FreshRSS

🔒
❌ Acerca de FreshRSS
Hay nuevos artículos disponibles. Pincha para refrescar la página.
AnteayerTus fuentes RSS

Health Literacy and Unmet Needs in Patients With Multiple Sclerosis: A Cross‐Sectional Study

ABSTRACT

Aims

To identify a correlation between unmet needs and HL levels in people with Multiple Sclerosis (pwMS) and to evaluate how sociodemographic characteristics influence HL levels and unmet needs.

Design

A cross-sectional study.

Methods

The study was conducted using a questionnaire including the HLS19-Q12 to assess HL and the Long-term Unmet Needs in Multiple Sclerosis tool, which evaluates five domains (neuropsychological, ambulation, physical, interpersonal relationship, and informational) and identifies whether needs are met or unmet and the desire for support.

Results

Among the 116 participants included in the study, the overall HL level was sufficient. Mean scores across unmet needs domains were comparable. A significant difference in HL emerged in the informational domain, where participants reporting informational needs and a desire for support showed higher mean ranks. Although not significant, participants who acknowledged a need and expressed a desire for help showed higher mean ranks in HLS19-Q12 scores across several domains. No significant correlations were found between HL and unmet needs domains.

Conclusion

HL levels may enhance patients' ability to recognize and express needs without necessarily ensuring that these needs are met.

Implications for the Profession and/or Patient Care

Routine assessment of both HL and unmet needs may help healthcare professionals identify patients who recognize problems but lack the structural support to address them.

Impact

The impact of HL on need recognition and communication, together with the complexity and interconnectedness of unmet needs, highlights the need for healthcare systems to implement organizational, systemic, and multidimensional interventions aimed at promoting HL and effectively addressing patients' needs. Such strategies may support better disease management and improve quality of life in pwMS.

Reporting Method

This study was reported according to STROBE checklist.

Patient or Public Contribution

None.

Barriers and facilitators to service utilisation and management of sexually transmitted infections in India: a multicentric mixed-method approach study protocol

Por: Aggarwal · S. · Khandekar · J. · Banerjee · B. · Agarwal · P. · Paul · S. · Parashar · M. · Goel · A. D. · Lakshmi · P. V. M. · Datkhile · K. · Naik · B. N. · Goel · M. · Verma · V. · Rajan · S. · Das · C. · Nigam · K.
Introduction

Sexually transmitted infections (STIs) have emerged as significant public health concerns, imposing a substantial burden on both individuals and the healthcare system of the country. Additionally, STIs may also result in major extensive psychological consequences that profoundly affect individuals with STIs. Despite the government’s implementation of different initiatives aimed at addressing STI-related challenges, these conditions are associated with shame and stigma which act as barriers to the effective utilisation of healthcare services. The purpose of the present study is to generate evidence on barriers and facilitators to service utilisation and management of STIs in India.

Methods and analysis

Indian Council of Medical Research, New Delhi, is conducting a multi-centre study employing a mixed-method approach. The study involves different levels of healthcare systems, including both government and private healthcare facilities across seven sites in several states of India, including Maharashtra, Rajasthan, Punjab, Bihar, Uttar Pradesh and New Delhi. For the quantitative data, individuals seeking healthcare services related to STIs will be enrolled and assessed using a semi-structured pilot-tested questionnaire. In-depth interviews and focus group discussions will also be conducted with different stakeholders as per the standard guidelines of the qualitative method by the designated trained project staff. Descriptive and inferential statistics will be applied to the quantitative data, while the qualitative data will be analysed using a deductive approach with thematic content analysis.

Ethics and dissemination

The study protocol has been approved by the ethics review committees of all the participating sites individually. The findings from this study will be published in peer-reviewed journals and disseminated through scientific conferences and meetings among policy-makers and government agencies. AIIMS/IEC/2024/609; AIIMS/Pat/IEC/2024/1205; F. 7/BIOETHICS/AIIMS-RBL/APPROEM/2021/1; KIMSDU/IEC/11/2022; LHMC/IEC/2024/11; IEC/02/EX/2024; PGI/IEC/2024EIC000373.

