The items in this checklist were as follows: (1) is the review question clearly and explicitly stated? (2) Were the inclusion criteria appropriate for the review question? (3) Was the search strategy appropriate? (4) Were the sources and resources used to search for studies adequate? (5) Were the criteria for appraising the studies appropriate? (6) Was critical appraisal conducted by ≥2 reviewers independently? (7) Were there methods to minimize errors in data extraction? (8) Were the methods used to combine studies appropriate? (9) Was the likelihood of publication bias assessed? (10) Were recommendations for policy or practice supported by the reported data? (11) Were the specific directives for new research appropriate?

The items in this checklist were as follows: (1) is it clear in the study what is the cause and what is the effect (ie, there is no confusion about which variable comes first)? (2) Was there a control group? (3) Were participants included in any comparisons similar? (4) Were the participants included in any comparisons receiving similar treatment or care other than the exposure or intervention of interest? (5) Were there multiple measurements of the outcome both before and after the intervention or exposure? (6) Were the outcomes of participants included in any comparisons measured in the same way? (7) Were outcomes measured in a reliable way? (8) Was follow-up complete and, if not, were differences between groups in terms of their follow-up adequately described and analyzed? (9) Was appropriate statistical analysis used?

The items in this checklist were as follows: (1) is there congruity between the stated philosophical perspective and the research methodology? (2) Is there congruity between the research methodology and the research question or objectives? (3) Is there congruity between the research methodology and the methods used to collect data? (4) Is there congruity between the research methodology and the representation and analysis of the data? (5) Is there congruity between the research methodology and the interpretation of the results? (6) Is there a statement locating the researcher culturally or theoretically? (7) Is the influence of the researcher on the research and vice versa addressed? (8) Are participants, and their voices, adequately represented? (9) Is the research ethical according to current criteria or, for recent studies, is there evidence of ethics approval by an appropriate body? (10) Do the conclusions drawn in the research report flow from the analysis or interpretation of the data?

The use of AI for medical questionnaires harnesses DL and ML to enhance disease evaluation, facilitate the development of novel questionnaires, and improve data predictive capacities. These 3 facets are essential diagnostic stages for assessing both physiological conditions and psychological issues. By reviewing recent algorithmic advances and clinical practice, this study uncovered the potential of incorporating AI into traditional medical questionnaires, offering new perspectives for broader clinical applications and informed medical diagnoses (Figure 4).

According to WHO data, since the onset of the COVID-19 pandemic, the global population experiencing anxiety and depression has markedly increased, accompanied by a 40% surge in the use of standardized questionnaires [73-76]. Traditional questionnaires offer convenient dissemination and, in some cases, self-administration [77-79]. However, as definitive diagnoses still require physician consultations, the assessment process remains labor intensive. Due to its speed and accuracy in data processing, AI has progressively been integrated into clinical support [43,44]. Notably, DL and NLP technologies—such as the pretrained bidirectional encoder representations from transformers (BERT) model and conversation-based models such as ChatGPT—observed rising adoption rates from 2023 to 2024 [77-80]. Furthermore, traditional algorithms, including support vector machine and k-nearest neighbor, continue to effectively evaluate patient data for complex disorders. Recent developments in the technical frameworks for applying these methods to medical questionnaire assessments are illustrated in Figure 2.

Analysis of AI applications in medical questionnaires showed that only 21% (3/14) of the studies involved AI-assisted questionnaires that had entered the clinical validation stage, whereas the remaining 79% (11/14) of the articles described the technology as being in the research stage (Multimedia Appendix 2). Clinical validation was been achieved in patient experience assessment using NLP-based sentiment analysis, in spinal pain evaluation through conversational AI systems [37], and in surgical risk prediction using ML for cataract surgery [66]. These applications share the characteristics of established clinical workflows, model interpretability, and structured validation frameworks. Most AI applications in mental health assessment, pain evaluation, disease differentiation, and specialized assessments remain in the research phases despite promising performance. This pattern stems from psychological assessment complexity [81], data standardization challenges, stringent clinical implementation requirements [82], and emerging technologies’ nascent nature in medical contexts. The findings indicate that AI-assisted medical questionnaires are technically feasible but still transitioning from research innovation to clinical implementation.

