Risultati per: Progressi nel trattamento della psoriasi: review

Introduction
Paracetamol, the most used analgesic medicine in the world, is considered a safe treatment, but when overdosed, it can be fatal. Evidence suggests that despite sales legislations, paracetamol overdose still accounts for around 100 000 accident and emergency visits and 50 000 hospital admissions per year in the UK. This systematic review aims to describe the possible factors linked to paracetamol overdoses (intentional and/or accidental) in the adult and child populations in the UK and the subgroups of the population that are at higher risk and identify any preventative interventions.

Methods and analysis
This review will be carried out in accordance with the Preferred Reporting Items for Systematic Review and Meta-analyses (PRISMA) guidance. Literature searches will be performed using six bibliographic databases: MEDLINE via PubMed, EMBASE, SCOPUS, PsycINFO, the Cochrane Library and PROSPERO register. Grey literature and social media will also be searched, and article reference lists are reviewed. Studies included will be in English with populations in the UK from 1998 onwards, experiencing paracetamol overdose (intentional or accidental), with no age restriction. Title and abstract screening and full-text review of included articles will be performed by two independent reviewers (with a third member to resolve disagreement). The risk of bias will be assessed using the JBI critical appraisal checklist. The quality of any systematic reviews included will be assessed using the AMSTAR 2 tool or the Mixed Methods Appraisal Tool (MMAT), as appropriate. It is anticipated to adopt a narrative synthesis of the findings via a thematic analysis. Meta-analysis and subgroup analysis will be considered if data are available.

Ethics and dissemination
Ethics approval is not required for this work since no data will be collected. Results will be disseminated through a peer-reviewed publication and local as well as national conference presentations; and a range of creative and inclusive methods and formats to inform and educate patients and the community.

PROSPERO registration number
CRD42024555406.

Objectives
Women diagnosed with BRCA1/2 mutations face significantly elevated lifetime risks of breast and ovarian cancer. Due to the distinctive biopsychosocial implications of a BRCA diagnosis, the care trajectory for these women is highly personalised, yet their care needs frequently remain unmet. The aim was to provide a first overview of the evidence of women’s experiences with person-centred care (PCC) within BRCA care and their needs for further PCC implementation.

Design
A scoping review, guided by the Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews, was conducted.

Data sources
Medline, Embase, Web of Science Core Collection, Cochrane Central Register of Controlled Trials, CINAHL Plus and Google Scholar were searched for literature published between January 2004 and February 2024.

Eligibility criteria
Peer-reviewed, primary studies on BRCA and PCC using quantitative, qualitative and mixed-methods designs were eligible. The criteria were iteratively refined to include publications based on samples that were >80% female and >80% BRCA positive.

Data extraction and synthesis
Titles and abstracts were screened with ASReview, a validated AI-driven tool. Data on PCC evidence and needs were extracted based on the eight Picker Principles of PCC and synthesised by describing themes within each principle.

Results
Of the 3801 articles identified as potentially relevant, 18 were included in the review. PCC needs were more prevalent than evidence of their implementation. Most of women’s positive experiences with PCC focused on ‘clear information, communication and support for self-care’, while limited to no evidence existed for other principles. The highest needs were found for increased ‘emotional support, empathy and respect’, ‘attention to physical and environmental needs’, and ‘clear information, communication and support for self-care’. All articles reported demands for more holistic, yet personalised care, though PCC was not mentioned explicitly.

Conclusions
This review suggests a person-centred approach is relevant to improving the standard of BRCA care for women. The first evidence of women’s experiences with PCC demonstrates how care delivered with sensitivity and respect for individual backgrounds can support women throughout their BRCA trajectory. Yet, substantial unmet needs remain among female BRCA carriers, highlighting the importance of further research and PCC implementation to enhance the quality of postdiagnostic care.