Clinical relevance of intracranial stenosis as false-positive findings of a deep learning algorithm trained to detect large vessel occlusions: a retrospective cohort study of a supraregional stroke centre

Por: Jungmann · M. · Manschikow · S. · Hönning · A. · Spohn · F. · Sparenberg · P. · Mutze · S. · Goelz · L.
Objectives

This study aims to explore the ability to identify high-grade intracranial arterial stenosis (ICAS) by an artificial intelligence (AI) designed to detect large vessel occlusions (LVO) and the clinical relevance of these ‘false positive’ findings.

Design

We are presenting a retrospective cohort study.

Setting

The study was conducted at a supraregional stroke centre of an urban tertiary care provider.

Participants

Consecutive stroke cases treated between January 2023 and December 2023 of patients >18 years of both sexes and any ethnicity were eligible for inclusion. 934 patients (52.7% male) with a mean age of 71.7±13.6 years (25–101 years) were included.

Interventions

CT angiographies were analysed by a deep learning algorithm for LVO detection of the anterior circulation. AI results were compared with radiology reports and secondary focused evaluation.

Primary and secondary outcome measures

Diagnostic accuracies for ICAS detection by the AI were calculated.

Results

Primary reports identified 30 ICAS and nine additional ICAS were detected during secondary evaluation (incidence 4.2%). The sensitivity of radiology reports was 77% (95% CI 0.61 to 0.89), the specificity 99% (95% CI 0.98 to 1.00), negative predictive value (NPV) 99% (95% CI 0.98 to 0.99) and positive predictive value (PPV) 79% (95% CI 0.65 to 0.88). The AI identified 13 of 39 ICAS correctly. 18 false positive cases (neither LVO nor ICAS) were flagged by the AI. The sensitivity of the algorithm was 33% (95% CI 0.19 to 0.50), the specificity 98% (95% CI 0.97 to 0.99), the NPV 97% (95% CI 0.96 to 0.98) and PPV 42% (95% CI 0.28 to 0.58).

Conclusion

Detection of high-grade ICAS by an algorithm trained to identify LVO is per se a false positive finding but occurred in 13 of 39 cases. Dedicated training for ICAS might lead to a beneficial tool during the diagnostic work-up for ischaemic stroke.

Trial registration

German Register for Clinical Trials (DRKS: DRKS00034019 https://drks.de/search/de/trial/DRKS00034019).

Lived experiences, challenges and coping strategies of patients with spinal cord injury using intermittent catheterisation in Riyadh, Saudi Arabia: a qualitative study

Por: Abuzied · Y. · Al-Amer · R. · Abdul Halain · A. · Japar · S.
Objectives

This study explored the lived experiences, challenges and coping strategies of Arab male patients with spinal cord injury (SCI) who rely on intermittent catheterisation (IC) to manage neurogenic bladder.

Design

A descriptive qualitative approach was employed, with data analysed using a phenomenological framework.

Setting

Rehabilitation Hospital, King Fahad Medical City, Riyadh, Saudi Arabia.

Participants

Male patients with SCI undergoing rehabilitation and performing IC were included in the study. Although both male and female patients were approached to participate, all eligible female patients declined participation. During the recruitment process, some female patients informally expressed privacy concerns and discomfort related to discussing bladder management issues and genital care, which may have contributed to their decision to decline participation.

Results

10 male participants with SCI were recruited after eligible female patients declined participation. Three main themes, each with associated subthemes, emerged to reflect the participants’ experiences. Theme 1: Frequent use of IC in daily life, comprised four subthemes: (1) frequency of practice, (2) environmental and health-related challenges, (3) privacy during IC and (4) fluid intake and output. Theme 2: Cleanliness and general care included two subthemes: (1) catheter cleaning and (2) incontinence. Theme 3 focused on body image and sexuality. Cultural and social norms, including privacy concerns and sensitivities surrounding intimate care in the local context, played a significant role in shaping participants’ experiences and coping strategies.