By leveraging DL on patient data, AI effectively evaluates how medical questionnaires adaptively distinguish between patient symptom variations, thereby accurately capturing changes in health status and demonstrating advantages in dynamic assessment. During prediagnostic evaluations, many pathological conditions have overlapping manifestations. For instance, post–COVID-19 sequelae resemble acute COVID-19 symptoms, and depression in bipolar disorders overlaps with that observed in unipolar depression [83-86]. To enhance diagnostic accuracy, one study used a series of RF algorithms to assess the psychometric properties of the DePaul Symptom Questionnaire–Short Form in classifying individuals with post–COVID-19 sequelae, those with myalgic encephalomyelitis or chronic fatigue syndrome (unrelated to COVID-19), and healthy controls. The results indicated that the DePaul Symptom Questionnaire–Short Form successfully distinguished patients with post–COVID-19 sequelae from healthy controls, achieving an accuracy of 92.18% [35].

Moreover, AI-based evaluations validated the diagnostic sensitivity of traditional questionnaires for subtle disorders such as women’s physical and mental health issues influenced by hormonal fluctuations. Researchers used support vector machine, artificial neural networks (ANNs), and decision trees to confirm the validity and accuracy of the International Physical Activity Questionnaire for menopausal women [71]. Currently, integrating multiple algorithms helps improve both model interpretability and patient classification precision. One team, for example, used a hybrid model (genetic algorithms combined with ANNs) to evaluate the effects of different weighting schemes in a traditional scale applied to daily stress events; after weight adjustments, they reported that the traditional questionnaire achieved a sensitivity of 83% and a specificity of 81% for stress detection, positioning the modified instrument as a high-performance screening tool [70].

Collectively, these findings demonstrate that AI enhances the precision with which traditional questionnaires differentiate between disease categories and unique patient populations while simultaneously refining traditional questionnaire metrics.

One of the key advantages of AI-driven data training is its capacity to construct intelligent data systems that assist clinicians in making more accurate diagnoses. Although clinical medical questionnaires undergo lengthy validation to ensure efficacy, traditional instruments often fail to comprehensively capture authentic patient behavior. For example, patients may complete questionnaires too hastily without supervision, leading to distorted results, and even after traditional assessments, diagnostic discrepancies of up to 17% may arise among different therapists [87]. Consequently, multidimensional approaches are needed in psychological and psychiatric diagnostics to reduce subjective influences and create intelligent data systems. A study on pathological voice data used AI to enhance the objectivity of the grade, roughness, breathiness, asthenia, and strain scale comparing 2 convolutional neural network (CNN)–based models—one built on Google’s TensorFlow and the other on Apple’s Core ML—both trained on identical pathological voice datasets [67]. By comparing these 2 models in classifying severity levels in pathological speech, it became possible to validate grade, roughness, breathiness, asthenia, and strain questionnaire results in real time without specialized equipment, thereby increasing the clinical objectivity of traditional questionnaires (Figure 5 [71]). In another effort, researchers designed a secure neural network–based application, randomly training and testing an ANN for diagnosing facial pain syndromes [67]. The system achieved a sensitivity of 92.4% and a specificity of 87.8%. Ultimately, AI-based data training promises to integrate patient information worldwide into intelligent online databases, thus expanding the accessibility and dissemination of intelligent data in the medical field.

Since 2013, ANNs and genetic algorithms have been used in the development of novel medical assessment models, enhancing parameter selection for psychological questionnaires and improving the accuracy of predicting patients’ psychological states [88,89]. In 2021 and 2022, as the range of assessment methods broadened, integrating traditional ML algorithms (logistic regression [LR], RF, and decision tree) with ANN and DL tools further advanced the design of complex medical questionnaires and refined the evaluation of symptoms related to anxiety and depression (Figure 3). Nevertheless, to achieve more profound and long-term predictions of patients’ psychological conditions, it remains essential to optimize both questionnaire item formulation and the assessment processes.

