1
|
Yang P, Cheng P, Zhang N, Luo D, Xu B, Zhang H. Statistical machine learning models for prediction of China's maritime emergency patients in dynamic: ARIMA model, SARIMA model, and dynamic Bayesian network model. Front Public Health 2024; 12:1401161. [PMID: 39022407 PMCID: PMC11252837 DOI: 10.3389/fpubh.2024.1401161] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/14/2024] [Accepted: 06/13/2024] [Indexed: 07/20/2024] Open
Abstract
Introduction Rescuing individuals at sea is a pressing global public health issue, garnering substantial attention from emergency medicine researchers with a focus on improving prevention and control strategies. This study aims to develop a Dynamic Bayesian Networks (DBN) model utilizing maritime emergency incident data and compare its forecasting accuracy to Auto-regressive Integrated Moving Average (ARIMA) and Seasonal Auto-regressive Integrated Moving Average (SARIMA) models. Methods In this research, we analyzed the count of cases managed by five hospitals in Hainan Province from January 2016 to December 2020 in the context of maritime emergency care. We employed diverse approaches to construct and calibrate ARIMA, SARIMA, and DBN models. These models were subsequently utilized to forecast the number of emergency responders from January 2021 to December 2021. The study indicated that the ARIMA, SARIMA, and DBN models effectively modeled and forecasted Maritime Emergency Medical Service (EMS) patient data, accounting for seasonal variations. The predictive accuracy was evaluated using Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and Coefficient of Determination (R 2) as performance metrics. Results In this study, the ARIMA, SARIMA, and DBN models reported RMSE of 5.75, 4.43, and 5.45; MAE of 4.13, 2.81, and 3.85; and R 2 values of 0.21, 0.54, and 0.44, respectively. MAE and RMSE assess the level of difference between the actual and predicted values. A smaller value indicates a more accurate model prediction. R 2 can compare the performance of models across different aspects, with a range of values from 0 to 1. A value closer to 1 signifies better model quality. As errors increase, R 2 moves further from the maximum value. The SARIMA model outperformed the others, demonstrating the lowest RMSE and MAE, alongside the highest R 2, during both modeling and forecasting. Analysis of predicted values and fitting plots reveals that, in most instances, SARIMA's predictions closely align with the actual number of rescues. Thus, SARIMA is superior in both fitting and forecasting, followed by the DBN model, with ARIMA showing the least accurate predictions. Discussion While the DBN model adeptly captures variable correlations, the SARIMA model excels in forecasting maritime emergency cases. By comparing these models, we glean valuable insights into maritime emergency trends, facilitating the development of effective prevention and control strategies.
Collapse
Affiliation(s)
- Pengyu Yang
- Department of Nursing, West China Hospital, Sichuan University, Chengdu, China
| | - Pengfei Cheng
- Department of Nursing, The Second Affiliated Hospital of Zhejiang University School of Medicine, Hangzhou, China
| | - Na Zhang
- International Nursing School, Hainan Medical University, Haikou, China
| | - Ding Luo
- International Nursing School, Hainan Medical University, Haikou, China
| | - Baichao Xu
- Department of Physical Education, Hainan Medical University, Haikou, China
- Hainan Provincial Key Laboratory of Sports and Health Promotion, Hainan Medical University, Haikou, China
| | - Hua Zhang
- International Nursing School, Hainan Medical University, Haikou, China
| |
Collapse
|
2
|
Sèbe M, Kontovas CA, Pendleton L. Reducing whale-ship collisions by better estimating damages to ships. THE SCIENCE OF THE TOTAL ENVIRONMENT 2020; 713:136643. [PMID: 31955104 DOI: 10.1016/j.scitotenv.2020.136643] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 11/18/2019] [Revised: 01/09/2020] [Accepted: 01/09/2020] [Indexed: 06/10/2023]
Abstract
Collisions between ships and whales raise environmental, safety, and economic concerns. The management of whale-ship collisions, however, lacks a holistic approach, unlike the management of other types of wildlife-vehicle collisions, which have been more standardized for several years now. In particular, safety and economic factors are routinely omitted in the assessment of proposed mitigation solutions to ship strikes, possibly leading to under-compliance and a lack of acceptance from the stakeholders. In this study, we estimate the probability of ship damage due to a whale-ship collision. While the probability of damage is low, the costs could be important, suggesting that property damages are significant enough to be taken into consideration when assessing solutions. Lessons learned from other types of wildlife-vehicle collisions suggest that the whale-ship collision should be managed as wildlife-aircraft collisions. For several years, the International Civil Aviation Organization (ICAO) manages collisions between aircrafts and wildlife at the international level. We advocate that its United Nations counterpart, namely the International Maritime Organization (IMO), get more involved in the whale-ship collision management. Further research is needed to more precisely quantify the costs incurred to ships from damages caused by whale-ship collisions.
