Smart healthcare in mobile hospitals: enhancing response to Disease X

Abstract

Background

Scientific and technological advancements have significantly augmented our capacity to comprehend and manage “Disease X,” while improving the efficiency and accuracy of outbreak management. Infectious disease prevention and control technology is advancing toward unmanned and intelligent methods, shifting from a traditional reactive response to public health emergencies to a more proactive and efficient outbreak management mechanism. This study aims to investigate the intelligent transformation of mobile hospitals, with the objective of bolstering their emergency response capabilities and fortifying their prevention and control strategies for unknown infectious diseases. This, in turn, seeks to mitigate the spread of epidemics and protect public health.

Methods

Semi-structured interviews with 10 experts were conducted. A framework analysis was used to organize the interview results and distill the experts’ overall views on the smart building of mobile hospitals.

Results

The smart transformation of mobile hospitals plays a crucial role in responding to public health emergencies. The overall status of mobile hospitals is analyzed through five key dimensions: role and significance, characteristics, challenges, necessity and feasibility, and influencing factors.

Conclusion

When confronting public health emergencies, mobile hospitals offer significant advantages over traditional medical institutions. In addressing “Disease X,” the intelligent transformation of these mobile hospitals is in accordance with contemporary trends, facilitating swift epidemic responses, precise patient management, efficient resource allocation, and improved adaptability to diverse environments and service demands. It is crucial for building a sustainable biosafety system.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12879-025-10925-3.

Background

The advancement of science and technology has significantly improved our capacity to comprehend and mitigate biological threats. The implementation of X disease prediction, prevention, and control strategies, incorporating web-based monitoring tools and epidemiological intelligence methods for risk assessment and early outbreak detection, has considerably advanced. Traditional hospitals generally feature permanent infrastructure and a relatively sufficient bed capacity [1]. However, during the COVID-19 pandemic, the intensive care unit (ICU) bed capacity in these hospitals proved critically inadequate, preventing many patients from receiving timely and effective treatment [2]. Furthermore, deficiencies in design and management may render isolation measures in traditional hospitals insufficient, complicating epidemic control efforts. Consequently, traditional hospitals may face challenges such as inefficient resource allocation and operational inefficiencies during sudden public health crises.

In contrast, mobile hospitals present a more adaptable solution, capable of rapid deployment to critical areas, particularly in scenarios of bed shortages. A study analyzing Wuhan’s cabin hospitals during the pandemic revealed that within 33 days, a facility with 35,499 beds was constructed and activated, admitting approximately 12,000 mild cases. This significantly transformed the relationship between new cases and bed availability into a highly negative correlation (r=-0.833) while markedly improving recovery rates (r = 0.961) [3]. Such a “peacetime-warfare” mechanism, including military field hospitals and cabin models, can complete site selection and deployment within days. For instance, Florida employed the E2SFCA mathematical model to optimize mobile hospital locations, ensuring vulnerable populations could access ICU resources within a 15-minute drive [2].

Innovations such as artificial intelligence (AI), biomanufacturing, microfluidics, and BioMEMS have demonstrated substantial potential in improving the efficiency and accuracy of epidemic management [4]. Technologies and related industries for infectious disease control are evolving toward an “unmanned, intelligent” model, shifting from a passive response to sudden public health emergencies to a proactive, immediate, and highly efficient epidemic defense mechanism. Unmanned and intelligent mobile hospitals, as products of technological integration, present innovative strategies for infectious disease control in the face of unknown epidemics. Multi-scenario emergency epidemic control robot systems have been developed to handle tasks such as ward disinfection, material delivery, and remote diagnosis and treatment [5]. Programmatically controlled robotic beds mitigate healthcare workers’ exposure risks through remote interaction, with their mechanical design and motion control systems validated via simulation, making them suitable for ICU scenarios. During the COVID-19 pandemic, such equipment demonstrated significant efficacy, transitioning medical operations from physical contact to digital management and reducing cross-infection rates by up to 67% [6].

However, research on nursing innovations highlights that mobile hospital nurses’ limited proficiency with emerging technologies (e.g., remote monitoring devices) undermines system effectiveness [7]. During the COVID-19 pandemic, some mobile hospitals in Nigeria had idle equipment due to insufficient training [8]. Additionally, discrepancies in communication protocols among different manufacturers of mobile hospital equipment (such as SIP/SDP mixed with proprietary protocols) hinder seamless system integration [9]. The adoption of China’s digital twin technology in mobile hospitals faces challenges due to incomplete standardization [10]. These issues underscore the need for multidimensional improvements to enhance mobile hospital capabilities, enabling their transition from “mobile emergency units” to “omni-scenario intelligent medical platforms.”