In developing medical questionnaires suited to diverse patient populations and conditions, AI integration confers distinct advantages. Traditional assessment methods, particularly those used to diagnose late-life depression, face notable limitations. Late-life depression is often accompanied by various comorbidities, and subtle symptom distinctions can be difficult to capture using conventional questionnaires [90-93]. To address this complexity, especially in older adults, NLP techniques can analyze patients’ linguistic patterns, thereby detecting latent symptoms that may be overlooked by traditional methods and, ultimately, expanding the questionnaire’s applicability. Moreover, Bayesian network–based analyses have been used to generate highly matched items, effectively facilitating the development of a potential risk assessment system for geriatric conditions [94,95]. AI-driven approaches have also improved applicability for other vulnerable groups. For instance, the Raghavendra Manjunath Shetty Digital Anxiety Scale leverages AI-generated facial expressions for children [68]. By enabling children to select expressions that best match their emotions, this interactive approach overcomes the limitations of traditional questionnaires, which often struggle to accurately convey or capture younger children’s emotional states.

In addition, scholars have applied the extreme gradient boosting algorithm to streamline risk assessment questionnaires for insomnia and obstructive sleep apnea (OSA) [38] (Figure 6 [38,96]). By avoiding cumbersome overnight polysomnography measurements, researchers focused on feature importance to design a simplified questionnaire that accurately predicts the risks of 3 sleep disorders—OSA, comorbid insomnia and sleep apnea, and insomnia—with an area under the receiver operating characteristic curve (AUROC) exceeding 0.897 for each. Figure 6 [38] illustrates the performance of a simplified questionnaire in predicting sleep disorder risk, demonstrating high accuracy in identifying OSA (AUROC=0.897), comorbid insomnia and sleep apnea (AUROC=0.947), and insomnia (AUROC=0.922). Figure 5 [86] also highlights the influence of various features on model predictions, ultimately improving the questionnaire’s applicability across different severities of sleep disorders. By replacing complex, burdensome items with a high-confidence, streamlined set of questions, patients face a reduced response burden, and applicability to diverse patient populations is enhanced.

In traditional clinical assessments, patients often interpret and respond differently due to varied cultural backgrounds, language habits, and life experiences. Questionnaire development must consider these cultural factors and provide timely feedback. Failure to account for the patient’s experience can result in extreme responses that skew diagnostic outcomes. Thus, incorporating appropriate open-ended questions can flexibly capture differences in patients’ understanding of medical questionnaires. One study used a multilingual and multicultural version of ChatGPT to generate a low back pain assessment questionnaire [65]. Its findings demonstrated that language training technology could effectively overcome linguistic and cultural barriers, offering strong support for future cross-cultural medical evaluations. Another study leveraged a speech dialogue system trained to develop a new pain assessment tool for patients with spinal issues [37]. By integrating natural language understanding and speech recognition, the system quickly recorded patients’ pain information and improved clinician-patient interactions. The error rates in speech recognition for physicians, nurses, and patients were 13.5%, 16.8%, and 34.7%, respectively. AI’s real-time feedback capabilities enable it to identify key factors from patient assessments across different backgrounds. One study showed that an AI-based patient-reported experience measure developed through NLP techniques could extract crucial information from patients’ open-ended responses [64], promptly relaying insights to clinicians. This timely exchange not only saves analytic time but also strengthens trust and understanding for patients from diverse cultural contexts during the diagnostic process.

Currently, AI serves as a crucial and promising tool for supporting physiological treatment and enabling early psychological interventions [97]. In predictive tasks, DL models (such as ANNs and CNNs) excel at extracting features from complex datasets, whereas ensemble learning algorithms—gradient boosting, RF, and Extreme Gradient Boosting—specialize in classification and prediction. By combining these technical strengths, AI models have transcended traditional medical constraints, effectively increasing the precision of disease prediction and diagnosis at multiple critical time points [98]. From 2022 onward, DL (CNNs and DL) and NLP (BERT, NLP, and ChatGPT) have observed growing adoption rates. Notably, the application of CNNs surged in 2023 (Figure 3), and the use of BERT and ChatGPT continued to expand in health care throughout 2024 [99]. These trends collectively underscore the advantages of integrating a range of AI methodologies to enhance predictive tasks in medical questionnaires.

