Useless piece of shit! NO DIET PROTOCOLS CREATED! What the fuck do you think stroke research is for? Just getting published; obviously don't care about stroke survivors or definitively preventing stroke?
Get rights and content
Introduction
Stroke,
characterized by its extremely high mortality and disability rates, has
already become one of the major disease types that pose a great threat
to human life and health worldwide (Qin et al., 2022; Campbell et al.,
2019; Hilkens et al., 2024). Based on the results of epidemiological
surveys, taking the United States as a typical example for analysis, the
prevalence of stroke has shown a significant upward trend, and it is
expected to climb from 3 % in 2012 to 4 % in 2030. Along with this, the
annual costs in the medical and nursing fields will approach as high as
nearly 200 billion US dollars (Ovbiagele et al., 2013). Post-stroke
depression (PSD), one of the most common neuropsychiatric complications
of stroke, has an incidence rate of 30–50 % and significantly increases
mortality and disability rates in patients (Lanctôt et al., 2020; Frank
et al., 2022; Chen et al., 2024). In view of this severe situation, if
high-risk stroke patient groups can be accurately identified in the
early stage of the disease and primary prevention strategies can be
implemented in advance, it is expected to significantly reduce the heavy
medical burden borne by society and the families of patients. Driven by
this background, prediction models and scoring scales have been
constructed and gradually developed and improved as effective
countermeasures, aiming to provide scientific basis and decision support
for the early warning and precise prevention and control of stroke and
PSD.
In the field of
neurosurgery, numerous scoring scales have been widely recognized.
Representative ones among them include the Glasgow Coma Scale (GCS)
(Teasdale and Jennett, 1974), the Mini-Mental State Examination (MMSE)
(Folstein et al., 1975), and the National Institutes of Health Stroke
Scale (NIHSS) (Kwah and Diong, 2014), etc. These scales, with their
remarkable advantages such as simple structure and convenient operation,
have been widely popularized and applied in clinical practice and have
become indispensable important tools in the diagnosis and treatment
process of neurosurgery. However, in terms of predicting the occurrence
of stroke, there is a relative lack of effective prediction models
available at present. Among them, although the Framingham Stroke Risk
Assessment Scale is somewhat well-known, it has many limitations itself.
For example, it has deficiencies in aspects such as the scope of risk
factors covered, the performance of prediction accuracy in specific
populations, and the adaptability to complex clinical situations, which
has led to its failure to be widely used in predicting the occurrence of
stroke in clinical practice.
In
addition, although some research teams have been committed to
developing a series of prediction models (Sonoda et al., 2019; Arafa et
al., 2022; Liu et al., 2020; Yu et al., 2021; Li et al., 2023), from the
overall effect evaluation, these models have not reached an ideal state
in key indicators such as prediction accuracy, practicability, and
universality, and it is difficult for them to meet the actual clinical
needs. Based on this, both clinicians when formulating precise diagnosis
and treatment plans and patients during the process of self-health
management and risk prediction are urgently in need of a stroke
prediction model that combines the characteristics of simplicity and
high accuracy to fill this crucial gap in current clinical practice and
provide more powerful support and guarantee for the early warning and
effective prevention and control of stroke.
SHAP
(SHapley Additive exPlanations), as an effective method specifically
used to interpret the output of machine learning models (Ali et al.,
2023), has its theoretical foundation deeply rooted in the concept of
Shapley values in game theory. By precisely calculating the contribution
degree of each feature in the model to the prediction results, SHAP
endows machine learning models with a high degree of interpretability.
Through this way, it is possible to gain in-depth insights into the
specific roles and contribution magnitudes played by each feature in the
process of generating the model's prediction results. The core
advantages of this method are remarkable. It can accurately and stably
measure and evaluate the importance of features. The obtained
measurement values have a wide range of application values. They can not
only be applied to the in-depth analysis of individual prediction
results to clarify the mechanism of each feature behind specific
predictions but also help with the systematic analysis of the overall
behavioral characteristics of the model at the macro level (Giacobbe et
al., 2023), thus providing a solid and reliable basis and guidance for
the optimization, performance improvement, and result interpretation of
the model.
The core
objective of this study is to explore the potential mechanisms of stroke
occurrence and construct an effective prediction system. It aims to
systematically screen the risk factors closely related to stroke
occurrence using the logistics regression analysis method, and then
build a prediction model and a prediction scoring table with high
reliability and accuracy. To enhance the interpretability and
transparency of the model, the SHAP method is introduced. By calculating
the contribution degree of each feature to the model's prediction
results, the complex relationships and action mechanisms within the
model are deeply analyzed, so that the output results of the model are
more interpretable and credible. Another core objective of our stroke
risk prediction model is to identify high-risk populations — individuals
not only threatened by stroke but also characterized by underlying
pathological mechanisms such as neuroinflammation and oxidative stress,
which have been demonstrated to be closely associated with the
development of depression and anxiety. It is expected that the results
of this study can provide a more solid and valuable scientific reference
basis for the formulation of early prevention strategies for stroke and
PSD, fill some gaps in the current research in this field, and promote
the further development and improvement of preventive medicine for
stroke and PSD.
This
study distinguishes itself from previous research through two key
innovations. First, it constructs a predictive scoring system
exclusively using readily available demographic and routine blood
markers, ensuring ease of implementation in primary care settings and
enabling layperson self-assessment without specialized medical training.
Second, the application of SHAP provides transparent, quantifiable
rankings of risk factors, offering mechanistic insights unattainable in
traditional black-box machine learning models.
More at link.
No comments:
Post a Comment