This study explores the design and implementation of intelligent diagnostic and treatment systems within these mobile hospitals, aiming primarily to improve the efficiency of emergency responses and the effectiveness of medical aid, ensuring swift and effective medical interventions to curb the spread of epidemics and safeguard public health.

Methods

Semi-structured interviews were conducted to uncover the practices, mechanisms, and relationships that the study aimed to explain, with a sample selected for its potential to provide theoretically generalizable insights [11]. The interviewees were selected based on their professional backgrounds, experiences, and cultural and social contexts. This selection process ensured that the interviews effectively supported the research objectives and provided valuable theoretical insights. While qualitative research often focuses on a small number of cases due to its intrinsic depth and nuance, it is sometimes necessary to account for the diversity and representativeness of the sample to ensure the broader applicability of the findings [12]. Careful attention was given to sample sourcing to avoid bias, ensuring that all participants were informed of the conditions of their participation and provided their consent. Additionally, measures were implemented to protect participants’ privacy and data security [13].

Various research methodologies have established sample size ranges (e.g., grounded theory studies typically include 5–35 participants, while case studies suggest 4–30) [14]. Structured interviews, owing to their predefined and standardized questions, necessitate a balance between depth and breadth of information. When the research objective is to identify shared characteristics within a defined group (e.g., standardized behavioral patterns in a professional domain), a sample of 10 participants can efficiently capture core patterns through structured questioning [15]. A study on medical behavior found that structured interviews with 12 participants achieved 80% data saturation [16]. The selection of a 10-participant sample in this study corresponds to the lower bound of the empirical range for grounded theory and case studies (5–35 participants) while offering a practical scope for achieving data saturation.

Data collection

The data were collected through semi-structured interviews, each of which began with a guiding question: “What does a mobile infectious disease hospital look like in your mind? What are its characteristics?” [17]. Prior to the interviews, the research team scheduled appointments with each participant, informing them about the interview’s purpose, relevant details, and confidentiality protocols. With participants’ consent, the interviews were recorded through a combination of on-the-spot note-taking and audio recording. After each interview, a unique identifier was assigned to each participant to maintain anonymity. Within 48 h, two members of the research team transcribed the audio recordings and field notes. Subsequently, these two members cross-checked the transcriptions and entered the data into a database [18].

Data analysis

This study employs the Framework Analysis method to systematically organize and analyze interview data. Framework Analysis is a structured research approach that deconstructs complex issues into multiple dimensions by constructing systematic models to logically analyze phenomena, policies, or technologies, identify key variables, and assess feasibility. Its core principle is the integration of cross-domain information using a predefined or dynamically adjusted analytical framework [19, 20].

The five key steps of Framework Analysis include familiarization with the data, constructing an initial thematic framework, indexing, charting, and developing a comprehensive analytical map and interpretation. The detailed implementation steps are outlined as follows [21, 22]:

(1) Familiarization: At this stage, researchers begin to comprehensively understand the transcribed dataset. They must repeatedly review recordings, organize field notes, and systematically document observations. Simultaneously, researchers must annotate collected materials, including sources, types, and key information, for systematic classification and analysis.

(2) Constructing an Initial Thematic Framework: As researchers categorize materials based on annotated content, the framework begins to take shape. Classification criteria may include thematic relevance, chronological order, and location.

(3) Indexing: This step parallels the coding process in other qualitative research methodologies. It involves screening materials, identifying relevant citations, and conducting comparisons within or across cases. (4) Charting: This step primarily entails extracting data from raw materials and integrating them into the newly developed thematic framework. Indexing and charting serve as essential components of data management. A critical aspect of this process is data condensation, achieved through comparison, reduction, and reorganization. Researchers can utilize tables or charts to systematically organize and analyze data. When constructing charts, data organization can follow two approaches: one guided by extracted themes and the other by distinct cases, as illustrated in Tables 1 and 2.

Table 1.

Case oriented table

	Theme 1	Theme 2	Theme 3 etc.
Case 1
Case 2
Case 3 etc.

Table 2.

