Artificial intelligence in psychiatry research, diagnosis, and therapy

Sun, Jie; Dong, Qunxi; Wang, S; Zheng, Yong-Bo; Liu, Xiaoxing; Lu, Tangsheng; Yuan, Kai; Shi, Jie; Hu, Bin; Lü, Lin; Han, Ying

doi:10.1016/j.ajp.2023.103705

Cited by 39 publications

(10 citation statements)

References 124 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A significant proportion of respondents in our study reported ease in integrating AI tools into their daily workflows, echoing findings from prior research by Fogliato [21], which emphasized the importance of user-friendly interfaces in facilitating technology adoption in healthcare settings [21]. The perceived benefits of AI in enhancing diagnostic efficiency and accuracy likely contributed to this positive attitude, aligning with the findings of a meta-analysis by Sun et al [22], which demonstrated the superior performance of AI-based diagnostic systems compared to traditional methods [22]. However, challenges such as compatibility issues with existing EMR systems and the need for extensive training were also identified, corroborating the findings of studies by Afzal et al [23] and Ebbers et al [24], which emphasized the importance of addressing usability concerns to ensure successful technology adoption in healthcare settings.…”

Section: Discussionsupporting

confidence: 87%

A Comprehensive Evaluation of AI-Assisted Diagnostic Tools in ENT Medicine: Insights and Perspectives from Healthcare Professionals

Alshehri,

Alahmari,

Alasiry

2024

JPM

View full text Add to dashboard Cite

The integration of Artificial Intelligence (AI) into healthcare has the potential to revolutionize medical diagnostics, particularly in specialized fields such as Ear, Nose, and Throat (ENT) medicine. However, the successful adoption of AI-assisted diagnostic tools in ENT practice depends on the understanding of various factors; these include influences on their effectiveness and acceptance among healthcare professionals. This cross-sectional study aimed to assess the usability and integration of AI tools in ENT practice, determine the clinical impact and accuracy of AI-assisted diagnostics in ENT, measure the trust and confidence of ENT professionals in AI tools, gauge the overall satisfaction and outlook on the future of AI in ENT diagnostics, and identify challenges, limitations, and areas for improvement in AI-assisted ENT diagnostics. A structured online questionnaire was distributed to 600 certified ENT professionals with at least one year of experience in the field. The questionnaire assessed participants’ familiarity with AI tools, usability, clinical impact, trust, satisfaction, and identified challenges. A total of 458 respondents completed the questionnaire, resulting in a response rate of 91.7%. The majority of respondents reported familiarity with AI tools (60.7%) and perceived them as generally usable and clinically impactful. However, challenges such as integration with existing systems, user-friendliness, accuracy, and cost were identified. Trust and satisfaction levels varied among participants, with concerns regarding data privacy and support. Geographic and practice setting differences influenced perceptions and experiences. The study highlights the diverse perceptions and experiences of ENT professionals regarding AI-assisted diagnostics. While there is general enthusiasm for these tools, challenges related to integration, usability, trust, and cost need to be addressed for their widespread adoption. These findings provide valuable insights for developers, policymakers, and healthcare providers aiming to enhance the role of AI in ENT practice.

show abstract

Section: Discussionsupporting

confidence: 87%

A Comprehensive Evaluation of AI-Assisted Diagnostic Tools in ENT Medicine: Insights and Perspectives from Healthcare Professionals

Alshehri,

Alahmari,

Alasiry

2024

JPM

View full text Add to dashboard Cite

show abstract

“…In advancing psychedelic epidemiological research, a promising opportunity lies in integrating robust causality assessment methods [ 45 ] and implementing artificial intelligence (AI) techniques to facilitate comprehensive analysis of large datasets [ 46 , 47 ]. Additionally, substantial methodological refinement can be achieved by incorporating rigorous systematic reviews and meta-analyses, enhancing the quality and depth of the evidence regarding the awareness and utilization patterns for psychedelic substances within specific target populations.…”

Section: Discussionmentioning

confidence: 99%

Cultural Divergence in Psychedelic Use among Medical Students: An ESPAD-Adapted Survey among Poles and Iraqis