According to 2024 WHO data, global aging is intensifying, and chronic diseases now account for >70% of all worldwide deaths [100]. In this context, AI-enabled analysis of global patient data can facilitate disease prediction. Ophthalmological conditions such as cataracts present an increasing diagnostic burden, with surgery remaining the only effective clinical intervention. Thus, the timely identification of risk factors for patients with cataracts is essential [101-103]. A 2022 study found that DL models surpass traditional statistical models in screening accuracy for age-related diseases, enabling more rapid identification of high-risk older populations. Further research has examined the use of AI for predicting cataract surgery risk. By leveraging questionnaires and medical records, the study compared its results to those of a traditional LR model. ML models achieved an area under the curve (AUC) between 0.781 and 0.790, outperforming the LR model’s AUC of 0.767. The gradient boosting machine model demonstrated the best performance, attaining an AUC of 0.790 [101]. These findings indicate that ML can accurately forecast disease occurrence by rapidly assimilating diverse data inputs even in the absence of biological data.

At present, the application of NLP techniques in mental health issue prediction is rapidly expanding [104]. ML methods (eg, LR and gradient boosting) and feature selection strategies have shown particular promise in early warning systems for mental health issues. One study on depression assessment used multiple ML and DL models to predict different levels of depressive states—normal, moderate, and severe. Among them, the RF model achieved an accuracy of 98.08%, outperforming the gradient boosting model (94.23%) and the CNN (92.31%) [103]. By applying feature selection and hyperparameter optimization, the study further enhanced model performance.

In addition, another research team used LR, RF, and gradient boosting models to evaluate suicidal intent and behaviors. Through Shapley Additive Explanations analysis, they identified the most effective features and reconstructed a simplified version of the Suicide Crisis Inventory–2 [36]. The LR model performed best, and the simplified questionnaire efficiently assessed and predicted suicidal crises in clinical settings, thereby reducing the supervision burden on health care providers [66]. The integration of AI not only improves data interpretability and predictive reliability but also contributes to timely health interventions in future health care systems.

The global population is projected to grow continuously by approximately 1.3 billion people between 2020 and 2050, representing a 17% increase from the 2020 population, with a peak of approximately 9.73 billion by 2064 [105]. Health informatics is a fast-growing area in the health care field. These instruments serve as critical tools for assessing population health [106]. Currently, AI technologies have already demonstrated significant potential and advantages in the development, analysis, and prediction processes of medical questionnaires.

Despite the remarkable progress of AI in this domain, numerous challenges and research gaps remain. Therefore, this section presents several new research directions based on the potential of AI to enhance rapid assessment, precise prediction, and adaptable response methods in medical questionnaires, aiming to further promote AI’s application and innovation in this field.

With the growing global population, the volume of questionnaires that health care institutions must collect and analyze is steadily increasing [107]. Traditional questionnaire evaluation methods are often time-consuming and require substantial human and economic resources [108]. Applying AI technologies to questionnaire assessments can significantly reduce labor and financial costs, a benefit that is especially pronounced in large-scale evaluations. Rapid questionnaire evaluation also enables researchers to quickly optimize questionnaires and establish related case identification systems, thereby allowing health care institutions to promptly allocate public health resources and respond more efficiently to public health events [109].

As global life expectancy continues to rise, the number and proportion of older individuals also increase. By 2030, a total of 1 in 6 people worldwide will be aged >60 years, and the population aged ≥60 years will grow from the current 1 billion to 1.4 billion, doubling to 2.1 billion by 2050 [110]. Common health issues among older adults include cognitive impairment, cataracts, and depression [111]. Integrating AI with medical questionnaires to predict disease occurrence can help family members and health care providers implement early interventions or treatments [112]. However, predictions based solely on questionnaires may have limitations. AI shows high predictive accuracy when incorporating physiological data such as speech signals, heart rate, and medical imaging [113-115]. Future research could combine questionnaire-based predictions with additional physiological information to improve and confirm the accuracy of disease forecasting.