Objectives
Cough occurring in patients with renal cell carcinoma (RCC) was first described in 1935 and is a frequently discussed symptom on patient forums. We aimed to systematically review the available evidence to explore the prevalence and risk factors for persistent cough in patients diagnosed with RCC to establish whether cough could be a presenting symptom of RCC.

Design
This epidemiological systematic review used the Preferred Reporting Items for Systematic Reviews and Meta-Analyses statement 2020.

Data sources
Medline, Embase, Science Citation Index, The Cochrane Library, ClinicalTrials.gov and the WHO trials register were searched without language restrictions until 1 June 2023.

Eligibility criteria for selecting studies
We included articles of all study designs reporting cough in patients (18 years or older) with RCC attributed to the disease itself or to treatment.

Data extraction and synthesis
Data from included articles was extracted using a preprepared and piloted form, and quality assessment was conducted independently by two authors. The risk of bias was assessed in studies other than case reports or case series using the critical appraisal instrument for studies reporting prevalence data. Narrative techniques were used for data analysis and, where appropriate, meta-analysis using a fixed-effects model was performed.

Results
Of 509 studies screened, 105 full-text articles were assessed, with 46 papers subsequently excluded, resulting in 59 analysed in depth. There were 105 patients with RCC reported as having a cough due to the disease itself within 30 case reports and 8 case series. When present, most coughs were described as persistent and dry in nature. The cause of cough was attributed to various aetiologies including pulmonary and endobronchial metastasis and paraneoplastic syndromes. Studies reporting patients with RCC developing a cough because of systemic treatment were heterogeneous. Two studies with 238 patients on temsirolimus and 230 on interferon-α (IFN-α) were suitable for meta-analysis using a fixed-effects model. Patients on temsirolimus were more likely to develop a cough than those on IFN-α (OR 1.95 with a 95% CI of 1.05 to 3.63, overall effect Z=2.12 (p=0.03), I2=0%).

Conclusion
Cough can occur in patients with RCC, as part of the disease pathogenesis, as an adverse effect of systemic treatment or due to unrelated causes such as pre-existing conditions (eg, asthma). Further research is required to determine the true prevalence and cause and to assess whether cough could be a presenting symptom for RCC.

PROSPERO registration number
CRD42022302962.

Introduction
The incidence of severe natural disasters has been increasing worldwide. The residents of long-term care facilities (LTCFs) are particularly vulnerable to such events. Therefore, promoting disaster preparedness among LTCF stakeholders is urgent. However, the optimal preparedness process remains unclear. To close this gap, we use a realist review (RR) to promote an understanding of under what circumstances and what works for promoting the disaster preparedness among LTCF stakeholders and develop theories for the process.

Methods and analysis
RR will be guided by the Realist and Meta-Narrative Evidence Synthesis: Evolving Standard. The following five steps will be employed: (1) literature review and search for evidence, (2) study selection, (3) data extraction, (4) data synthesis and (5) development of the initial programme theory (IPT). Evidence will be searched using MEDLINE, CINAHL, PsycINFO, Web of Science, Cochrane Library, Scopus and ICHUSHI (a Japanese database). Grey literature and citation tracking will also be used. Documents of any design or publication type will be included. The study selection, coding and synthesis will be conducted independently by two authors. An IPT will be developed in the Context–Mechanism–Outcome configuration to understand how to promote disaster preparedness among LTCF stakeholders. The developed IPT will be verified by experts or stakeholders to enhance its validity.

Ethics and dissemination
Ethical approval will not be required because this is a review of published literature. The results will be disseminated at scientific conferences and peer-reviewed journals. The developed IPT will be used in subsequent research and iteratively tested or refined to better explain under what circumstances and what works for promoting disaster preparedness among LTCF stakeholders.

Registration details
This protocol has been registered at the Open Science Framework https://doi.org/10.17605/OSF.IO/J4TU6.

Introduction
Breast cancer is the fifth-leading cause of cancer-related mortality in women globally. Asia has a lower overall incidence of breast cancer compared with global incidence rates. Unique dietary habits observed in South Asians contribute significantly to low incidence rates. This review aims to explore the literature on the association between dietary habits and breast cancer among South Asian women.