Collapse
Affiliation(s)
- Maxime Sèbe
- Univ Brest, Ifremer, CNRS, UMR 6308, AMURE, IUEM, 29280 Plouzané, France.
| | - Christos A Kontovas
- Liverpool Logistics, Offshore and Marine Research Institute (LOOM), Liverpool John Moores University, Liverpool L3 3AF, United Kingdom.
| | - Linwood Pendleton
- World Wildlife Fund, Global Science, Washington, DC, USA; Duke University, Durham, NC, USA; Global Change Institute, University of Queensland, Brisbane, QLD, Australia; Ifremer, CNRS, UMR 6308, AMURE, IUEM, 29280 Plouzané, France.
| |
Collapse
|
3
|
Lam RPK, Wong RTM, Lau EHY, Wong KW, Cheung ACK, Chaang VK, Chen L, Tsang TC, Chan TK, Chee PPY, Ko FHF, Leung CS, Yang SM. Injury patterns of mass casualty incidents involving high-speed passenger ferries presenting to accident and emergency departments in Hong Kong: a retrospective review. Injury 2020; 51:252-259. [PMID: 31836173 DOI: 10.1016/j.injury.2019.12.001] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 11/26/2019] [Accepted: 12/01/2019] [Indexed: 02/02/2023]
Abstract
BACKGROUND Accidents involving high-speed passenger ferries have the potential to cause mass-casualty incidents (MCIs), yet there is a lack of relevant studies available to inform hospital disaster preparedness planning. OBJECTIVE The objective was to study the injury patterns and outcomes of MCI victims involved in high-speed passenger ferry accidents in Hong Kong waters. METHODS A retrospective study was conducted from 1 January 2005 to 31 December 2015. All MCIs involving high-speed passenger ferries were captured from the Marine Department of Hong Kong. Victims of all age who were sent to the accident and emergency departments (A&Es) of seven public hospitals around Victoria Harbour, including three trauma centres, were identified from electronic disaster registries of the study hospitals. Data on injury patterns and outcomes were extracted from medical records with the Injury Severity Score (ISS) calculated for each victim. The Kruskal-Wallis test was used to compare medians of the ISS across different mechanisms of injury. Multivariable logistic regression was performed to identify independent predictors for major trauma (ISS≥16). RESULTS During the study period, eight MCIs involving high-speed passenger ferries were reported and 512 victims (median age: 44 years, age range: 2-85 years) were sent to the study hospitals. The A&E triage categories were Cat 1, 3.1%; Cat 2, 4.3%; Cat 3, 19.3%; Cat 4, 72.9%; and Cat 5, 0.4%, respectively. The median ISS was 1.0 (interquartile range: 1.0-2.0). Fourteen victims (2.7%) had an ISS≥16 and age was the only independent predictor for major trauma (OR 1.06, p = 0.025, 95% CI 1.01-1.11). Trauma call was activated at A&E for 11 victims. In total, 100 victims (19.5%) were admitted to the study hospitals, including 19 (3.5%) and 15 (2.9%) who required surgery and intensive care unit stay, respectively. Eleven victims (2.1%) died, mostly due to drowning. CONCLUSION MCIs involving high-speed passenger ferries can result in a sudden surge in demand for both A&E and in-patient care, though the majority of victims may have minor injuries. Better access to lifejackets and mandatory seatbelt use may help to reduce injuries and deaths.
Collapse
Affiliation(s)
- Rex Pui Kin Lam
- Emergency Medicine Unit, Li Ka Shing Faculty of Medicine, The University of Hong Kong, Hong Kong Special Administrative Region, China; Accident and Emergency Department, Queen Mary Hospital, Hong Kong Special Administrative Region, China; Accident and Emergency Department, Pamela Youde Nethersole Eastern Hospital, Hong Kong Special Administrative Region, China.
