Pub Date : 2024-04-15DOI: 10.1101/2024.04.13.24305151
Ameenat Lola Solebo, Lisanne Horvat-Gitsels, Christine Twomey, Siegfried Karl Wagner, Jugnoo S Rahi
Introduction Patient portals allowing access to electronic health care records and services can inform and empower, but may widen existing sociodemographic inequities. We aimed to describe associations between activation of a paediatric patient portal and patient race/ethnicity, socioeconomic status and markers of previous engagement with health care.
{"title":"Socioeconomic and demographic patterning of family uptake of a paediatric electronic patient portal innovation","authors":"Ameenat Lola Solebo, Lisanne Horvat-Gitsels, Christine Twomey, Siegfried Karl Wagner, Jugnoo S Rahi","doi":"10.1101/2024.04.13.24305151","DOIUrl":"https://doi.org/10.1101/2024.04.13.24305151","url":null,"abstract":"<strong>Introduction</strong> Patient portals allowing access to electronic health care records and services can inform and empower, but may widen existing sociodemographic inequities. We aimed to describe associations between activation of a paediatric patient portal and patient race/ethnicity, socioeconomic status and markers of previous engagement with health care.","PeriodicalId":501556,"journal":{"name":"medRxiv - Health Systems and Quality Improvement","volume":"97 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140609155","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Current machine learning-based Alzheimer’s disease (AD) diagnosis methods fail to explore the distinctive brain patterns across different AD stages, lacking the ability to trace the trajectory of AD progression. This limitation can lead to an oversight of the pathological mechanisms of AD and suboptimal performance in AD diagnosis. To overcome this challenge, this paper proposes a novel stage-aware brain graph learning model. Particularly, we analyze the different brain patterns of each AD stage in terms of stage-specific brain graphs. We design a Stage Feature-enhanced Graph Contrastive Learning method, named SF-GCL, utilizing specific features within each AD stage to perform graph augmentation, thereby effectively capturing differences between stages. Significantly, this study unveils the specific brain patterns corresponding to each AD stage, showing great potential in tracing the trajectory of brain degeneration. Experimental results on a real-world dataset demonstrate the superiority of our model.
目前基于机器学习的阿尔茨海默病（AD）诊断方法无法探索不同AD阶段的独特大脑模式，缺乏追踪AD进展轨迹的能力。这一局限性可能导致对阿尔茨海默病病理机制的疏忽，并使阿尔茨海默病诊断效果不佳。为了克服这一挑战，本文提出了一种新型的阶段感知脑图学习模型。特别是，我们从特定阶段的脑图角度分析了 AD 每个阶段的不同脑模式。我们设计了一种名为 SF-GCL 的阶段特征增强图对比学习方法，利用 AD 各阶段的特定特征进行图增强，从而有效捕捉各阶段之间的差异。值得注意的是，这项研究揭示了与 AD 每个阶段相对应的特定大脑模式，在追踪大脑退化轨迹方面显示出巨大的潜力。在真实世界数据集上的实验结果证明了我们模型的优越性。
{"title":"Stage-aware Brain Graph Learning for Alzheimer’s Disease","authors":"Ciyuan Peng, Mujie Liu, Chenxuan Meng, Sha Xue, Kathleen Keogh, Feng Xia","doi":"10.1101/2024.04.14.24305804","DOIUrl":"https://doi.org/10.1101/2024.04.14.24305804","url":null,"abstract":"Current machine learning-based Alzheimer’s disease (AD) diagnosis methods fail to explore the distinctive brain patterns across different AD stages, lacking the ability to trace the trajectory of AD progression. This limitation can lead to an oversight of the pathological mechanisms of AD and suboptimal performance in AD diagnosis. To overcome this challenge, this paper proposes a novel stage-aware brain graph learning model. Particularly, we analyze the different brain patterns of each AD stage in terms of stage-specific brain graphs. We design a Stage Feature-enhanced Graph Contrastive Learning method, named SF-GCL, utilizing specific features within each AD stage to perform graph augmentation, thereby effectively capturing differences between stages. Significantly, this study unveils the specific brain patterns corresponding to each AD stage, showing great potential in tracing the trajectory of brain degeneration. Experimental results on a real-world dataset demonstrate the superiority of our model.","PeriodicalId":501556,"journal":{"name":"medRxiv - Health Systems and Quality Improvement","volume":"37 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140609217","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-04-15DOI: 10.1101/2024.04.14.24305788
Anne Büscher, Nicolle Reinhold, Joachim Kugler
Introduction Standardization in healthcare is crucial for comprehensive patient care, as emphasized by the WHO and quality management principles. Clinical pathways offer a structured approach to describing essential processes, particularly relevant in gynecologic oncology care. Despite their proven benefits, pathways remain underutilized, highlighting the need for explicit translation of implicit pathways.