Topic oriented table

	Case 1	Case 2	Case 3 etc.
Theme1
Theme 2
Theme 3 etc.

(5) Developing a Comprehensive Analytical Map and Interpretation: This stage focuses on analyzing each core point presented in the charts. It involves examining the data in conjunction with the research theme to discover patterns and trends. Finally, the analysis results are synthesized to develop a comprehensive understanding of the research topic.

(6) Forming a Comprehensive Analysis Map and Interpretation: This stage focuses on analyzing each core point presented in the charts. It involves analyzing data displayed in tables or charts, delving deeply into the materials in conjunction with the research theme, discovering patterns and trends. Finally, summarize the analysis results to form a comprehensive understanding of the research topic.

Ethics approval and consent to participate

This study was conducted in accordance with the ethical principles of the Declaration of Helsinki. Ethical approval was obtained from the Institutional Review Board of the 958th Hospital of the Army Medical University Ethics Committee (ID: IRB20241k-10), and written informed consent was provided by all participants.

Results

A convenience and purposeful sampling method was used to recruit key informants via email. The emails included the purpose of the study and the individuals who recommended them as potential participants. A total of 10 key informants were interviewed. Table 3 summarizes the characteristics of the participants.

Table 3.

Interview participants (N = 10)

Characteristics	No.(%)	Characteristics	No.(%)
Gender		Engaged in the profession
Male	8(80)	Nosocomial infections	1(10)
Female	2(20)	Hospital management	1(10)
Age		Hospital Information	3(30)
30 ~ 40 years old	3(30)	Health Research	3(30)
41 ~ 50 years old	6(60)	Nursing management	1(10)
51 ~ 60 years old	1(10)	Contagious disease	1(10)
Over 60 years old	0(0)	Years of experience in the profession
Title		Less than 10 years	3(30)
Senior	3(30)	10 ~ 20 years	2(20)
Associate Senior	4(40)	20 ~ 30 years	3(30)
Intermediate	4(40)	More than 30 years	2(20)
Junior	0(0)

Five themes were identified: (1) role and significance, (2) characteristics, (3) challenges, (4) necessity and feasibility, and (5) influencing factors. The details are presented in Table 4

Table 4.

Overall construction of mobile hospitals

Topic	Typical original quote
Role and significance	For major public health emergencies, fixed hospitals……. In contrast, the advantages of mobile hospitals…… are not only able to effectively control the spread of disease but also provide more timely and effective medical interventions at the source,…… enhancing the effectiveness of epidemic prevention and control. (Expert #2)
Characteristics	…… major public health emergencies, fixed hospitals…… and the transit process……. Mobile hospitals can be deployed at the scene of an outbreak,……, and can also reduce the risk of patient transit. (Expert #2) …… can be deployed quickly and can quickly admit and control infectious disease patients. (Expert #7) …… basic a rescue and treatment function; second, as mobility, in the infectious disease outbreak when the need to go deep into the most serious areas of the epidemic.…… The sparrow is small, but it has all the organs. (Expert #8) …… modularity into a system,……, with the reality of infectious disease diagnosis and treatment has to have a combination, to have a shared mechanism, as well as regular training. The…… system is complete,…… quickly assembled. (Expert #9) …… Infectious diseases in complex environments in the field can be quickly laid out, reached and unfolded.…… (Expert #10)
Challenges	…… The most important thing is infection control, and how to effectively protect healthcare workers from infection is the primary issue. (Expert #1) …… The main problem may be that there is inevitably a contact between a doctor and a patient,…… and…… there is a risk of crossover. (Expert #2) There may be some bottlenecks and mitigation issues when demand exceeds supply.…… is the issue of human resources. (ii) The anticipation of supplies, now we have early warning can be prepared,…… epidemic outbreaks,……. (iii) Material consumption preparation,…… about the consumption of logistic support substances and so on. (Expert #8) …… poor mobility,…… low level of informatization,…… incompatibility between systems. (Expert #5) …… Intelligent informatization capability is low,…… compatibility is poor, and…… modules are relatively independent. (Expert #6) Modularity, whether consistency can be achieved between mobile and uncertain environments,……. Equipment is bulky and has high voltage requirements, yet the more concise the mobile requirements the better,……. Intelligent equipment running operation with terrain environment is more demanding. (Expert #10)
Necessity and feasibility	Intelligence is the future.…… feasibility. (Expert #5) …… can reduce exposure and the risk of infection;…… is now greatly supported by technologies such as the Internet of Things, drones, and unmanned vehicles. (Expert #7) ……. Intellectualization is also created artificially, and it is important to combine people and intellectualization on both legs. Keeping close to clinical needs, solving clinical problems, and doing a good job of related a warning.……. Of course, in some aspects, intellectualization will provide us with a lot of convenience, such as in the statistical analysis of data. (Expert #8) The daily work is closely related to informatization,……, it can reflect the important role of informatization. (Expert #9)
Influencing factors	The familiarity of medical staff and patients with the consultation process of this hospital,……. To make the whole process of consultation and treatment services more fluent, improve the proficiency of medical staff and their mastery of the system.……. (Expert #1) First, information technology must be a little bit more integrated.……. Now intelligent hospital construction builds an integration platform at the bottom,…… This integration platform will define these data into a standardized thing.……. (Expert #2) Infrastructure development and supporting conditions will affect the services provided by mobile hospitals, which are highly informatized and require high levels of operators. (Expert #4) …… temporary rollout in a geographical area, supporting facilities and equipment are generally lacking; there are also many draw groups of personnel who are unfamiliar. (Expert #7) …… must focus on the ability of the personnel, the higher the fit between the personnel and the clinical and intellectualized tools, the higher the efficiency, and the smoother the flow of the personnel’s work; ② Funding: how much funding is invested in the construction is also an issue to be considered,……; ③ Environment: according to different environments according to local conditions,……. (Expert #8) …… integrated consideration,…… standardized design, funding……,…… mechanism for continuous improvement,………… summarize and feedback. (Expert #9) First, the mobile hospital…… is clearly positioned…… to solve the problem without evacuation conditions, and to provide the most services in a limited environment. (Expert #10)