Al-Imam,

Motyka,

Michalak

2024

EJIHPE

View full text Add to dashboard Cite

Psychedelics can profoundly alter cognition and consciousness. Their use in Middle Eastern countries, including Iraq, is ambiguous. We aim to investigate psychedelic awareness and use among Iraqi and Polish medical students. We surveyed 739 university students from Poland (315) and Iraq (424) using 31 adapted questions from the European School Survey Project on Alcohol and Other Drugs (ESPAD). We conducted multivariable analyses based on binary logistic regression to identify the factors associated with psychedelic awareness and use. Most of the respondents were females (65.6%) and senior medical students (69.6%). Notably, the Polish students displayed a higher prevalence of psychedelic use (21.6% compared to 1.2%, p < 0.001), while the Iraqi participants exhibited a lower familiarity with psychedelics (p < 0.001). The multivariable model demonstrated a commendable level of statistical accuracy and satisfactorily conformed to the Hosmer–Lemeshow goodness-of-fit test (statistical accuracy = 91.61%, Nagelkerke R2 = 0.488, p-value = 0.848). Several factors emerged as correlates of increased psychedelic use, including lacking an intact religious belief system or commitment to its practice (OR = 7.26, 95% CI [2.33, 22.60]). Additionally, those who perceived a low risk associated with sporadic psychedelic use (3.03, [1.44, 6.36]) were likelier to engage in such behavior. Other factors included residing in Poland (2.82, [0.83, 9.55]), maintaining positive attitudes toward psychedelics (2.49, [1.20, 5.14]), frequent social nightlife activities (2.41, [1.26, 4.61]), male gender (2.05, [1.10, 3.85]), and cigarette or tobacco smoking (2.03, [1.06, 3.86]). Significant disparities exist between Poles and Iraqis, influenced by religiosity, perceptions of the usage risks, geographical location, gender, attitudes toward psychedelics, parental leniency, and social freedom, especially concerning nightlife activities. Addressing the factors influencing psychedelic usage is paramount to responsible psychedelic engagement and culturally sensitive interventions to prevent misuse.

show abstract

“…The application of Statistical Signal Processing in AD detection holds substantial potential for early diagnosis, tracking disease progression, and assessing the effectiveness of therapeutic interventions. By statistically characterizing the deviations in neural activity and connectivity, this approach can enable the identification of subtle, preclinical changes in brain function that precede observable cognitive deficits, thus fostering early intervention and individualized treatment strategies [49].…”

Section: Statistical Signal Processing For Ad Detectionmentioning

confidence: 99%

Recent Progresses in Signal Processing for Alzheimer's Disease Detection

Zhao

2023

Preprint

View full text Add to dashboard Cite

Alzheimer's Disease (AD) is a neurodegenerative disease that is common in the elderly. This paper introduces the overview of Alzheimer's disease and the application of relevant signal processing methods in its detection. Signal processing is a technique that converts raw data into meaningful information and is widely used in the medical field. This paper lists common signal processing techniques, including Fourier transform, time-frequency analysis and statistical signal processing, and discusses their applications in the detection of Alzheimer's disease. Fourier transform can convert time domain signals into frequency domain representations, providing an effective tool for the study of EEG in Alzheimer's disease. Time-frequency analysis can perform a combined time and frequency analysis of the signal to help detect the signal characteristics of Alzheimer's disease. Statistical signal processing methods can be used to identify the features of Alzheimer's disease by building mathematical models. Finally, the challenges of Alzheimer's disease detection are discussed, including signal noise, diversity, and insufficient data volume. Through in-depth research and development of signal processing methods, it is expected to improve the accuracy and efficiency of early detection of Alzheimer's disease.

show abstract

Artificial intelligence in psychiatry research, diagnosis, and therapy

Cited by 39 publications

References 124 publications

A Comprehensive Evaluation of AI-Assisted Diagnostic Tools in ENT Medicine: Insights and Perspectives from Healthcare Professionals

A Comprehensive Evaluation of AI-Assisted Diagnostic Tools in ENT Medicine: Insights and Perspectives from Healthcare Professionals

Cultural Divergence in Psychedelic Use among Medical Students: An ESPAD-Adapted Survey among Poles and Iraqis

Recent Progresses in Signal Processing for Alzheimer's Disease Detection

Contact Info

Product

Resources

About