It is estimated that 1.3 billion people worldwide have severe disabilities, and this number is expected to rise [116]. Individuals with disabilities who have experienced stroke, limb loss, or spinal cord injuries often exhibit impaired hand function [117-119], significantly reducing their efficiency in completing traditional paper-based questionnaires. Integrating traditional questionnaires with AI-driven LLMs to create an AI questionnaire is one solution. By leveraging LLM technologies, users can respond verbally to questionnaire items, circumventing traditional written formats [120,121] (Figure 7).

Persons with disabilities may face discrimination in various aspects of life, resulting in generally lower educational attainment than that of other populations [122]. For these groups, especially individuals with mental disabilities such as autism or dementia, challenging vocabulary, complex sentence structures, and ambiguous answer choices pose major obstacles to questionnaire completion [123]. One approach involves using NLP-enhanced questionnaires; AI models such as ChatGPT or Bard can provide immediate explanations of terminology, thereby reducing the difficulty and improving the efficiency of questionnaire completion for individuals with lower educational levels [124,125]. Another solution integrates AI image generators such as DALL-E to add graphical support, thereby increasing the clarity and comprehensibility of questionnaire options [126]. In addition, combining virtual reality paradigms with AI-driven visual questionnaires may offer more adaptive and inclusive assessment options for individuals with cognitive limitations. This strategy could further expand the range of response modalities available in digital health evaluation [127,128].

Some individuals with mental disabilities may resist answering questionnaires through writing or speech. This reluctance can compromise the completion rate of traditional medical questionnaires, disrupt data collection, and undermine data validity. In fact, beyond textual and linguistic information, patients’ facial expressions, vocal emotions, and behaviors also carry clinically valuable data. Embodied AI robots with multimodal data collection capabilities may offer a solution [129]. By using cameras, microphones, and other devices, these robots can capture facial expressions, vocal emotional cues, and behavioral indicators during questionnaire administration [130,131]. AI-driven evaluation and analysis of these data can, in turn, guide the refinement of patient health questionnaires.

Individuals with severe disabilities—such as those with cerebral palsy, amyotrophic lateral sclerosis, or locked-in syndrome—may be unable to respond to certain medical questionnaires using normal speech or gestures for physiological or psychological reasons [132,133]. For these populations, clinicians might consider using AI technologies, brain-computer interfaces, or brainwave data to interpret and analyze patients’ eye movements, enabling more personalized completion of medical questionnaires. However, in doing so, health care professionals must ensure the accuracy of these physiological measurements [134]. Preventing the misinterpretation of patient information is essential to maintaining the validity and reliability of medical questionnaire data.

AI technologies have already demonstrated substantial potential in the realm of medical questionnaires. However, the widespread implementation of AI still faces a range of complex challenges, including data privacy and security, data quality, system integration, and social equity. This section will systematically examine these issues and provide an in-depth analysis of possible strategies to overcome them. The goal is to furnish a scientific foundation and direction for effectively applying AI in medical questionnaires, thereby driving its comprehensive implementation and optimization within the health care sector.

Despite the potential that AI brings to the development, prediction, and evaluation of medical questionnaires, it also exposes multidimensional structural limitations in the context of actual clinical requirements.

ML models such as RF and LR are frequently adopted not because they represent the cutting edge of technology but because they are easier for health care professionals to understand, are less costly to validate, and do not require a reconfiguration of the hospital’s information system [135,136]. For example, Siddiqua et al [63] achieved high classification accuracy using an integrated ML model in their study of depression risk, but the choice of model was largely motivated by considerations of interpretability rather than absolute optimality of technical performance. This phenomenon suggests that the trust mechanisms required for clinical adoption are far more dominant than model complexity in many settings.

In contrast, DL models embody a different paradigm. These methods are able to mine complex patterns in high-dimensional data and even achieve learning without predefined feature structures [137]. The advantages are particularly significant when dealing with multimodal data or unstructured text [138]. However, in the specific scenario of medical questionnaires, DL models often struggle to generalize stably due to small sample sizes, high data annotation costs, and large model variance [137,139,140]. Even though ANNs performed well when used to classify facial pain in the study by McCartney et al [69], the model still faces greater challenges in clinical settings subject to legal liability due to the lack of a clear and traceable explanatory path for its diagnostic mechanism.