{"title":"The development of the gynecologic oncology pathway “VivaPathway GT“ – a qualitative study about the transformation from an implicit to an explicit, evidence-based clinical pathway in a Berlin-based tertiary care hospital","authors":"Anne Büscher, Nicolle Reinhold, Joachim Kugler","doi":"10.1101/2024.04.14.24305788","DOIUrl":"https://doi.org/10.1101/2024.04.14.24305788","url":null,"abstract":"<strong>Introduction</strong> Standardization in healthcare is crucial for comprehensive patient care, as emphasized by the WHO and quality management principles. Clinical pathways offer a structured approach to describing essential processes, particularly relevant in gynecologic oncology care. Despite their proven benefits, pathways remain underutilized, highlighting the need for explicit translation of implicit pathways.","PeriodicalId":501556,"journal":{"name":"medRxiv - Health Systems and Quality Improvement","volume":"72 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140609109","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-04-09DOI: 10.1101/2024.04.08.24305473
Henry Zakumumpa, Caroline Kyozira, Martin Bulamu, Remmy Buhuguru
Introduction A fully functional referral system is central to achieving quality maternal and newborn care. In 2018, Uganda established Kawempe National Referral hospital (KRNH) as the highest level of care for maternity services. There is a dearth of data examining if the referral function for which it was established has been met. The objectives of this study were two fold; i) to assess the appropriateness of in-coming referrals at KRNH ii) to examine factors underpinning referral decisions at lower referring facilities across Uganda.
{"title":"A health systems analysis of non-compliance to the maternity referral system by health facilities in Uganda: Findings from a mixed-methods study","authors":"Henry Zakumumpa, Caroline Kyozira, Martin Bulamu, Remmy Buhuguru","doi":"10.1101/2024.04.08.24305473","DOIUrl":"https://doi.org/10.1101/2024.04.08.24305473","url":null,"abstract":"<strong>Introduction</strong> A fully functional referral system is central to achieving quality maternal and newborn care. In 2018, Uganda established Kawempe National Referral hospital (KRNH) as the highest level of care for maternity services. There is a dearth of data examining if the referral function for which it was established has been met. The objectives of this study were two fold; i) to assess the appropriateness of in-coming referrals at KRNH ii) to examine factors underpinning referral decisions at lower referring facilities across Uganda.","PeriodicalId":501556,"journal":{"name":"medRxiv - Health Systems and Quality Improvement","volume":"47 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140598000","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-04-05DOI: 10.1101/2024.04.04.24305355
Pilar Artiach Hortelano, Neil Morton, Paul Wicks, Michael Young, Rebecca Burdell, Duncan Richards
Background Novel therapeutics should always be tested in a sample representative of the population in need of treatment. Initial efforts of drug development take place in early phase trials (phase-I and -II), setting the direction for late-stage studies (phase-III and -IV). However, study samples in early phase trials typically fail to recruit Black, Asian and minority ethnic groups, which might produce results which don’t generalise to a broader population in later trials, and ultimately, clinical practice. Focusing on early phase clinical trials the present study (1) explored the barriers and incentives that determine participation of ethnic minorities in clinical research, and (2) proposes strategies that mitigate such barriers.