Role and significance

The participants unanimously recognized the importance of mobile hospitals due to their rapid response capability, comprehensive treatment services, flexible transportation mechanisms, and effective outbreak control.

Characteristics

The salient features of the Mobile hospital, as identified by the participants, are as follows: (1) Rapid mobility and deployment: Guarantees the ability to set up and commence operations immediately. (2) Modularity and functional integrity: Comprehensive medical equipment and independent air purification systems enable the rapid establishment of multifunctional medical units. (3) Optimized resource allocation: Direct access to the outbreak area mitigates the risk of patient transfer, alleviates local resource shortages, and facilitates resource-sharing strategies. (4) Intelligent and integrated design: This architectural approach enhances information processing capabilities and optimizes the data management process.

Challenges

Challenges in the development of mobile hospitals include the following: (1) Infection control and personnel protection: Intelligent strategies are urgently needed to reduce the risk of cross-infection. (2) Flexibility in site and resource allocation: Balancing flexibility with specific constraints is essential. (3) Inadequate informationization and intelligence: Compatibility problems among existing systems need to be addressed. (4) Manpower and material supply chain tension: There is continuous pressure on manpower and material capacity.

Necessity and feasibility

The experts unanimously emphasized the critical role of intelligence in enhancing the effectiveness and safety of mobile hospitals. While advanced technologies, such as the Internet of Things (IoT), present substantial potential in this domain, it is imperative to carefully balance portability, system compatibility, and efficient resource utilization throughout implementation.

Influencing factors

The critical factors influencing the smart transformation of mobile hospitals include: (1) Personnel competence and teamwork: Specialized skills, continuous training, and efficient collaboration are vital for successful outcomes. (2) Policy orientation: Relevant policies must be promptly updated, with clearly defined roles. (3) Technology compatibility and training quality: Ensuring equipment compatibility, system integration, and high-standard training mechanisms is essential. (4) Investment scale and implementation considerations: Investment scale, environmental adaptability, and practical complexity represent significant barriers to the implementation of smart technologies.

Discussion

The current intelligent solutions for mobile hospitals embody the forefront of deep integration between modern medical and information technologies, designed to improve the flexibility, accessibility, and responsiveness of healthcare services. These solutions extend beyond conventional ambulances and temporary medical stations, offering a comprehensive spectrum of healthcare services, from remote diagnostics to on-site emergency interventions. Fundamentally, these solutions harness advanced technologies to enhance medical resource efficiency and healthcare quality.