The emergence of natural language models, on the other hand, brings new possibilities for questionnaire development and interactive evaluation. Systems such as ChatGPT are capable of generating linguistically fluent question items and simulating preliminary physician-patient dialogues [141]. However, this class of models suffers from well-known problems such as factual errors, semantic drift, and contextual mismatch [142-144]. Coraci et al [65] validated the correlation of an AI-generated questionnaire for low back pain with a traditional scale but pointed out problems such as incomplete logic of its content and inconsistency in its scoring criteria. In the absence of strong constraints, the variability of such systems is highly likely to undermine the standardized properties on which medical questionnaires are based.

Therefore, although each of the current AI approaches has its own technical advantages, their actual value still depends on whether they can be adapted to specific clinical needs, system constraints, and resource conditions. When the task emphasizes interpretability, limited data samples, or low deployment costs, ML is still a safe choice. When the problem involves high-dimensional inputs or the identification of subtle diagnostic clues, DL is advantageous provided that the output has a verifiable path of interpretation. Natural language modeling contributes most when interactivity and content adaptation are core requirements, but it must operate under controlled mechanisms to avoid destabilizing the data. Therefore, future research should not stop at improving technical performance but should aim to build model selection strategies that respond to real clinical situations.

The application of AI in medical questionnaires necessitates handling large volumes of personal health data, making data privacy and security primary concerns [145]. The sensitivity of patient information demands stringent privacy safeguards throughout data collection, storage, and sharing processes. Federated learning has emerged as an innovative approach to protect data privacy, allowing AI models to learn from distributed datasets without centralized data sharing, thereby mitigating the risk of data breaches [146]. However, this approach still faces limitations, particularly when dealing with large-scale, heterogeneous data. In such complex scenarios, the privacy-enhancing capabilities of federated learning may be constrained [147]. Hence, future research must focus on developing more effective data privacy protection techniques. Concurrently, as AI systems become more powerful, data security requirements intensify. Related studies can further explore techniques such as homomorphic encryption and differential privacy [148], ensuring data security during transmission and processing.

In fact, safeguarding data privacy and security requires not only technical solutions but also robust legal support. Regulations such as the European Union’s General Data Protection Regulation and the US Health Insurance Portability and Accountability Act set legal standards for the legitimate use of personal health data [149]. Nonetheless, striking a balance between efficient data use and privacy protection remains a complex challenge in practice. Future research should continue exploring the equilibrium between privacy safeguards and data availability, especially when sharing data across multiple institutions. Ensuring patient information security while enhancing data usability is a key issue warranting focused attention.

As global health care systems improve, medical questionnaire data are often collected from multiple institutions. During data sharing among health care facilities, inconsistencies can arise due to variations in language translation, data formats, recording methods, and collection standards. When integrating AI into the evaluation and prediction processes for medical questionnaires, data discrepancies—such as bias, inaccuracies, or inconsistencies—can significantly undermine the reliability of AI assessments [150,151]. To ensure stable AI model performance across diverse questionnaire types, future research should consider standardizing data collection and processing methods.

Beyond data quality, data bias also critically influences the performance of AI systems in medical questionnaire development, evaluation, and prediction [152]. Bias in AI systems often stems from imbalanced training data [153]. For example, if the questionnaire data used for training underrepresent certain racial or marginalized groups or groups with certain disabilities, the model’s accuracy and predictive capabilities will diminish for these populations, potentially hindering their access to timely and effective health care services [154]. To address this issue, it is critical to ensure the diversity and representativeness of training data during questionnaire collection and development. Future research could use standardized methods such as the integration of the WHO’s Data Quality Review framework and the Metric framework designed specifically for health care AI to systematically validate the quality of training datasets [155,156]. In addition, future studies could use targeted data collection strategies such as NLP-based terminology simplification, visual questionnaire enhancement, and culturally adapted translation [157]. These might help reduce the risk of exclusion of specific populations, particularly older people, people with disabilities, and linguistically or culturally marginalized groups [158]. These combined efforts can contribute to the development of more inclusive and bias-resistant AI health assessment models.

