The predictive performance of artificial intelligence on the outcome of stroke: a systematic review and meta-analysis

Yang, Yujia; Tang, Li; Deng, Yiting; Li, Xuzi; Luo, Anling; Zhang, Zhao; He, Li; Zhu, Cairong; Zhou, Muke

doi:10.3389/fnins.2023.1256592

Cited by 4 publications

(1 citation statement)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A vast array of studies has employed machine learning and statistical methods for AIS prediction. However, most of these studies focus on the prognosis of AIS, while research specifically aimed at predicting the incidence of AIS is less common [37][38][39] . Studies focusing on AIS incidence risk frequently address AIS as a uniform condition or may introduce a single stratifying factor, such as hypertension or diabetes, to forecast AIS occurrences 11,12 .…”

Section: Discussionmentioning

confidence: 99%

Acute ischemic stroke prediction and predictive factors analysis using hematological indicators in elderly hypertensives post-transient ischemic attack

Shu,

Zheng,

Luo

et al. 2024

Sci Rep

View full text Add to dashboard Cite

Elderly hypertensive patients diagnosed with transient ischemic attack (TIA) are at a heightened risk for developing acute ischemic stroke (AIS). This underscores the critical need for effective risk prediction and identification of predictive factors. In our study, we utilized patient data from peripheral blood tests and clinical profiles within hospital information systems. These patients were followed for a three-year period to document incident AIS. Our cohort of 11,056 individuals was randomly divided into training, validation, and testing sets in a 5:2:3 ratio. We developed an XGBoost model, developed using selected indicators, provides an effective and non-invasive method for predicting the risk of AIS in elderly hypertensive patients diagnosed with TIA. Impressively, this model achieved a balanced accuracy of 0.9022, a recall of 0.8688, and a PR-AUC of 0.9315. Notably, our model effectively encapsulates essential data variations involving mixed nonlinear interactions, providing competitive performance against more complex models that incorporate a wider range of variables. Further, we conducted an in-depth analysis of the importance and sensitivity of each selected indicator and their interactions. This research equips clinicians with the necessary tools for more precise identification of high-risk individuals, thereby paving the way for more effective stroke prevention and management strategies.

show abstract

Section: Discussionmentioning

confidence: 99%

Acute ischemic stroke prediction and predictive factors analysis using hematological indicators in elderly hypertensives post-transient ischemic attack

Shu,

Zheng,

Luo

et al. 2024

Sci Rep

View full text Add to dashboard Cite

show abstract

Systematic Review of Machine Learning Applied to the Secondary Prevention of Ischemic Stroke

Chen,

Qian,

Wang

et al. 2024

J Med Syst

View full text Add to dashboard Cite

Miller Fisher’s Rules and Digital Health: The Best of Both Worlds

Andrade,

Mendes,

Silva

2024

Cerebrovasc Dis

View full text Add to dashboard Cite

Background Professor Fisher's legacy, defined by meticulous observation, curiosity, and profound knowledge, has established a foundational cornerstone in medical practice. However, the advent of automated algorithms and artificial intelligence in medicine raises questions about the applicability of Fisher's principles in this era. Our objective is to propose adaptations to these enduring rules, addressing the challenges and leveraging the opportunities presented by digital health. Summary The adapted rules we propose advocate for the harmonious integration of traditional bedside manners with contemporary technological advancements. The judicious use of advanced devices for patient examination, recording, and sharing, while upholding patient confidentiality, is pivotal in modern practice and academic research. Additionally, the strategic employment of AI tools at the bedside, to aid in diagnosis and hypothesis generation, underscores their role as valued complements to clinical reasoning. These adapted rules emphasize the importance of continual learning from experience, literature, and colleagues, and stress the necessity for a critical approach towards AI-derived information, which further consolidates clinical skills. These aspects underscore the perpetual relevance of Professor Fisher's rules, advocating not for their replacement but for their evolution. Thus, a balanced methodology that adeptly utilizes the strengths of AI and digital tools, while steadfastly maintaining the core humanistic values, arises as essential in the modern practice of medicine. Key Messages A commitment between traditional medical wisdom and modern technological capabilities may enhance medical practice and patient care. This represents the future of medicine – a resolute commitment to progress and technology, while preserving the essence of medical humanities.

show abstract

The predictive performance of artificial intelligence on the outcome of stroke: a systematic review and meta-analysis

Cited by 4 publications

References 29 publications

Acute ischemic stroke prediction and predictive factors analysis using hematological indicators in elderly hypertensives post-transient ischemic attack

Acute ischemic stroke prediction and predictive factors analysis using hematological indicators in elderly hypertensives post-transient ischemic attack

Systematic Review of Machine Learning Applied to the Secondary Prevention of Ischemic Stroke

Miller Fisher’s Rules and Digital Health: The Best of Both Worlds

Contact Info

Product

Resources

About