猴痘疫情的全球传播态势已构成国际关注的突发公共卫生事件。流行病学资料显示，该疾病原本主要流行于非洲地区。但自2022年5月起，其传播模式出现了显著变化。北美、欧洲等以往的非流行地区，新增确诊病例数呈现出指数级增长趋势，全球累计确诊病例在短时间内迅速突破数万例。因此，加强猴痘传播规律研究，不仅能提升全球传染病监测能力，还能有效遏制病毒跨国扩散，为制定精准防控措施提供科学支撑。

通过不同地区猴痘新增病例数、发病率等数据进行传播趋势研究。从时间分布、地区分布及人群特征三个维度，系统分析猴痘全球传播情况，为建立合适的传播预测模型奠定基础。针对猴痘病例数据，构建SVR, BPNN, LSTM, ARIMA四种单一预测模型，采用网格搜索法完成模型超参数的确定。为进一步提升模型性能，引入部落竞争与成员合作（CTCM）算法对模型参数寻优，构建CTCM-SVR, CTCM-BPNN, CTCM-LSTM等优化模型。针对单一预测模型存在的数据信息捕捉不全面问题，构建猴痘权重组合预测模型。鉴于CTCM算法在参数空间的高效寻优能力，构建CTCM权重组合模型，并构建等权重组合模型、误差倒数组合模型和优势矩阵组合模型三种对比模型。最终通过对比所有模型的预测性能，实现对模型准确性的科学评估。

研究发现，猴痘传播呈现明显的时空演变特征。2022年全球疫情主要集中在美洲和欧洲地区，美国、巴西、西班牙等国家受影响最为严重；2023年亚洲地区疫情开始凸显，韩国、日本、中国等国家报告了较为集中的病例；2024年非洲地区病例数持续上升，刚果民主共和国等国家成为新的高发区域。人群特征分析显示，猴痘病例主要集中在18-49岁年龄段，且以男性患者为主。在模型评估中，单一模型中CTCM-SVR模型表现最优；而CTCM权重组合模型的预测性能更优于单一模型。这一结果表明，相较于传统的网格搜索法，CTCM算法在模型参数优化中更具优势；权重组合模型通过集成多个单一模型的预测优势，在捕捉疾病传播过程中复杂动态规律方面，较单一模型表现出显著优越性。

The global spread of the monkeypox epidemic has constituted a public health emergency of international concern. Epidemiologic information shows that the disease was originally prevalent mainly in the African region. However, since May 2022, there has been a significant change in its transmission pattern. The number of new confirmed cases in previously non-endemic regions such as North America and Europe has shown an exponential growth trend, and the global cumulative number of confirmed cases has rapidly exceeded tens of thousands in a short period of time. Therefore, strengthening the study of monkeypox transmission pattern can not only improve the global infectious disease surveillance capacity, but also effectively curb the transnational spread of the virus and provide scientific support for the development of precise prevention and control measures.

Transmission trends were studied using data on the number of new cases and incidence rates of monkeypox in different regions. The global spread of monkeypox was systematically analyzed from three dimensions, namely, time distribution, regional distribution and population characteristics, to lay the foundation for establishing an appropriate transmission prediction model. Four single prediction models, SVR, BPNN, LSTM, and ARIMA, were constructed for the monkeypox case data, and the grid search method was used to complete the determination of model hyperparameters. In order to further improve the performance of the models, Competition of tribes and cooperation of members algorithm(CTCM) were introduced to optimize the model parameters, and CTCM-SVR, CTCM-BPNN, CTCM-LSTM and other optimization models were constructed. Aiming at the problem of incomplete capture of data information in single prediction model, we constructed monkey pox weight combination prediction model. In view of the CTCM algorithm's efficient optimization ability in the parameter space, the CTCM weight combination model is constructed, and three comparison models are constructed: the equal weight combination model, the inverse error combination model and the dominance matrix combination model. Ultimately, the scientific assessment of model accuracy is realized by comparing the prediction performance of all models.

The study found that the spread of monkeypox presents obvious spatial and temporal evolution characteristics. 2022 the global epidemic was mainly concentrated in the Americas and Europe, with countries such as the United States, Brazil, and Spain being the most seriously affected; in 2023 the epidemic began to be highlighted in Asia, with countries such as South Korea, Japan, and China reporting a relatively high concentration of cases; and in 2024, the number of cases in Africa continued to rise, with countries such as the Democratic Republic of the Congo becoming the new high incidence region. Population characterization shows that monkeypox cases are mainly concentrated in the age group of 18-49 years old, and male patients are predominant. In the model evaluation, the CTCM-SVR model performed the best among the single models; while the CTCM weight combination model had a better predictive performance than the single model. This result indicates that the CTCM algorithm is more advantageous in model parameter optimization than the traditional grid search method, and that the weight combination model, by integrating the predictive advantages of multiple single models, is significantly superior to the single model in capturing the complex dynamics of the disease transmission process.