While the combination of AI with the health care clinical environment offers transformative potential for the evaluation, development, and prediction of health care questionnaires, AI continues to suffer from significant technical limitations that hinder its full application and effectiveness. The accuracy of AI diagnosis is highly dependent on the quality, quantity, and diversity of the training data [159]. If models are developed based on limited or homogeneous datasets, they tend to show a decrease in predictive performance when applied to more diverse or different patient populations, thus increasing the risk of misdiagnosis or missed diagnoses [160]. In addition, the diagnostic conclusions drawn by AI are themselves subject to a degree of uncertainty [161]. Particularly when dealing with microscopic lesions or early stages of a disease, this uncertainty may manifest itself in a high false-positive or false-negative rate, which can negatively affect clinical decision-making and may even delay patients receiving effective treatment [162].

Practical implementation challenges complicate the integration of AI-enhanced questionnaires into clinical practice, especially when considering novel response modalities (Figure 7). Integrating AI-based questionnaire tools into existing clinical workflows can be resource intensive, involving significant initial setup costs and ongoing training requirements for health care providers [163]. Clinicians are often skeptical due to the limited transparency and interpretability of AI algorithms, which further hinders the widespread adoption of AI [164,165]. Therefore, the future development of transparent and explainable AI systems and the provision of targeted training and education for health care professionals are important strategies to overcome these barriers and facilitate the successful integration of AI into clinical practice.

For AI-based questionnaire tools to be successful in health care environments, the ability to integrate with existing health care infrastructure is critical. However, the complexity of health care systems and the lack of data interoperability pose significant challenges to such integration. Current health care systems are often intricate, with established workflows and legacy technologies that may be incompatible with new AI tools [153]. Implementing AI-based questionnaires typically requires significant infrastructure upgrades, capital investments, and time-consuming workflow redesigns. In addition, different health care institutions often use disparate data standards and formats within their electronic health record systems [166]. This variation complicates the exchange and integration of data from AI-based questionnaire tools.

Related current studies, such as the Mayo Clinic’s successful integration of an AI-based mental health screening questionnaire into its Epic electronic health record system using the Fast Healthcare Interoperability Resources standard, demonstrate advancements in health care technology [167,168]. This study significantly improved diagnostic efficiency and clinician satisfaction. Similarly, the UK National Health Service seamlessly integrated an AI-based dementia screening tool using the Health Level Seven protocol [169]. This technology streamlined clinical workflow and improved patient prognosis. These studies demonstrate that standardized interoperability frameworks can play a key role in bridging the technological divide between AI tools and clinical systems.

To facilitate scalable and sustainable AI integration, future research could prioritize standardized data formats such as the Health Level Seven or Fast Healthcare Interoperability Resources protocols to build flexible and scalable technology interfaces. Such solutions help lower the threshold of system integration and reduce the disruption to established processes, which will be beneficial in enhancing the acceptance of AI systems by medical staff and promoting the sustainable development of AI technologies in diverse health care scenarios.

Deploying AI in health care settings raises key ethical and regulatory issues [170]. The transparency of algorithms is critical, and lack of interpretability may undermine clinician trust and potentially compromise patient safety through opaque clinical recommendations. Ensuring that AI decisions are clearly explainable and illustrative is essential to promote clinician acceptance and reduce risk [171,172].

Informed consent is also a key ethical consideration [173,174]. Patients need to be fully informed about how their data will be used by AI systems, including the potential risks and benefits, highlighting the need for transparent communication and robust consent processes. In addition, the allocation of responsibilities in AI-assisted diagnostics is an ongoing regulatory challenge [175,176]. It is essential to clearly define responsibilities among health care providers, AI developers, and organizations, particularly in the event of errors or adverse events. This requires comprehensive regulatory guidelines and liability frameworks to address the issue of liability in a transparent and effective manner.

It is important to note that the use of AI must comply with strict regulatory standards, including the General Data Protection Regulation and Health Insurance Portability and Accountability Act [177,178]. This is crucial for the legal and ethical use of AI-powered medical questionnaires. Future research should meet these stringent data protection and privacy requirements to better ensure a foundation for the safe and ethical integration of AI technologies into medical practice.