Limitations of traditional public health emergency systems

The existing public health emergency system encounters numerous challenges in addressing sudden infectious disease outbreaks, primarily manifesting in the following areas: Traditional processes dependent on manual monitoring and paper-based records, including case reporting and epidemiological investigations, are prone to significant delays, failing to satisfy the urgent demands of outbreak control.

In December 2019, China reported the first cases of pneumonia of unknown origin in Wuhan. Europe confirmed its first COVID-19 case on January 7, 2020, followed by the World Health Organization’s declaration of a global public health emergency on January 30, 2020 [23]. Australia imposed a nationwide lockdown on March 26 and intensified epidemic prevention measures on April 15 [24].

In resource-limited regions, including remote and conflict-affected areas, persistent challenges such as insufficient medical equipment and workforce shortages undermine the capacity for infectious disease containment [25]. In conventional hospital designs, physical isolation measures, such as zoning management, frequently fail due to inflexible spatial layouts or inadequate enforcement of operational protocols, thereby heightening the risk of nosocomial infections [26].

Clinical decision-making is predominantly experience-based, and the absence of real-time data integration and analytical tools constrains diagnostic accuracy, particularly in the emergence of novel pathogens. During outbreaks of emerging pathogens, real-time data integration tools play a crucial role in enhancing epidemic surveillance efficiency. Machine learning-based contact tracing algorithms facilitate the rapid identification of high-risk populations. However, in the absence of such tools, clinicians face difficulties in accessing dynamic transmission data promptly, resulting in diagnostic delays [27].

Innovative breakthroughs in intelligent diagnosis and treatment solutions for mobile hospitals

Intelligent process optimization and infection control

Traditional medical institutions primarily depend on manual operations (e.g., handwritten patient records), which are susceptible to human error, potentially resulting in cross-infections. Delays and inaccuracies inherent in paper-based records can impede real-time contact tracing, thereby elevating infection risks [28]. The adoption of electronic data collection systems (e.g., the INTCare system) enhances data timeliness and accuracy while minimizing human intervention [29]. Mobile healthcare systems leveraging big data analytics (BDA) and cloud computing (CC) integrate IoT devices (e.g., dual-channel automatic acoustic sensors such as ASP) to autonomously capture vital signs data. For example, infrared ultra-wideband (IR-UWB) radar technology captures 16-bit resolution data at a frequency of 64 Hz/s and transmits it in real time to the cloud via Bluetooth, thereby reducing direct contact between healthcare workers and patients [30]. These technologies have demonstrated reliability in intensive care settings, where automated hourly calculations of vital signs data can substitute for manual recording, thereby optimizing medical resource allocation [31].

The integration of thermal imaging tracking and facial recognition technologies enables real-time monitoring of patient movement trajectories, automatically identifying potential infection pathways [32]. Modular designs facilitate the reconfiguration of outpatient and inpatient workflows, ensuring physical separation and functional autonomy of clean, semi-contaminated, and contaminated zones (the ‘three zones’). In Hong Kong’s cabin hospitals, standardized modules (e.g., isolation cabins, medical units) were rapidly assembled to establish the physical separation of the three zones. Research indicates that these designs can facilitate the deployment of 1,000-bed facilities within 72 h, ensuring complete zone isolation through airtight partitions and intelligent ventilation systems [33, 34].

Intelligent diagnostic assistance systems and resource optimization

Traditional decision-making primarily depends on individual physicians’ expertise, and the absence of data-driven resource allocation results in suboptimal diagnostic efficiency and resource misallocation [29]. An artificial intelligence (AI)-driven clinical decision support system is developed to integrate multi-source data (e.g., medical imaging, laboratory diagnostics, and epidemiological analyses). Utilizing machine learning models, the system forecasts disease progression and suggests personalized treatment regimens [25]. The deployment of 5G networks facilitates real-time data exchange and enhances the allocation of cross-regional medical resources (e.g., negative-pressure isolation units, personal protective equipment) [35]. The traffic operation index assessment framework validates the feasibility of cross-regional data collaboration by integrating and standardizing multi-source datasets (e.g., GPS signals, surveillance footage, and mobile network data) [33].

Voice-controlled interfaces and AI-driven triage systems are implemented to streamline patient workflows and improve system accessibility in resource-constrained settings (e.g., rural healthcare facilities) [36]. Non-contact voice-controlled systems are especially crucial in resource-limited settings, exemplified by the INTCare system, which automates patient interactions through electronic health record (EHR) processing and clinical workflow optimization [29].