Conclusions

IC was associated with challenges affecting multiple aspects of daily life among patients with SCI, including social interactions and body image. Participants described various coping strategies used to manage the physical and psychological demands associated with IC. These experiences appeared to be influenced by cultural considerations, including privacy, modesty and sensitivity surrounding urinary care within the local Saudi context.

Identifying social determinants of health subgroups and their associations with health outcomes in a prospective US adult COVID-19 cohort: an analysis of the INSPIRE registry

Por: Burrola-Mendez · Y. · Lin · E. · Parrish · C. · Hsu · C. · Hill · M. J. · Gottlieb · M. · Rising · K. L. · Wisk · L. E. · Gentile · N. L. · Geyer · R. E. · Weinstein · R. A. · Santangelo · M. · Gatling · K. · Dyal · J. W. · Elmore · J. G. · Rodriguez · R. M. · Watts · P. · Chen · J. · Diao
Objective

To identify subgroups with similar social determinants of health (SDOH) characteristics using latent class analysis (LCA) and examine their associations with physical and mental health, cognitive function and missed workdays at 3 and 6 months post-SARS-CoV-2 infection. We hypothesised that intersecting SDOH factors would differentially influence COVID-19-related health outcomes across subgroups.

Design

Prospective cohort study from the Innovative Support for Patients with SARS-CoV-2 Infections Registry (INSPIRE), with longitudinal data collection and cross-sectional analyses at baseline, 3-month and 6-month follow-ups.

Setting

Multicentre registry across eight US academic medical centres (Chicago, Dallas, Houston, Los Angeles, New Haven, Philadelphia, San Francisco and Seattle).

Participants

Adults aged ≥18 years, fluent in English or Spanish, with self-reported acute COVID-19 symptoms and a confirmed positive SARS-CoV-2 test within 42 days before enrolment (9 December 2020 to 12 August 2022), and access to an internet-connected device. Exclusions included incarceration, inability to provide informed consent, lack of confirmed SARS-CoV-2 infection or no internet access. Of 3791 eligible participants with complete baseline data, 2897 (76.4%) completed the 3-month follow-up and 2666 (70.3%) completed the 6-month follow-up; most were aged 18–49 years (74–75%), female (66–67%), white (86.6–87.5%) and non-Hispanic (86.6–87.5%).

Outcome measures

Prespecified primary outcomes were physical and mental health (Patient-Reported Outcomes Measurement Information System (PROMIS)-29 V.2.1 T-scores for depression, anxiety, fatigue, sleep disturbance, pain interference, physical function and social participation), cognitive function (PROMIS Cognitive Function Short Form 8 T-scores) and missed workdays due to illness (binary: >1 week vs ≤1 week, from a single-item survey). All measures were self-reported and collected at baseline, 3 months and 6 months; no changes from protocol.

Results

LCA identified a 4-class model as optimal (lowest Bayesian Information Criterion (BIC) after evaluating 1–7 class models; significant demographic differences (2 p

Conclusions

In this US prospective cohort, SDOH-based subgroups showed persistent disparities in health outcomes post-SARS-CoV-2 infection. Findings highlight the urgent need for intersectional approaches to address systemic inequities in post-COVID-19 recovery.

Trial registration number

NCT04610515.

Prevalence of PRISm and COPD and associated factors in a university medical centre spirometry unit: a cross-sectional analysis

Por: Akiki · Z. · Khoueiry · E. · Smayra · E. · Nader · A. · El Teress · K. · Safi · C. · El Ashkar · I. · Majed · A. · Fawaz · A. · Salameh · P. · Gaspard · D.
Objectives

Preserved Ratio Impaired Spirometry (PRISm) is a new spirometric entity defined in international guidelines, associated with overall worse outcomes. It remains unclear whether this represents a distinct entity or an early phase of multiple other diseases, such as chronic obstructive pulmonary disease (COPD) and restrictive lung diseases. There is a notable scarcity of data on PRISm, particularly in Lebanon. This study aimed to evaluate the prevalence of PRISm and COPD, and their associated factors, among individuals aged 40 years and above who underwent spirometry in a single university medical centre between 2022 and 2024.