背景 新疗法应始终在代表需要治疗人群的样本中进行测试。药物开发的初期工作是进行早期试验（I 期和 II 期），为后期研究（III 期和 IV 期）确定方向。然而，早期试验中的研究样本通常未能招募到黑人、亚裔和少数民族群体，这可能导致试验结果无法推广到更广泛的人群中，最终影响到临床实践。本研究以早期临床试验为重点，(1) 探讨了决定少数民族参与临床研究的障碍和激励因素，(2) 提出了减少这些障碍的策略。
{"title":"“It’s not about the money, money” - Well, actually it is. Divergent views on drivers of early phase clinical trial participation among ethnically diverse potential trial participants in the United Kingdom: A Mixed Methods Study","authors":"Pilar Artiach Hortelano, Neil Morton, Paul Wicks, Michael Young, Rebecca Burdell, Duncan Richards","doi":"10.1101/2024.04.04.24305355","DOIUrl":"https://doi.org/10.1101/2024.04.04.24305355","url":null,"abstract":"<strong>Background</strong> Novel therapeutics should always be tested in a sample representative of the population in need of treatment. Initial efforts of drug development take place in early phase trials (phase-I and -II), setting the direction for late-stage studies (phase-III and -IV). However, study samples in early phase trials typically fail to recruit Black, Asian and minority ethnic groups, which might produce results which don’t generalise to a broader population in later trials, and ultimately, clinical practice. Focusing on early phase clinical trials the present study (1) explored the barriers and incentives that determine participation of ethnic minorities in clinical research, and (2) proposes strategies that mitigate such barriers.","PeriodicalId":501556,"journal":{"name":"medRxiv - Health Systems and Quality Improvement","volume":"25 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140597995","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-04-03DOI: 10.1101/2024.04.03.24305214
Matthew Alabi, Leanne Dougherty, Eno-Obong Etim, Adebola Adedimeji
Background Family Planning Counselling (FPC) involves information exchange on contraceptive methods between a provider and client and providing appropriate support in choosing a method that best suits the client’s needs. Access to sexual and reproductive health information enables women to make informed health decisions. However, the low modern contraceptive prevalence among women in northern Nigeria may be attributed to poor FPC and exposure to FP messages, among other factors. This study examines the impact of quality FPC and exposure to FP messages on modern contraceptive use.
{"title":"DOES QUALITY OF COUNSELING AND EXPOSURE TO FAMILY PLANNING MESSAGES INFLUENCE THE USE OF MODERN CONTRACEPTIVES AMONG WOMEN IN NORTHERN NIGERIA?","authors":"Matthew Alabi, Leanne Dougherty, Eno-Obong Etim, Adebola Adedimeji","doi":"10.1101/2024.04.03.24305214","DOIUrl":"https://doi.org/10.1101/2024.04.03.24305214","url":null,"abstract":"<strong>Background</strong> Family Planning Counselling (FPC) involves information exchange on contraceptive methods between a provider and client and providing appropriate support in choosing a method that best suits the client’s needs. Access to sexual and reproductive health information enables women to make informed health decisions. However, the low modern contraceptive prevalence among women in northern Nigeria may be attributed to poor FPC and exposure to FP messages, among other factors. This study examines the impact of quality FPC and exposure to FP messages on modern contraceptive use.","PeriodicalId":501556,"journal":{"name":"medRxiv - Health Systems and Quality Improvement","volume":"300 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140598270","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-04-03DOI: 10.1101/2024.04.02.24305221
Jérémie Gallien, George Chen, Yi Zhang, Yuhang Du, Jody Lori, Joseph Sieka, Bentoe Tehoungue
This paper presents a simple mathematical model and an associated physical device to predict (i) the risk that a woman’s active labor will begin without a skilled birth attendant based on her parity and anticipated time to access skilled care; and (ii) the extent to which that risk may be reduced by moving to a maternity waiting home some time before her expected due date. This tool is designed to facilitate more systematic discussions and better-informed decisions about labour care access arrangements during antenatal consultations.