Modular design and rapid deployment capability

Traditional medical facility construction involves prolonged development cycles, hindering the ability to address urgent public health emergencies [37]. Implementing a three-zone modular design in mobile hospitals facilitates rapid deployment. By assembling standardized modular units (e.g., isolation wards and medical stations), a temporary hospital with a 1,000-bed capacity can be established within 72 h, as demonstrated by Hong Kong’s cabin hospitals [37]. During the COVID-19 pandemic, Wuhan’s cabin hospitals in China provided 4,000 beds within 29 h by repurposing public infrastructure, such as sports complexes, showcasing the efficiency of modular design [34].

Mathematical models further indicate that resource allocation strategies in modular hospitals, such as optimizing bed turnover rates, contribute to effective epidemic containment [28]. Airtight partitions and advanced ventilation systems are implemented to maintain strict separation between contaminated and sterile zones, minimizing infection risk [37].

The siting of mobile hospitals must adhere to specific criteria, including maintaining a green buffer zone (≥ 20 m), proximity to tertiary care centers, ample space availability, and accessibility to transportation networks [38]. Wuhan’s cabin hospitals utilized large venues, such as exhibition centers, to optimize patient transfer efficiency while managing logistical challenges in material distribution [34]. Modular design enables dynamic reconfiguration of functional units in response to epidemic severity, preventing resource misallocation [26].

Challenges faced by innovative technologies in mobile hospitals

The application of AI in infectious disease prevention and control is widespread and multifaceted, encompassing various domains, including disease surveillance, diagnosis, treatment, and policy development. However, its potential ethical and privacy implications warrant careful consideration. Patients may rely on AI due to trust in the technology and dependence on AI-driven decisions, such as diagnostic assistance and treatment recommendations, which may offer reassurance but also contribute to psychological dependency. Excessive dependence on AI could undermine patients’ trust in human physicians, thereby impacting the doctor-patient relationship. Such dependence may also result in an unquestioning acceptance of AI-generated decisions, disregarding its inherent limitations and associated risks [39].

ChatGPT may exhibit limitations in evaluating patients’ mental health conditions and may not provide timely human intervention during crises [40]. In the future, a “human-AI collaboration” should be realized through technological transparency, hybrid intervention models, and ethical safeguards, ensuring efficiency gains while maintaining the humanistic values of healthcare. Future research should prioritize cross-cultural adaptability, long-term psychological impact assessments, and accountability mechanisms to establish a sustainable AI-driven prevention and control system.

The current state of technological dependency for mobile hospitals in extreme environments (e.g., power outages or network disruptions) primarily concerns the reliability of power supply and network connectivity. Power supply interruptions may result from various factors, including damage to non-reserve components, failure of safety and automation equipment, incorrect operator decisions, scheduled maintenance, and inadequate system capacity. Such interruptions may lead to isolated power failures within the system, which are generally categorized as planned and unplanned types [41]. Therefore, hospitals must implement measures to ensure the stability and reliability of network connectivity, such as utilizing backup network equipment or satellite communication technology to mitigate network disruptions.

In clinical settings, artificial intelligence-based Clinical Decision Support Systems (CDSS) could influence the roles and skillsets of doctors, and existing accountability mechanisms may not adequately address these changes. When AI begins evaluating specific cases, doctors may fear losing their professional expertise and question the fairness of AI assessments. Furthermore, concerns arise regarding who is utilizing AI, how AI evaluates doctors’ practices, and whether AI can detect issues that doctors may overlook. These concerns suggest that current accountability mechanisms may not adequately address the challenges posed by AI-driven diagnostics, particularly in mobile healthcare settings [42].

Simultaneously, in mobile hospitals, the risk of data breaches from IoT devices primarily arises from security vulnerabilities and threats, including malicious code injection, impersonation attacks, denial-of-service (DoS/DDoS) attacks, replay attacks, and data integrity violations [43–45].

The use of mobile health (mHealth) platforms among homeless populations has yielded positive outcomes. Homeless individuals have exhibited a positive attitude toward mobile technologies and SMS services, which can enhance their connection with the healthcare system and providers, as well as improve health education, preventive care, and chronic disease management. However, these strategies have yet to be widely evaluated or implemented for homeless populations, and the healthcare system presents several barriers. Discrimination and bias against homeless individuals frequently deter them from seeking medical care [46]. The implementation of telemedicine and mHealth applications is hindered by technical limitations, such as device compatibility, network connectivity stability, and patients’ acceptance of technology. These issues impact patients’ user experience and adherence to the systems [45, 47].