[1]Thornhill J P, Gandhi M, Orkin C. Mpox: The reemergence of an old disease and inequities[J]. Annual Review of Medicine, 2024, 75(1): 159-175.

[2]Noghabi F A, Rizk J G, Makkar D, et al. Managing monkeypox virus infections: A contemporary review[J]. Iranian Journal of Medical Sciences, 2024, 49(1): 1.

[3]Gong Q, Wang C, Chuai X, et al. Monkeypox virus: A re-emergent threat to humans[J]. Virologica Sinica, 2022, 37(4): 477-482.

[4]Ogoina D, Damon I, Nakoune E. Clinical review of human mpox[J]. Clinical Microbiology and Infection, 2023, 29(12): 1493-1501.

[5]Gurnani B, Kaur K, Chaudhary S, et al. Ophthalmic manifestations of monkeypox infection[J]. Indian Journal of Ophthalmology, 2023, 71(5): 1687-1697.

[6]Carlson C, Katz R. WHO ends public health emergency designation for mpox[J]. British Medical Journal, 2023, 381, 1190.

[7]世界卫生组织. WHO Director-General declares mpox outbreak a public health emergency of international concern[EB/OL]. (2024-08-14) [2025-01-15]. https://www.who.int/news/item/14-08-2024-who-director-general-declares-mpox-outbreak-a-public-health-emergency-of-international-concern.

[8]Kang Y, Yu Y, Xu S. Human monkeypox infection threat: A comprehensive overview[J]. PLOS Neglected Tropical Diseases, 2023, 17(4): e0011246.

[9]世界卫生组织. 2022-24 Mpox Outbreak: Global Trends[EB/OL]. (2024-11-21) [2024-11-25]. https://worldhealthorg.shinyapps.io/mpx_global/.

[10]Mathieu E, Spooner F, Dattani S, et al. Mpox[EB/OL]. (2022-05-01) [2024-11-25]. https://ourworldindata.org/mpox.

[11]Paredes M I, Ahmed N, Figgins M, et al. Underdetected dispersal and extensive local transmission drove the 2022 mpox epidemic[J]. Cell, 2024, 187(6): 1374-1386. e13.

[12]Okoli G N, Van Caeseele P, Askin N, et al. Comparative evaluation of the clinical presentation and epidemiology of the 2022 and previous Mpox outbreaks: A rapid review and meta-analysis[J]. Infectious Diseases, 2023, 55(7): 490-508.

[13]Pan D, Nazareth J, Sze S, et al. Transmission of monkeypox/mpox virus: A narrative review of environmental, viral, host, and population factors in relation to the 2022 international outbreak[J]. Journal of Medical Virology, 2023, 95(2): e28534.

[14]Patel A, Bilinska J, Tam J C H, et al. Clinical features and novel presentations of human monkeypox in a central London centre during the 2022 outbreak: Descriptive case series[J]. British Medical Journal, 2022, 378: e072410.

[15]Beiras C G, Malembi E, Escrig-Sarreta R, et al. Concurrent outbreaks of mpox in Africa—an update[J]. The Lancet, 2025, 405(10472): 86–96.

[16]Brosius I, Van Dijck C, Coppens J, et al. Presymptomatic viral shedding in high‐risk mpox contacts: A prospective cohort study[J]. Journal of Medical Virology, 2023, 95(5): e28769.

[17]喻湘, 魏卓航, 桑圣刚, 等. 猴痘流行病学及防控研究进展[J]. 中华疾病控制杂志, 2024, 28(10): 1217-1222.

[18]Guzzetta G, Marziano V, Mammone A, et al. The decline of the 2022 Italian mpox epidemic: Role of behavior changes and control strategies[J]. Nature Communications, 2024, 15(1): 2283.

[19]Titanji B K, Hazra A, Zucker J. Mpox clinical presentation, diagnostic approaches, and treatment strategies: A review[J]. The Journal of the American Medical Association, 2024, 332(19): 1652-1662.

[20]Thieme A H, Zheng Y, Machiraju G, et al. A deep-learning algorithm to classify skin lesions from mpox virus infection[J]. Nature Medicine, 2023, 29(3): 738-747.