Methods and analysis
A systematic search will be conducted using electronic databases MEDLINE, EMBASE, CINAHL, Web of Science and Scopus. Additional articles will be searched in Google Scholar and a reference list of the selected articles. Review questions will be framed into different components according to the PICOS (population, intervention, comparator, outcomes, studies) framework. Women above 18 years of age who are diagnosed with breast cancer in the South Asian region will be the population of interest. Only the studies reported in the English language will be included. Both title and abstract screening and full-text screening will be done by two independent reviewers. The quality of included studies will be assessed using the Joanna Briggs Institute critical appraisal tools. Based on the findings, a random-effects meta-analysis will be performed if outcomes are homogeneous, or a narrative synthesis will be conducted if outcomes are heterogeneous.

Ethics and dissemination
This study does not require ethics approval, as it is based on published documents. The findings of this study will be shared with a broader audience through scientific channels including publication in open-access journals and presentations at both national and international forums.

PROSPERO registration number
CRD42023464682.

Introduction
Several studies have addressed the use of pressure injury preventive measures and bundles for hospitalised patients. However, there is a gap in research regarding the use of pressure injury preventive measures and bundles in the home environment. This scoping review aims to identify, explore and map the international literature on pressure injury preventive measures and bundles in the home and community environments.

Methods and analysis
The Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews will be used to guide the reporting of this scoping review. The Joanna Briggs Institute guide will inform the methods. A modified version of the Preferred Reporting Items for Systematic Review and Meta-Analysis Protocols will be used to guide the reporting of this scoping review protocol. An initial search was carried out in July 2024. The search will be conducted in electronic databases such as LILACS, SciELO, Scopus, PubMed, Embase, CINAHL, Cochrane Library and Web of Science. The search will be restricted to studies in English, Portuguese and Spanish, with no time restriction. Additional literature will be retrieved by reviewing the reference lists of the selected studies based on their titles. Two independent reviewers will carry out the data extraction process. Essential details, including the author, references and findings pertinent to the review questions, will be collected. The findings will be displayed through graphs, tables and figures, supplemented by a narrative summary.

Ethics and dissemination
As this review will be conducted using secondary data, ethical approval is not required. Results will be shared with the international scientific community through conference presentations and publication in a high-impact journal.

Study registration
This scoping review was registered with the Open Science Framework registry (osf.io/m5gvn) on 8 August 2024.

Objective
This study aimed to systematically evaluate published predictive models for dental caries in children and adolescents.

Design
A systematic review and meta-analysis of observational studies.

Data sources
Comprehensive searches were conducted in PubMed, Web of Science, Cochrane Library, Cumulative Index to Nursing and Allied Health Literature, Embase, China National Knowledge Infrastructure, Wanfang Database, China Science and Technology Journal Database (VIP) and SinoMed for relevant studies published up to 18 January 2024. The search focused on caries prediction models in children and adolescents.

Eligibility criteria
Eligible studies included observational research (cohort, case–control and cross-sectional designs) that developed risk prediction models for dental caries in children and adolescents aged ≤18 years. Each model was required to include a minimum of two predictors. Studies were excluded if they were not available in English or Chinese, primarily focused on oral microbiome modelling, or lacked essential details regarding study design, model construction or statistical analyses.

Results
A total of 11 studies were included in the review. All models demonstrated a high risk of bias, primarily due to inappropriate statistical methods and unclear applicability resulting from insufficiently detailed presentations of the models. Logistic regression, random forests and support vector machines were the most commonly employed methods. Frequently used predictors included fluoride toothpaste use and brushing frequency. Reported area under the curve (AUC) values ranged from 0.57 to 0.91. A combined predictive model incorporating six caries predictors achieved an AUC of 0.79 (95% CI: 0.73 to 0.84).