Setting

Outpatient Pulmonary Function Tests Laboratory at a Lebanese university medical centre.

Participants

All individuals aged 40 years or older who performed spirometry between 2022 and 2024

Methods

A retrospective analysis of pulmonary function tests (PFTs) and demographics was performed. Patients were classified based on the spirometry patterns that are consistent with COPD (forced expiratory volume in the first second (FEV1)/forced vital capacity (FVC)1/FVC≥0.7 and FEV11/FVC≥0.7 and FEV1≥80%). A small number of PFTs did not meet the above criteria and were classified as ‘others’; they were excluded from the main analysis but retained for descriptive estimation of PRISm and COPD prevalence over the past 3 years. The prevalence and associated risk factors of PRISm and COPD were assessed. Descriptive, bivariate and multinomial regression models were performed using IBM’s Statistical Package for the Social Sciences V.29.

Results

A total of 698 PFTs were performed for 639 patients. The prevalence of PRISm and COPD in the centre between 2022 and 2024 was 11% and 17%, respectively. Compared with normal PFTs, subjects with PRISm were older (adjusted OR; aOR (95% CI)=1.03 (1.002 to 1.05); p=0.03) and more likely to be ex-smokers (aOR=2.19 (1.12 to 4.30); p=0.022); patients with COPD were older (aOR 1.09 (1.07 to 1.12); p

Conclusion

These findings highlight PRISm as a potentially relevant pattern within chronic airway disease. Within the context of Sustainable Development Goal 3 on non-communicable diseases, they underscore the importance of identifying this subgroup for closer clinical attention. Further longitudinal and multicentre studies are needed to better understand the clinical significance of PRISm and its relationship to chronic airway diseases.

Outcomes of invasive mechanical ventilation in critically ill patients with interstitial lung disease: protocol for a systematic review and meta-analysis

Por: Kola · N. · Parker · R. · Hall · A. · Spencer · L. G. · Fletcher · S. V. · Welters · I. D. · Johnston · B. W.
Introduction

Interstitial lung diseases (ILDs) represent a heterogeneous group of disorders, which have in common persistent inflammation and/or pulmonary fibrosis, involving mainly but not exclusively the interstitium. This results in restrictive ventilatory physiology and limited respiratory reserve. Patients with ILD can have frequent exacerbations of their disease, with subsequent acute respiratory failure that may require admission to the intensive care unit (ICU). The diagnosis and management of ILD in the ICU presents unique challenges due to the paucity of evidence supporting survival benefits of organ support in this cohort of patients.

Methods and analysis

This systematic review will be reported in accordance with the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) statement, and the protocol will follow the Preferred Reporting Items for Systematic Review and Meta-Analysis Protocols (PRISMA-P) guideline. MEDLINE, Embase, Emcare and CENTRAL will be searched for studies published from inception to 2026, involving adult patients with ILD requiring invasive mechanical ventilation (IMV), with or without comparison to non-invasive respiratory support such as high-flow oxygen, non-invasive ventilation (NIV), continuous positive airway pressure or bilevel positive airway pressure. Eligible studies will include randomised controlled trials and observational studies (cohort and case–control) in adults with ILD and acute respiratory failure requiring IMV in the intensive care setting. Case series with fewer than 10 patients, non-human or in vitro studies and studies involving perioperative lung transplant or lung cancer as the primary diagnosis will be excluded. The primary outcomes assessed will be in-hospital and 1-year mortality, and secondary outcomes will include ventilator-free days, ICU and hospital length of stay, NIV failure, reintubation and postdischarge respiratory outcomes where available. Where feasible, meta-analysis will be conducted using a random-effects model. Heterogeneity will be assessed using the I² statistic. Prespecified subgroup analyses will be performed, including ILD subtype (eg, idiopathic pulmonary fibrosis (IPF) vs non-IPF), presence of pulmonary hypertension, timing of IMV initiation (early vs late), baseline lung function (forced vital capacity ≥50% vs

Ethics and dissemination

This systematic review will be based on published data, and as such, no ethical approval is required. Findings from this study will be disseminated through peer-reviewed publications as well as presentations in healthcare-based settings.

