-Sarfo, who predicted in increase in HIV incidence cases among the Ghanaian population using ARIMA model (1,1,1) (22). The ARIMA (1,1,1) model used by Abogaye-Sarfo has both autoregressive and moving average components, which are present in the ARIMA (1,0,0) model. However, the ARIMA (1,1,1) model has an additional autoregressive component, which allows it to capture more complex patterns in the data. Despite these differences, the ARIMA (1,0,0) model was still able to predict an increase in HIV/AIDS incidence cases, which is consistent with the findings of Abogaye-Sarfo. This similarity in findings indicates a common trend or pattern suggested by both the ARIMA model and Abogaye-Sarfo’s study. It implies that multiple analyses or models are converging on the same prediction of an increase in HIV incidence cases. This consistency strengthens the evidence for the potential upward trend in HIV incidence within the Ghanaian population. It is important to note that the specific methodologies, data sources, and assumptions used in the ARIMA model and Abogaye-Sarfo’s study may differ. However, the fact that both arrived at similar conclusions suggests a degree of agreement in their respective analyses. Additionally, it is worth considering potential reasons for the predicted increase in HIV incidence cases. These might include factors such as changes in population demographics, shifts in sexual behavior patterns, variations in access to healthcare and prevention programs, or other social and environmental factors that could influence HIV transmission rates. Understanding these underlying factors can help inform public health interventions and strategies to address the increasing HIV incidence.

In conclusion, this study employed the ARIMA model (1,0,0) to forecast the incidence of HIV in the Kumba District Hospital over the period from 2023 to 2026. The primary outcome of the analysis indicates that the model predicts an upward trend in the number of HIV incidence cases in the coming years, suggesting a potentially worsening situation. This finding aligns with the results of other studies that have utilized similar models to forecast HIV incidence trends in different regions. The model demonstrated independence from errors and proved to be a perfect fit, signifying that its predictions corresponded closely with the observed data. While various studies may adopt different parameter configurations tailored to their specific objectives and data characteristics, it is crucial to interpret these predictions with caution. Other factors, such as alterations in prevention strategies, healthcare interventions, and sociopolitical contexts, may significantly influence the actual incidence of HIV. The response to the research question, “What is the trend of HIV incidence in the Kumba District Hospital from 2023 to 2026?,” reveals that the ARIMA model anticipates an increase in HIV incidence cases over the years. This underscores the necessity for ongoing efforts to prevent and treat HIV in the region. Looking ahead, future studies should aim to refine the ARIMA model for a more nuanced understanding of the underlying patterns and dynamics of HIV incidence in the area. Furthermore, research should investigate the impact of various prevention strategies and healthcare interventions on HIV incidence trends. By conducting such analyses, we can enhance our understanding of the contributing factors to HIV incidence trends and develop more effective prevention and treatment strategies for the disease.