Conclusions
Simplified predictive models for childhood caries showed moderate discriminatory performance but exhibited a high risk of bias, as assessed using the Prediction Model Risk of Bias Assessment Tool (PROBAST). Future research should adhere to PROBAST guidelines to minimise bias risk, focus on enhancing model quality, employ rigorous study designs and prioritise external validation to ensure reliable and generalisable clinical predictions.

PROSPERO registration number
CRD42024523284.

Objectives
There is a need to better inform clinicians and decision-makers in primary or community care settings on selecting the appropriate point-of-care tests (POCTs) for screening purposes (as a part of the NHS Health Check Programme). Here we provide an overview of the published analytic validity and diagnostic accuracy studies on POCTs for measuring blood lipids that are available on the UK market to determine whether they meet the accuracy specifications based on the 1995 US National Cholesterol Education Program (NCEP) recommendations.

Design
Rapid review of analytical validity and diagnostic accuracy studies.

Data sources
On 12 May 2023, Medline and Embase were searched. Google Scholar was manually scrutinised to identify additional studies. Key article reference lists were also hand-searched.

Eligibility criteria
We included analytical validity and diagnostic accuracy studies that compared POCT to laboratory testing (or another POCT) performance for measuring at least total cholesterol (TC) and high-density lipoprotein cholesterol (HDL-C).

Data extraction and synthesis
Identified studies were independently reviewed by two researchers using standardised methods of screening. Where necessary, conflicts were resolved by a third reviewer. Title and abstract as well as full texts were screened using prespecified inclusion and exclusion criteria. The quality of identified studies was assessed using QUADAS-2 for diagnostic accuracy studies and a modified quality appraisal tool for studies of diagnostic reliability (QAREL) for analytical validity studies. We assessed the quality of analytical and diagnostic accuracy studies and compared the accuracy of the POCTs for TC, triglyceride (TG), HDL-C and low-density lipoprotein cholesterol (LDL-C) against NCEP standards for mean per cent bias, coefficient of variation or total error. We narratively synthesised analytical and clinical validity evidence from retrieved studies.

Results
This study examined analytical and diagnostic accuracy evidence for the selected POCTs. Through the review of 22 studies, 6 POCTs were identified. All retrieved studies were analytical validity assessments, while five of them also reported diagnostic accuracy information. The majority of evidence focused on Cholestech LDX, CardioChek PA and Accutrend Plus. Evidence of between and within-study heterogeneity was found. Precision measures often showed systematic differences between the POCT and reference standards. Most devices, except for Elemark, met at least one NCEP standard for either TC, TG, HDL-C, or LDL-C.

Conclusions
We found that evidence for two of the devices mostly met the requirements of the NCEP standard of evidence for bias and precision and could be recommended to general practitioners to use in the NHS Health Check programme. These were the Cholestech LDX and the Cobas b101 system.

Objectives
The COVID-19 pandemic highlighted the deterioration of nurses’ working conditions and a growing global nursing shortage. Little is known about the factors, strategies and interventions that could improve nurse retention in the peri- and post-COVID-19 period. An improved understanding of strategies that support and retain nurses will provide a foundation for developing informed approaches to sustaining the nursing workforce. The aim of this scoping review is to investigate and describe the (1) factors associated with nurse retention, (2) strategies to support nurse retention and (3) interventions that have been tested to support nurse retention, during and after the COVID-19 pandemic.

Design
Scoping review.

Data sources
This scoping review was performed according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews. MEDLINE, Embase, CINAHL and Scopus databases were searched on 17 April 2024. The search was limited to a publication date of ‘2019 to present’.

Eligibility criteria
Qualitative, quantitative, mixed-methods and grey literature studies of nurses (Registered Nurse (RN), Licenced Practical Nurse (LPN), Registered Practical Nurse (RPN), Publlic Health Nurse (PHN), including factors, strategies and/or interventions to support nurse retention in the peri- and post-COVID-19 period in English (or translated into English), were included. Systematic reviews, scoping reviews and meta-syntheses were excluded, but their reference lists were hand-screened for suitable studies.