[21]Asif S, Zhao M, Li Y, et al. AI-based approaches for the diagnosis of Mpox: Challenges and future prospects[J]. Archives of Computational Methods in Engineering, 2024, 31(6): 3585-3617.

[22]Overton C E, Abbott S, Christie R, et al. Nowcasting the 2022 mpox outbreak in England[J]. PLOS Computational Biology, 2023, 19(9): e1011463.

[23]Charniga K, Madewell Z J, Masters N B, et al. Nowcasting and forecasting the 2022 US Mpox outbreak: Support for public health decision making and lessons learned[J]. Epidemics, 2024, 47: 100755.

[24]Kaftan D, Kim H Y, Ko C, et al. Performance analysis of mathematical methods used to forecast the 2022 New York City Mpox outbreak[J]. Journal of Medical Virology, 2024, 96(8): e29791.

[25]McAndrew T, Majumder M S, Lover A A, et al. Early human judgment forecasts of human monkeypox, May 2022[J]. The Lancet Digital Health, 2022, 4(8): e569-e571.

[26]Manohar B, Das R. Artificial neural networks for the prediction of monkeypox outbreak[J]. Tropical Medicine and Infectious Disease, 2022, 7(12): 424.

[27]Long B, Tan F, Newman M. Forecasting the monkeypox outbreak using ARIMA, prophet, NeuralProphet, and LSTM models in the United States[J]. Forecasting, 2023, 5(1): 127-137.

[28]Yasmin F, Hassan M M, Zaman S, et al. A forecasting prognosis of the monkeypox outbreak based on a comprehensive statistical and regression analysis[J]. Computation, 2022, 10(10): 177.

[29]Brand S P C, Cavallaro M, Cumming F, et al. The role of vaccination and public awareness in forecasts of Mpox incidence in the United Kingdom[J]. Nature Communications, 2023, 14(1): 4100.

[30]Zhang L, Huang J, Yan W, et al. Global prediction for mpox epidemic[J]. Environmental Research, 2024, 243: 117748.

[31]Qureshi M, Khan S, Bantan R A R, et al. Modeling and forecasting monkeypox cases using stochastic models[J]. Journal of Clinical Medicine, 2022, 11(21): 6555.

[32]Eid M M, El-Kenawy E S M, Khodadadi N, et al. Meta-heuristic optimization of LSTM-based deep network for boosting the prediction of monkeypox cases[J]. Mathematics, 2022, 10(20): 3845.

[33]Iftikhar H, Khan M, Khan M S, et al. Short-term forecasting of monkeypox cases using a novel filtering and combining technique[J]. Diagnostics, 2023, 13(11): 1923.

[34]Laurenson-Schafer H, Sklenovská N, Hoxha A, et al. Description of the first global outbreak of mpox: An analysis of global surveillance data[J]. The Lancet Global Health, 2023, 11(7): e1012-e1023.

[35]Munir T, Khan M, Cheema S A, et al. Time series analysis and short-term forecasting of monkeypox outbreak trends in the 10 major affected countries[J]. BMC Infectious Diseases, 2024, 24(1): 16.

[36]Singh V, Khan S A, Yadav S K, et al. Modeling global monkeypox infection spread data: A comparative study of time series regression and machine learning models[J]. Current Microbiology, 2024, 81(1): 15.

[37]Alnaji L. Machine learning in epidemiology: Neural networks forecasting of monkeypox cases[J]. Plos One, 2024, 19(5): e0300216.

[38]Cuba W M, Huaman Alfaro J C, Iftikhar H, et al. Modeling and analysis of monkeypox outbreak using a new time series ensemble technique[J]. Axioms, 2024, 13(8): 554.

[39]Shishkin A, Bleichrodt A, Luo R, et al. Short-Term predictions of the trajectory of Mpox in east Asian countries, 2022–2023: A Comparative Study of Forecasting Approaches[J]. Mathematics, 2024, 12(23): 3669.

[40]Ndembi N, Folayan M O, Komakech A, et al. Evolving epidemiology of Mpox in Africa in 2024[J]. The New England Journal of Medicine, 2025, 392(7), 666–676.

[41]Wei W, Wang G, Tao X, et al. Time series prediction for the epidemic trends of monkeypox using the ARIMA, exponential smoothing, GM (1, 1) and LSTM deep learning methods[J]. Journal of General Virology, 2023, 104(4): 001839.

[42]欧阳泽龙, 李锦琼, 汪官曌, 等. 基于时间序列模型的全球猴痘周新增病例预测[J/OL]. 中国动物传染病学报, 1-9 [2025-03-05].