| | - Ronald Tat Ming Wong
- Emergency Medicine Unit, Li Ka Shing Faculty of Medicine, The University of Hong Kong, Hong Kong Special Administrative Region, China
| | - Eric Ho Yin Lau
- School of Public Health, Li Ka Shing Faculty of Medicine, The University of Hong Kong, Hong Kong Special Administrative Region, China
| | - Kin Wa Wong
- Emergency Medicine Unit, Li Ka Shing Faculty of Medicine, The University of Hong Kong, Hong Kong Special Administrative Region, China; Accident and Emergency Department, Pamela Youde Nethersole Eastern Hospital, Hong Kong Special Administrative Region, China
| | - Arthur Chi Kin Cheung
- Emergency Medicine Unit, Li Ka Shing Faculty of Medicine, The University of Hong Kong, Hong Kong Special Administrative Region, China
| | - Vi Ka Chaang
- Emergency Medicine Unit, Li Ka Shing Faculty of Medicine, The University of Hong Kong, Hong Kong Special Administrative Region, China
| | - Lujie Chen
- Emergency Medicine Unit, Li Ka Shing Faculty of Medicine, The University of Hong Kong, Hong Kong Special Administrative Region, China
| | - Tat Chi Tsang
- Accident and Emergency Department, Queen Mary Hospital, Hong Kong Special Administrative Region, China
| | - Tak Kuen Chan
- Accident and Emergency Department, Ruttonjee Hospital, Hong Kong Special Administrative Region, China
| | - Peter Pay Yun Chee
- Accident and Emergency Department, St John Hospital, Hong Kong Special Administrative Region, China
| | - Frank Hiu Fai Ko
- Accident and Emergency Department, Queen Elizabeth Hospital, Hong Kong Special Administrative Region, China
| | - Chin San Leung
- Accident and Emergency Department, Princess Margaret Hospital, Hong Kong Special Administrative Region, China
| | - Siu Ming Yang
- Accident and Emergency Department, Kwong Wah Hospital, Hong Kong Special Administrative Region, China
| |
Collapse
|
4
|
Ryan K, George D, Liu J, Mitchell P, Nelson K, Kue R. The Use of Field Triage in Disaster and Mass Casualty Incidents: A Survey of Current Practices by EMS Personnel. PREHOSP EMERG CARE 2018; 22:520-526. [DOI: 10.1080/10903127.2017.1419323] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/18/2022]
|
5
|
Yang C, Gao J, Du J, Wang H, Jiang J, Wang Z. Understanding the Outcome in the Chinese Changjiang Disaster in 2015: A Retrospective Study. J Emerg Med 2016; 52:197-204. [PMID: 27727034 DOI: 10.1016/j.jemermed.2016.08.013] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/11/2016] [Accepted: 08/18/2016] [Indexed: 12/01/2022]
Abstract
BACKGROUND Rescue after a maritime disaster remains a great challenge in emergency medicine. OBJECTIVE We performed an overview of rescue efforts among the victims in the sunken cruise ship Eastern Star in the 2015 Changjiang River marine disaster, as well as possible preventive measures in maritime transport situations. METHODS The rescue records of 454 victims of the sunken ship were analyzed retrospectively. Their demographic data, rescue effects, accident inducement, and injury disposition were reviewed. A thorough analysis from the point of view of maritime traffic safety was also performed. RESULTS Of the 454 victims, 442 (97.36%) were killed and only 12 (2.64%) survived. The survivors were classified based on their gender, rescue type, and rescue spot as follows: male (91.67%), female (8.33%); tourists (50.00%), and ship staff (50.00%), after the breakdown of the rescue spot in Jianli, Hubei province, China. The survivors were saved only during the initial 17 h after the disaster. The survivors suffering from somato- and psychotrauma were urgently treated for limb injuries, infections of the upper respiratory tract and lungs, fluid and electrolyte imbalance, and acute traumatic stress. This incident was the most severe maritime disaster since the establishment of the People's Republic of China on October 1, 1949, due to the large number of elderly victims, fast overturning speed, and severe weather. CONCLUSIONS Emergency rescue requires more automated and intelligent systems for maritime safety. An increased focus must be placed on public welfare and ethics, with the goal of influencing more prosocial behavior rather than the pursuit of profit.
Collapse
Affiliation(s)
- Ce Yang
- State Key Laboratory of Trauma, Burns and Combined Injury, Fourth Department of Research, Institute of Surgery, Daping Hospital, the Third Military Medical University, Chongqing, P.R. China
| | - Jie Gao
- State Key Laboratory of Trauma, Burns and Combined Injury, Fourth Department of Research, Institute of Surgery, Daping Hospital, the Third Military Medical University, Chongqing, P.R. China
| | - Juan Du
- State Key Laboratory of Trauma, Burns and Combined Injury, Fourth Department of Research, Institute of Surgery, Daping Hospital, the Third Military Medical University, Chongqing, P.R. China
| | - Haiyan Wang
- State Key Laboratory of Trauma, Burns and Combined Injury, Fourth Department of Research, Institute of Surgery, Daping Hospital, the Third Military Medical University, Chongqing, P.R. China
| | - Jianxin Jiang
- State Key Laboratory of Trauma, Burns and Combined Injury, Fourth Department of Research, Institute of Surgery, Daping Hospital, the Third Military Medical University, Chongqing, P.R. China
| | - Zhengguo Wang
- State Key Laboratory of Trauma, Burns and Combined Injury, Fourth Department of Research, Institute of Surgery, Daping Hospital, the Third Military Medical University, Chongqing, P.R. China; International Traffic Medicine Association, Bloomfield Hills, Michigan
| |
Collapse
|
6
|
|