Data extraction and synthesis
The following data items were extracted: title, journal, authors, year of publication, country of publication, setting, population (n=), factors that mitigate intent to leave (or other retention measure), strategies to address nurse retention, interventions that address nurse retention, tools that measure retention/turnover intention, retention rates and/or scores. Data were evaluated for quality and synthesised qualitatively to map the current available evidence.

Results
Our search identified 130 studies for inclusion in the analysis. The majority measured some aspect of nurse retention. A number of factors were identified as impacting nurse retention including nurse demographics, safe staffing and work environments, psychological well-being and COVID-19-specific impacts. Nurse retention strategies included ensuring safe flexible staffing and quality work environments, enhancing organisational mental health and wellness supports, improved leadership and communication, more professional development and mentorship opportunities, and better compensation and incentives. Only nine interventions that address nurse retention were identified.

Conclusions
Given the importance of nurse retention for a variety of key outcomes, it is imperative that nursing leadership, healthcare organisations and governments work to develop and test interventions that address nurse retention.

Our approach enhances the understanding of global variation in rotavirus vaccine performance and can be used to inform predictions of the potential impact of rotavirus vaccines for countries that have yet to introduce them. Higher-quality data on predictor variables and broader regional representation in vaccine trials are required for more robust vaccine performance estimates.

Introduction
Self-harm behaviour is commonly observed in adolescents and can serve as a potential warning sign for suicide. It is prevalent among adolescents in sub-Saharan Africa, with a median lifetime prevalence of 10.3%. The negative impacts of adolescent self-harm include poor educational performance, impaired physical functioning and unemployment. Despite its significance, there is limited knowledge and intervention programmes addressing self-harm in sub-Saharan Africa.

Objective
The proposed scoping review aims to identify and analyse the current literature on the types and factors associated with self-harm among adolescents in sub-Saharan Africa. The findings will guide future systematic reviews and qualitative and quantitative studies that will help address the knowledge gap. Findings from this study will also inform strategies to address this critical issue.

Methods
This scoping review will follow the Joanna Briggs Institute methodology. Studies on self-harm among adolescents between ages 10 and 19 years in any sub-Saharan African country done between 2000 and 2024 will be included. The literature search will be conducted across the following databases: Embase (Ovid), Medline (Ovid), PsycINFO (Ovid), PubMed, African Journals Online and African Index Medicus (WHO). Additional relevant articles will be searched in grey literature databases such as Google Scholar, conference proceedings, PhD theses and dissertations. Two reviewers will conduct title and abstract screening as well as full-text screening, with any conflicts resolved by a third independent reviewer.

Ethics and Dissemination
Ethics approval is not required for this scoping review protocol. The review process and findings will be shared with and informed by relevant knowledge users. The findings of this review will be shared globally through an open-access peer-reviewed publication and conference presentations. The results will provide new insights for future systematic reviews and both quantitative and qualitative studies. Additionally, they will inform policies and intervention programmes for self-harm among adolescents in sub-Saharan Africa.

Objective
The objective of this study is to perform a comprehensive systematic review and meta-analysis of the accuracy of signs, symptoms and case definitions for the diagnosis of influenza.

Design
Systematic review and meta-analysis of diagnostic accuracy.

Setting
Inpatient or outpatient setting.

Participants
Three databases (PubMed, CINAHL and EMBASE) were searched through February 2024 for studies of clinical diagnosis of influenza using prospective data collection and a high-quality reference standard. Data were abstracted by researchers working in parallel and resolving discrepancies by discussion.

Primary and secondary outcome measures
Quality was assessed using QUADAS-2. Summary estimates (or ranges) of sensitivity and specificity, likelihood ratio (LR), the Youden Index and the area under the receiver operating characteristic curve were calculated.