At the same time, in mobile hospitals, the risk of data breaches from IoT devices primarily stems from security vulnerabilities and threats, including malicious code injection, impersonation attacks, denial-of-service attacks (DoS/DDoS), replay attacks, and data integrity compromises [43–45].

The application of mobile health (mHealth) platforms among homeless populations has shown positive outcomes. Homeless individuals have demonstrated a favorable attitude toward mobile technologies and SMS services, which can effectively improve their connection with the healthcare system and providers, as well as enhance health education, preventive care, and chronic disease management. However, these strategies have not yet been widely evaluated or implemented for homeless populations, and the healthcare system presents multiple barriers. Discrimination and bias against homeless individuals often deter them from seeking medical care [46]. The implementation of telemedicine and mHealth applications is constrained by technical limitations, such as device compatibility, network connectivity stability, and patients’ acceptance of technology. These issues affect patients’ user experience and adherence to the systems [45, 47].

Conclusion

In the face of the emerging challenge posed by “Disease X,” mobile hospitals offer significant advantages over traditional healthcare organizations. These mobile facilities leverage modern communication and information technologies to deliver healthcare services through mobile devices or vehicles, enhancing accessibility and efficiency, especially in remote or resource-constrained environments. Their rapid deployment capability allows for the immediate delivery of critical healthcare services during emergencies, such as natural disasters or epidemics that disrupt routine hospital operations [48]. For example, during the COVID-19 outbreak, China deployed mobile field hospitals to centralize patient management and effectively reduce virus transmission. These facilities played crucial roles in controlling the epidemic within the country [49]. The swift response capability of mobile hospitals enables them to quickly reach disaster areas, address medical resource gaps promptly, alleviate the burden on local healthcare organizations, and manage patient flow efficiently [50].

This study, based on expert interview data, employs the framework analysis method to evaluate the current operational status of mobile hospitals. It develops a framework for intelligent diagnosis and treatment, focusing on three dimensions: an intelligent transformation strategy, innovation in intelligent diagnosis and treatment models, and the construction of intelligent auxiliary decision-making systems for these hospitals. This framework aims to accelerate the response rate of mobile hospitals to public health crises, enhance the effectiveness of specialized treatments, and improve the flexibility and practicality of public health emergency management systems to better address the challenges posed by “Disease X” in the future.

Limitations

This study has several limitations: Regarding expert selection, since the research is in the preliminary stage of framework exploration, only 10 experts from China were chosen, which may lead to an insufficient sample size and limited regional/institutional representation, potentially affecting the reliability and generalizability of the conclusions. Furthermore, the current research focuses on the qualitative construction of the framework and has not yet incorporated quantitative methods to systematically validate the indicators. Future research could enhance scientific rigor through the following improvements: (1) Expand the expert sample size by including experts from multiple countries or institutions, employing stratified sampling to optimize representativeness; (2) Introduce quantitative analysis methods (e.g., the Delphi expert consultation method) in subsequent stages to quantitatively screen and prioritize the indicators for mobile hospital construction, thereby strengthening the empirical support and external validity of the conclusions.

Electronic supplementary material

Below is the link to the electronic supplementary material.

Author contributions

Xu Luo and Yongjun Luo contributed to the conception and design of the study.Juanling He and Rongrong Ni acquired the data. Juanling He performed the data analysis and wrote the first draft of the manuscript. Rongrong Ni and Sifeng Wu revised the manuscript critically. All authors contributed to manuscript revision, read, and approved the submitted version.

Funding

This study was supported by Research and Application of Intelligent Diagnosis and Treatment Service System for Fever Clinic, Chongqing Applied Basic Research Fund, China(CSTB2022TIAD-KPX0167).

Data availability

The data that support the findings of this study are available on request from the corresponding author, Mr Luo, upon reasonable request.

Declarations

Ethics approval and consent to participate

This study adhered to the ethical principles outlined in the Declaration of Helsinki. Ethical approval was granted by the Institutional Review Board of the 958th Hospital of the Army Medical University Ethics Committee (ID: IRB20241k-10). Written informed consent was obtained from all participants and witnessed by at least two study personnel. All data were handled confidentially.

Consent for publication

Not applicable.

Competing interests

The authors declare no competing interests.