[43]Ma S, Ge J, Qin L, et al. Spatiotemporal epidemiological trends of mpox in mainland China: Spatiotemporal ecological comparison study[J]. JMIR Public Health and Surveillance, 2024, 10: e57807.

[44]商伟静, 梁万年, 刘民. 2022—2024年全球猴痘流行特征及防控进展研究[J]. 国际病毒学杂志, 2024, 31(4): 347-352.

[45]梁文娟, 张荣光, 陆家海. 2024年猴痘的流行病学特征和预防治疗研究进展[J]. 传染病信息, 2024, 37(06): 481-486.

[46]Yang L, Shami A. On hyperparameter optimization of machine learning algorithms: theory and practice[J]. Neurocomputing, 2020, 415: 295-316.

[47]Morales-Hernández A, Van Nieuwenhuyse I, Rojas Gonzalez S. A survey on multi-objective hyperparameter optimization algorithms for machine learning[J]. Artificial Intelligence Review, 2023, 56(8): 8043-8093.

[48]Valarmathi R, Sheela T. Heart disease prediction using hyper parameter optimization (HPO) tuning[J]. Biomedical Signal Processing and Control, 2021, 70: 103033.

[49]Bischl B, Binder M, Lang M, et al. Hyperparameter optimization: foundations, algorithms, best practices, and open challenges[J]. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, 2023, 13(2): e1484.

[50]Tai K Y, Dhaliwal J. Machine learning model for malaria risk prediction based on mutation location of large-scale genetic variation data[J]. Journal of Big Data, 2022, 9(1): 85.

[51]Qin J, Yang D, Zhang W. A pork price prediction model based on a combined sparrow search algorithm and classification and regression trees model[J]. Applied Sciences, 2023, 13(23): 12697.

[52]Ameri R, Hsu C C, Band S S, et al. Forecasting PM 2.5 concentration based on integrating of CEEMDAN decomposition method with SVM and LSTM[J]. Ecotoxicology and Environmental Safety, 2023, 266: 115572.

[53]Ajin R S, Segoni S, Fanti R. Optimization of SVR and CatBoost models using metaheuristic algorithms to assess landslide susceptibility[J]. Scientific Reports, 2024, 14(1): 24851.

[54]庞梦吟, 王海宁, 万通明, 等. 基于组合预测模型的疫情确诊人数预测[J]. 计算机技术与发展, 2022, 32(11): 198-203.

[55]Zhang L, Ruan J, Du Z, et al. Transmission line tower failure warning based on FBG strain monitoring and prediction model[J]. Electric Power Systems Research, 2023, 214: 108827.

[56]Guo J, Liu Y, Zou Q, et al. Study on optimization and combination strategy of multiple daily runoff prediction models coupled with physical mechanism and LSTM[J]. Journal of Hydrology, 2023, 624: 129969.

[57]赖晓蓥, 钱俊. ARIMA-LSTM-XGBoost加权组合模型在肺结核发病趋势预测的研究[J]. 现代预防医学, 2021, 48(01): 5-9.

[58]邵影, 徐梦婷, 刁羽雪, 等. 基于组合模型的河南省甲型H1N1流感流行特征分析与预测[J]. 应用数学进展, 2024, 13(11): 4772-4780.

[59]Chen L, Wu T, Wang Z, et al. A novel hybrid BPNN model based on adaptive evolutionary artificial bee colony algorithm for water quality index prediction[J]. Ecological Indicators, 2023, 146: 109882.

[60]Pang X, Zhou Y, Wang P, et al. An innovative neural network approach for stock market prediction[J]. The Journal of Supercomputing, 2020, 76: 2098-2118.

[61]Ospina R, Gondim J A M, Leiva V, et al. An overview of forecast analysis with ARIMA models during the COVID-19 pandemic: Methodology and case study in Brazil[J]. Mathematics, 2023, 11(14): 3069.

[62]Chen Z, Li S, Khan A T, et al. Competition of tribes and cooperation of members algorithm: An evolutionary computation approach for model free optimization[J]. Expert Systems with Applications, 2025, 265: 125908.

[63]Saraiva E F, Sauer L, Pereira C A B. A hierarchical Bayesian approach for modeling the evolution of the 7-day moving average of the number of deaths by COVID-19[J]. Journal of Applied Statistics, 2023, 50(10): 2194-2208.

[64]Bata M H, Carriveau R, Ting D S K, et al. COVID-19 infected cases in Canada: Short-term forecasting models[J]. Plos One, 2022, 17(9): e0270182.