PROSPERO registration number

CRD420251265836.

Feasibility of NIV-NAVA as a primary respiratory support and its clinical impacts in a targeted group of preterm infants: protocol for a prospective observational study

Por: Cho · H. · Jung · Y. H. · Park · J. · Yang · H. J. · Kim · M. J. · Lee · J.
Introduction

Non-invasive neurally adjusted ventilatory assist (NIV-NAVA) is a promising respiratory support method for avoiding invasive mechanical ventilation in neonatal intensive care units (NICUs). However, its effectiveness and safety have not been widely established through clinical evidence. In this study, we aim to evaluate the feasibility of NIV-NAVA as a primary respiratory support method after birth and its effects on short-term clinical outcomes and long-term neurodevelopment in preterm infants.

Methods and analysis

In this prospective multicentre observational study, 230 preterm infants will be recruited after birth. This study will include preterm infants born between 27+0 and 31+6 weeks of gestation who require respiratory support within the first 48 hours after birth. NIV-NAVA will be initiated as primary respiratory support either immediately after birth or during the early NICU stay, with settings adjusted according to each infant’s clinical condition. Discontinuation of NIV-NAVA or transition to continuous positive airway pressure or high-flow nasal cannula will be performed based on clinical stability. A less invasive surfactant administration method will be used for infants with respiratory distress syndrome to avoid intubation whenever possible. Infants intubated at birth will be extubated to NIV-NAVA as early as is clinically feasible. Invasive ventilation may be applied if clinical deterioration occurs. The rate of NIV-NAVA failure, duration of non-invasive and invasive ventilation, rate of bronchopulmonary dysplasia and clinical outcomes, such as air leak, patent ductus arteriosus, intraventricular haemorrhage and retinopathy of prematurity, will be measured. The neurodevelopmental outcomes of infants will be assessed for up to 3 years.

Ethics and dissemination

The Institutional Review Board (IRB) of Korea University Anam Hospital (2024AN0554) and Seoul National University Bundang Hospital (IRB No. B-2507-984-304) approved this study. The results will be disseminated through scientific conferences and publications.

Trial registration number

NCT06786039 registered on 14 January 2025.

Musculoskeletal surgeons use mixed reasoning rather than pure Bayesian strategies in clinical practice

by Robert Parisien, Alexander Drost, Amin Razi, Sina Ramtin, David Ring, Stein J. Janssen

Objectives

To inform efforts to promote regular and normalized Bayesian reasoning, we studied factors associated with the degree to which surgeons use Bayesian reasoning to navigate uncertainty across different clinical scenarios.

Methods

Science of Variation Group members (153; 58% North America, 30% Europe, 69% over 15 years of experience) completed an online survey reading 8 scenarios of test and treatment decisions and chose one of 4 answer options with higher scores indicating more Bayesian reasoning. Internal consistency of the survey was assessed using Cronbach alpha.

Results

The average Bayesian reasoning score across all scenarios was 3.0 (IQR 2.7–3.2) on a 4-point scale, indicating a relative context-dependent variability. Completely non-Bayesian reasoning was selected least often (8.6%, 90 of 1,044) and fully Bayesian reasoning represented 29% (301 of 1,044) of responses. Most surgeons showed mixed patterns (defined as reasoning in which prior probability is acknowledged but underweighted, without explicit probabilistic updating): 85% (121 of 142) used fully Bayesian reasoning at least once (121 of 142) while 42% (60 of 142) used completely non-Bayesian reasoning at least once. The Cronbach alpha was 0.43 suggesting the scenarios measured different aspects of clinical reasoning rather a unified construct.

