Estimating severe fever with thrombocytopenia syndrome transmission using machine learning methods in South Korea

Global epidemiology of severe fever with thrombocytopenia syndrome virus in human and animals: a systematic review and meta-analysis

Background

Since the initial identification of the Severe Fever with Thrombocytopenia Syndrome (SFTS) in ticks in rural areas of China in 2009, the virus has been increasingly isolated from a diverse array of hosts globally, exhibiting a rising trend in incidence. This study aims to conduct a systematic analysis of the temporal and spatial distribution of SFTS cases, alongside an examination of the infection rates across various hosts, with the objective of addressing public concerns regarding the spread and impact of the disease.

Methods

In this systematic review and meta-analysis, an exhaustive search was conducted across multiple databases, including PubMed, Web of Science, Embase, and Medline, CNKI, WanFang, and CQVIP. The literature search was confined to publications released between January 1, 2009, and May 29, 2023. The study focused on collating data pertaining to animal infections under natural conditions and human infection cases reported. Additionally, species names were unified using the National Center for Biotechnology Information (NCBI) database. The notification rate, notification death rate, case fatality rate, and infection rates (or MIR) were assessed for each study with available data. The proportions were pooled using a generalized linear mixed-effects model (GLMM). Meta-regressions were conducted for subgroup analysis. This research has been duly registered with PROSPERO, bearing the registration number CRD42023431010.

Findings

We identified 5492 studies from database searches and assessed 238 full-text studies for eligibility, of which 234 studies were included in the meta-analysis. For human infection data, the overall pooled notification rate was 18.93 (95% CI 17.02-21.05) per ten million people, the overall pooled notification deaths rate was 3.49 (95% CI 2.97-4.10) per ten million people, and the overall pooled case fatality rate was 7.80% (95% CI 7.01%-8.69%). There was an increasing trend in notification rate and deaths rate, while the case fatality rate showed a significant decrease globally. Regarding animal infection data, among 94 species tested, 48 species were found to carry positive nucleic acid or antibodies. Out of these, 14 species were classified under Arthropoda, while 34 species fell under Chordata, comprising 27 Mammalia and 7 Aves.

Interpretation

This systematic review and meta-analysis present the latest global report on SFTS. In terms of human infections, notification rates and notification deaths rates are on the rise, while the case fatality rate has significantly decreased. More SFTSV animal hosts have been discovered than before, particularly among birds, indicating a potentially broader transmission range for SFTSV. These findings provide crucial insights for the prevention and control of SFTS on a global scale.

Funding

None.

Time series models in prediction of severe fever with thrombocytopenia syndrome cases in Shandong province, China

Severe fever with thrombocytopenia syndrome (SFTS) is an emerging infectious disease caused by the SFTS virus (SFTSV). Predicting the incidence of this disease in advance is crucial for policymakers to develop prevention and control strategies. In this study, we utilized historical incidence data of SFTS (2013-2020) in Shandong Province, China to establish three univariate prediction models based on two time-series forecasting algorithms Autoregressive Integrated Moving Average (ARIMA) and Prophet, as well as a special type of recurrent neural network Long Short-Term Memory (LSTM) algorithm. We then evaluated and compared the performance of these models. All three models demonstrated good predictive capabilities for SFTS cases, with the predicted results closely aligning with the actual cases. Among the models, the LSTM model exhibited the best fitting and prediction performance. It achieved the lowest values for mean absolute error (MAE), mean square error (MSE), and root mean square error (RMSE). The number of SFTS cases in the subsequent 5 years in this area were also generated using this model. The LSTM model, being simple and practical, provides valuable information and data for assessing the potential risk of SFTS in advance. This information is crucial for the development of early warning systems and the formulation of effective prevention and control measures for SFTS.

Applications of Artificial Intelligence in Thrombocytopenia

Thrombocytopenia is a medical condition where blood platelet count drops very low. This drop in platelet count can be attributed to many causes including medication, sepsis, viral infections, and autoimmunity. Clinically, the presence of thrombocytopenia might be very dangerous and is associated with poor outcomes of patients due to excessive bleeding if not addressed quickly enough. Hence, early detection and evaluation of thrombocytopenia is essential for rapid and appropriate intervention for these patients. Since artificial intelligence is able to combine and evaluate many linear and nonlinear variables simultaneously, it has shown great potential in its application in the early diagnosis, assessing the prognosis and predicting the distribution of patients with thrombocytopenia. In this review, we conducted a search across four databases and identified a total of 13 original articles that looked at the use of many machine learning algorithms in the diagnosis, prognosis, and distribution of various types of thrombocytopenia. We summarized the methods and findings of each article in this review. The included studies showed that artificial intelligence can potentially enhance the clinical approaches used in the diagnosis, prognosis, and treatment of thrombocytopenia.

The First Nationwide Surveillance of Severe Fever with Thrombocytopenia Syndrome in Ruminants and Wildlife in Taiwan

Since the first discovery of severe fever with thrombocytopenia syndrome virus (SFTSV) in China in 2009, SFTSV has rapidly spread through other Asian countries, including Japan, Korea, Vietnam and Pakistan, in chronological order. Taiwan reported its first discovery of SFTSV in sheep and humans in 2020. However, the prevalence of SFTSV in domestic and wildlife animals and the geographic distribution of the virus within the island remain unknown. A total of 1324 animal samples, including 803 domestic ruminants, 521 wildlife animals and 47 tick pools, were collected from March 2021 to December 2022 from 12 counties and one terrestrial island. The viral RNA was detected by a one-step real-time reverse transcription polymerase chain reaction (RT-PCR). Overall, 29.9% (240/803) of ruminants showed positive SFTSV RNA. Sheep had the highest viral RNA prevalence of 60% (30/50), followed by beef cattle at 28.4% (44/155), goats at 28.3% (47/166), and dairy cows at 27.5% (119/432). The bovine as a total of dairy cow and beef cattle was 27.8% (163/587). The viral RNA prevalence in ticks (predominantly Rhipicephalus microplus) was similar to those of ruminants at 27.7% (13/47), but wild animals exhibited a much lower prevalence at 1.3% (7/521). Geographically the distribution of positivity was quite even, being 33%, 29.1%, 27.5% and 37.5% for northern, central, southern and eastern Taiwan, respectively. Statistically, the positive rate of beef cattle in the central region (55.6%) and dairy cattle in the eastern region (40.6%) were significantly higher than the other regions; and the prevalence in Autumn (September-November) was significantly higher than in the other seasons (p < 0.001). The nationwide study herein revealed for the first time the wide distribution and high prevalence of SFTSV in both domestic animals and ticks in Taiwan. Considering the high mortality rate in humans, surveillance of other animal species, particularly those in close contact with humans, and instigation of protective measures for farmers, veterinarians, and especially older populations visiting or living near farms or rural areas should be prioritized.