Results
The final meta-analysis included 67 studies, each with between 119 and 155 866 participants. Most were judged to be low risk of bias. The signs and symptoms with the highest overall accuracy for all studies based on the Youden Index were any fever (0.32), overall clinical impression (0.28), coryza (0.25), cough and fever (0.25), and measured fever (0.25). Accuracy varied widely by age group. Only the overall clinical impression had a positive LR greater than 2.0. Cough was the most sensitive finding (0.92) with a negative LR of 0.28 in adults. The absence of any fever also had a low negative LR (0.30). The Centers for Disease Control and Prevention (CDC) definition of influenza-like illness (ILI) had good specificity but poor sensitivity in adults, while in infants, it had good sensitivity but widely varying specificity. The European CDC and WHO case definitions for ILI had modest sensitivity and specificity.

Conclusions
Individual signs and symptoms, their combinations, and ILI case definitions have very limited accuracy for identifying persons with influenza. More accurate surveillance and diagnosis will require the development and validation of accurate risk scores or greater use of point-of-care testing.

Introduction
Emergency humanitarian situations can be caused by extreme weather events, natural disasters, civil conflicts, international wars, terrorism and pandemics, which threaten our health and compromise health systems worldwide. Pharmacists are the third-largest healthcare professional group globally and provide pharmaceutical care and advice to people in need. However, the training opportunities to prepare pharmacists to respond in emergency humanitarian areas are not well described and may be limited. This scoping review aims to understand the extent and type of evidence in relation to training and education activities to prepare future pharmacists for disaster management in humanitarian emergency situations.

Methods and analysis
We will analyse peer-reviewed literature relating to educational or training activities for pharmacists/pharmacy students in the delivery of pharmacy services in humanitarian emergency situations. Relevant medical subject headings and keywords will be used to search Ovid MEDLINE, Scopus, EMBASE, ERIC, Informit, Web of Science and CINAHL databases from inception to the end of July 2024. Hand searching of any key references identified will also be performed. The title and abstract of search results will be screened to identify articles eligible to be included for full review. Articles meeting the inclusion criteria will undergo data extraction, content analysis and synthesis of the evidence using NVivo qualitative analysis software. A narrative summary of key themes and concepts in the literature will be presented as results. An international panel of experts will be consulted to inform decision-making processes during the development and interpretation stages, and we propose a template for the incorporation of participatory/consultative methodology into the scoping review process.

Ethics and dissemination
Ethics approval is not required for this study protocol because the members of the expert panel consulted are researchers who are participating based on their professional skills. Findings will be disseminated via publication in a peer-reviewed journal and presentation at international conferences.

Introduction
Cerebral palsy (CP) is a paediatric disorder with permanent impairment of movement and posture with a prevalence of about 2.11 in 1000 births in the world. Given the therapeutic effect of hand-arm bimanual intensive therapy including lower extremities (HABIT-ILE) in children with CP, a systematic review of the available literature on this topic is warranted. The objective of this study is to systematically review the effectiveness of HABIT-ILE on upper extremity, lower extremity and trunk outcomes within the domains of body functions and structures, activity and participation of the International Classification of Functioning, Disability and Health in children with CP.

Methods and analysis
This study will be conducted following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. Searches will be conducted in six databases: MEDLINE, PubMed, Cochrane Library, Scopus, OT seeker and Web of Science for available published literature. The grey literature sources will include WorldCat, National Technical Information Service, Agency for Healthcare Research and Quality, Open Grey, WHO and OpenDOAR. Manual searches of citations of included papers will be performed to collect all experimental studies of HABIT-ILE in children with CP. The level of evidence for included articles will be classified according to the level of evidence in the guidelines for systematic reviews on the American Occupational Therapy Association website. Based on the study design of the included articles, the risk of bias will be assessed using the revised Cochrane risk-of-bias tool, the Cochrane Risk Of Bias In Non-randomised Studies – of Interventions tool and the quality assessment tool recommended by the American Occupational Therapy Association. In order to synthesise the data, narrative synthesis will be used, along with meta-analysis, if available.