Conclusions

The finding that surgeons use relatively context-dependent reasoning suggests an opportunity for surgeons to develop and practice Bayesian reasoning strategies both in training programs and in practice.

The Parent Support Team Programme: A Mixed‐Methods Evaluation of an Early Intervention‐Focused Child and Family Health Nursing Programme

ABSTRACT

Aims

The Parent Support Team (PST) is an intensive early intervention home visiting programme delivered by child and family health nurses to families with infants aged 0–6 months experiencing psychosocial and health vulnerabilities. In contrast, mainstream services provide universal clinic-based care and scheduled developmental checks. This mixed-methods study aimed to: (1) describe demographic and psychosocial characteristics, service activity and well-baby check attendance among PST clients compared with mainstream service clients; (2) evaluate changes in maternal depressive symptoms following PST engagement; and (3) explore client experiences, including perceived outcomes and facilitators and barriers to change.

Design

Convergent parallel mixed-methods study.

Methods

Retrospective data were extracted from electronic medical records for PST clients (909 mothers; 1038 children) and mainstream service clients (17,707 mothers; 21,764 children) between August 2019 and December 2022. Quantitative analyses described demographics, psychosocial characteristics, service use and maternal depressive symptoms. PST client experience surveys (166 mothers) were analysed using descriptive statistics and thematic analysis.

Results

PST clients demonstrated greater psychosocial complexity and higher maternal depressive symptoms at entry than mainstream clients. PST mothers had more frequent service contacts and maintained stronger engagement with services after discharge. The proportion of mothers with clinically significant depressive symptoms decreased following programme participation. Survey findings indicated improved parenting confidence and practical skills. Positive outcomes were attributed to nurse qualities, opportunities to discuss concerns, a holistic care approach and the service model. Reported barriers included accessibility, scope of education topics and communication challenges.

Conclusion

The PST programme effectively engages vulnerable families, supports maternal mental health and promotes sustained connection with child and family health services.

Impact

Intensive early intervention home visiting programmes may improve outcomes for families with complex needs and warrant broader implementation.

Reporting Method

SRQR guidelines were followed.

Patient or Public Contribution

None.

Towards precision vibration therapy for poststroke balance: a domain-specific systematic review and meta-analysis protocol

Por: Kim · J.-D. · Park · S.-R. · Chun · J. M. · Seok · J.-W. · Seo · J.-W.
Introduction

Balance impairment is a major contributor to falls, reduced mobility and loss of independence in individuals after stroke. Vibration therapy (VT) has been increasingly investigated as a non-invasive intervention to improve postural control and balance in individuals with stroke. However, the reported effects remain inconsistent, and a comprehensive synthesis focusing specifically on balance-related outcomes is lacking. This review aims to evaluate the effectiveness of VT on balance function and to explore the influence of intervention characteristics and outcome constructs.

Methods and analysis

This protocol follows the Preferred Reporting Items for Systematic Review and Meta-Analysis Protocols (PRISMA-P) guidelines. Randomised and non-randomised controlled studies will be systematically identified from major electronic databases. Balance-related outcomes will be categorised using a predefined construct-based framework (eg, static postural control, dynamic balance, limits of stability, functional mobility and gait performance). Meta-analyses will be conducted only within conceptually homogeneous constructs; otherwise, findings will be synthesised narratively. Risk of bias will be assessed using Cochrane Risk of Bias 2 and Risk of Bias in Non-randomised Studies of Interventions. Random-effects models will be applied where appropriate, and meta-regression analyses will be exploratory.

Ethics and dissemination

Ethical approval is not required because this study will use only previously published data and will not involve individual-level human participant data. The findings will be disseminated through publication in a peer-reviewed journal and presentation at relevant academic conferences.

PROSPERO registration number

CRD420251110102.

Reducing the therapeutic vacuum: a qualitative study learning from experiences of care delivery during terror attacks in the UK over the past 20 years

Por: Stephens · T. J. · Dave · D. · Hughes · A. H. · Swift · B. · Glasgow · S. M. · Fothergill · R. · Grier · G. · Brohi · K. · Park · C. L.
Objectives

The complex and dynamic care context of terror attacks must be better understood to reduce deaths. This study was designed to understand the tension between saving lives and maximising safety for emergency responders attending active terror incidents.

Design, setting and participants

Qualitative study exploring the experience of survivors and emergency responders (armed and unarmed police, paramedics, doctors and fire officers) present in the hot (unsafe) zone of five major terror attacks in the UK since 2000. We used reflexive thematic data analysis to build qualitative case studies, comparing similarities and tensions between perspectives of different participant groups.

Results

In our analysis of over 2000 min of interview data from 26 participants, we found a common view that the priority during a terror-related mass casualty event was to save lives. However, responder groups maintained distinct mental models that shaped their operational priorities regarding treatment for those injured within the hot zone. All responders expressed willingness to take self-assessed risks to save lives, but better interagency communication was noted to be required to achieve this safely. All responders felt it was vital to have experienced health professionals present to triage and facilitate urgent treatment and extraction decisions. Armed police commanders had dual responsibilities to achieve rapid care delivery while preventing further terrorist-inflicted injuries. Operationally, this was perceived as leading to a lack of shared mental models between responders regarding what is ‘unsafe’ due to zoning, rather than communication of risk, potentially delaying vital care delivery. There were mixed survivor perspectives regarding the risks that responders should be exposed to, but broad agreement that there was a notable absence of health professionals present in the hot zone during the immediate aftermath of attacks.

Conclusion

There is strong professional and public support for improving care delivery, including potential hot zone working, to minimise the therapeutic vacuum in active terrorist attacks. Better risk communication and better shared mental models are necessary to balance responder risk with care delivery to maximise lives saved as safely as possible.

Deep learning-based arterial waveform analysis for predicting postoperative cerebrovascular events in pediatric patients with Moyamoya disease

by Jung-Bin Park, Youmin Shin, Jihun Kim, Yoon Jung Kim, Seung-Bo Lee, Eun-Hee Kim, Joo Whan Kim, Seung-Ki Kim, Hee-Soo Kim, Young-Gon Kim

Background

Postoperative cerebrovascular events, including transient ischemic attacks, infarctions, and hemorrhages, remain a significant concern in pediatric patients with Moyamoya disease (MMD)undergoing surgical revascularization. This study aimed to develop an explainable deep learning-based classification model using intraoperative arterial blood pressure (ABP) waveform analysis for postoperative cerebrovascular events in pediatric patients undergoing surgery for MMD, with exploratory analysis of associated waveform-derived physiologic features.

Methods

This retrospective study included 181 pediatric patients (≤18 years) who underwent revascularization surgery for MMD, with an independent temporal holdout cohort of 79 patients reserved for validation. ABP signals were preprocessed using detrending, pulse segmentation, and normalization, then converted into image representations for deep learning classification. Various convolutional neural network (CNN) models, including ResNet50, ResNet34, DenseNet121, VGG16, and VGG19, were evaluated against Vision Transformer (ViT) architectures. Multiple image transformation methods were tested, and Grad-CAM analysis and statistical comparisons of waveform-derived physiologic features were conducted between patients with and without postoperative cerebrovascular events.

Results

The optimal model configuration achieved the best performance using raw pulse waveforms with three consecutive pulses per image. CNN-based models outperformed ViT-based models, with the highest internal classification performance observed using raw pulse waveforms (AUROC = 0.772, SD = 0.070).In the independent temporal validation cohort, the model achieved an AUROC of 0.738 ± 0.011 at the patient level. Grad-CAM visualization highlighted the diastolic runoff phase as a region of interest for classification. Four waveform-derived features related to arterial compliance were significantly associated with postoperative cerebrovascular events (p  Conclusions

In this study, CNN-based deep learning models demonstrated the feasibility of predicting postoperative cerebrovascular events from intraoperative ABP waveforms, with diastolic runoff dynamics emerging as a potentially relevant physiologic pattern. These findings are exploratory and require prospective multi-center validation before clinical application.

❌