Ethics and dissemination
As this study only reviewed previously published articles, ethical approval was not required. The findings will be published in a peer-reviewed scientific journal.

PROSPERO registration number
CRD42024518179.

Introduction
Globally, osteoarthritis (OA) is the most prevalent musculoskeletal disease, affecting approximately 600 million people. It is characterised by progressive degeneration of the articular cartilage, osteophyte formation and asymmetric joint space narrowing, leading to pain, stiffness and functional impairment. The current focus of disease management is on symptom relief and functional improvement. However, these interventions frequently do not provide adequate outcomes. This may be attributed to a lack of consideration for contextual factors, including the presence of comorbidities such as depression. Several studies indicate that depression is highly prevalent, affecting up to 20% of patients with OA. As depression is known to be a multifactorial disorder, there are various risk factors that may increase the likelihood of comorbid depression in patients with OA. Consequently, the scoping review’s objective is to map the existing literature on risk factors for comorbid depression in individuals with OA. Furthermore, the review is expected to provide important information for further in-depth investigation and the development of predictive tools to support the early identification of patients with OA at risk of comorbid depression.

Methods and analysis
The intended review will target studies reporting risk factors for comorbid depression in individuals with OA. All available primary and grey literature will be considered for inclusion. Only articles published in English or German will be included in the review. The review will follow the format specified by the Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews and the Joanna Briggs Institute Manual for Evidence Synthesis. Original research in published and unpublished literature from inception until August 2024 will be included in the review. The databases to be searched will include PubMed, EMBASE, PsycInfo and Web of Science. In addition, further literature will be identified by searching the reference lists of the included studies. Three reviewers will independently screen the identified studies for final inclusion. The data will be extracted and presented in tabular form and in a narrative summary that aligns with the review’s objective. Furthermore, a quality assessment of the included studies will be conducted using appropriate tools, and the results will be incorporated into the synthesis. Any disagreements that arise between the reviewers will be resolved through discussion or with an additional reviewer.

Ethics and dissemination
Ethics committee approval will not be required because only published and publicly available data will be examined to answer the research question of the scoping review. We will not collect any personal information or any information that requires ethical approval. Following the conclusion of the review, the information will be disseminated to clinicians, health administrators and researchers via publications in peer-reviewed journals and conference presentations.

Objectives
To evaluate whether postpartum haemorrhage (PPH) can be predicted using both machine learning (ML) and traditional statistical models.

Design
Diagnostic systematic review and meta-analysis of observational and clinical studies, prospectively registered on PROSPERO, performed accordingly to the Preferred Reporting Items for Systematic Reviews and Meta-analysis and Prediction model risk of bias assessment tool for studies developing, validating or updating prediction models, with the use of an independent analysis by a large language model (GPT-4 Open AI).

Data sources
MEDLINE/PubMed, LILACS-BVS, Cochrane Library, Scopus-Elsevier, Embase-Elsevier and Web of Science.

Eligibility criteria for selected studies
The literature search was conducted on 4 January 2024 and included observational studies and clinical trials published in the past 10 years that assessed early PPH and PPH prediction and that applied accuracy metrics for outcomes evaluation. We excluded studies that did not define PPH or had exclusive PPH subgroups evaluation.

Primary and secondary outcome measures
The primary outcome is the accuracy of PPH prediction using both ML and conventional statistical models. A secondary outcome is to describe the strongest risk factors of PPH identified by ML and traditional statistical models.

Results
Of 551 citations screened, 35 studies were eligible for inclusion. The synthesis gathered 383 648 patients in 24 studies conducted with conventional statistics (CS), 9 studies using ML models and 2 studies using both methods. Multivariate regression was a preferred modelling approach to predict PPH in CS studies, while ML approaches used multiple models and a myriad of features. ML comparison to CS was only performed in two studies, and ML models demonstrated a 95% higher likelihood of PPH prediction compared with CS when applied to the same dataset (OR 1.95, 95% CI 1.88 to 2.01, p