{"title":"A simple mathematical model and physical device to estimate a woman-specific probability of skilled birth assistance and associated benefit of maternity waiting home stay","authors":"Jérémie Gallien, George Chen, Yi Zhang, Yuhang Du, Jody Lori, Joseph Sieka, Bentoe Tehoungue","doi":"10.1101/2024.04.02.24305221","DOIUrl":"https://doi.org/10.1101/2024.04.02.24305221","url":null,"abstract":"This paper presents a simple mathematical model and an associated physical device to predict (i) the risk that a woman’s active labor will begin without a skilled birth attendant based on her parity and anticipated time to access skilled care; and (ii) the extent to which that risk may be reduced by moving to a maternity waiting home some time before her expected due date. This tool is designed to facilitate more systematic discussions and better-informed decisions about labour care access arrangements during antenatal consultations.","PeriodicalId":501556,"journal":{"name":"medRxiv - Health Systems and Quality Improvement","volume":"300 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140597997","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-04-03DOI: 10.1101/2024.04.02.24305238
K Neadley, C Shoubridge, A Smith, S Martin, M Boyd, C Hocking
Introduction Integrating health and social care to address unmet social needs is an emerging priority for health systems worldwide. Screening and referral interventions for unmet social needs in healthcare settings have shown promising results. Most screening and referral interventions are implemented in primary care, despite evidence that disadvantaged populations face substantial barriers to accessing such care. There are few social care interventions in hospital settings. To address this gap, we designed a hospital-based intervention screening an outpatient population for unmet social needs and using a Health Navigator to provide referrals and follow-up to appropriate community and government resources. Here we present a protocol for a feasibility and acceptability study of a hospital-based Health Navigator intervention.
{"title":"Addressing unmet social needs using a health navigator for patients at a major metropolitan hospital in Australia: a mixed-methods feasibility study","authors":"K Neadley, C Shoubridge, A Smith, S Martin, M Boyd, C Hocking","doi":"10.1101/2024.04.02.24305238","DOIUrl":"https://doi.org/10.1101/2024.04.02.24305238","url":null,"abstract":"<strong>Introduction</strong> Integrating health and social care to address unmet social needs is an emerging priority for health systems worldwide. Screening and referral interventions for unmet social needs in healthcare settings have shown promising results. Most screening and referral interventions are implemented in primary care, despite evidence that disadvantaged populations face substantial barriers to accessing such care. There are few social care interventions in hospital settings. To address this gap, we designed a hospital-based intervention screening an outpatient population for unmet social needs and using a Health Navigator to provide referrals and follow-up to appropriate community and government resources. Here we present a protocol for a feasibility and acceptability study of a hospital-based Health Navigator intervention.","PeriodicalId":501556,"journal":{"name":"medRxiv - Health Systems and Quality Improvement","volume":"30 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140598421","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-03-19DOI: 10.1101/2024.03.14.24304312
Kathleen M. Foldvari, Paul Stolee, Elena Neiterman, Veronique M. Boscart, Catherine Tong
Background: Amyotrophic Lateral Sclerosis (ALS), an incurable motor neuron disease, primarily affects those between the ages of 60-79, and has an approximate post-diagnosis life--expectancy of only two to five years. The condition has an unpredictable but ultimately terminal trajectory that poses a number of challenges for patients, caregivers and healthcare providers. While the diagnosis and disclosure are critical periods for intervention and support, knowledge regarding the relational, communicational and psychodynamic forces that occur within the process of diagnostic disclosure is relatively limited. Objectives: The purpose of this study was to explore the experiences of persons living with ALS in the diagnosis and disclosure of the condition, and the experiences of their caregivers. Methods: We conducted a focus group and in-depth individual interviews with Canadians living with ALS (n = 9), family caregivers (n = 7), a professional caregiver (n = 1), and one past caregiver (1). The interviews were transcribed, cleaned, and anonymized, and then entered into NVivo 11 for thematic analysis. Results: Participants discussed the diagnosis process, including the inklings and subtle changes prior to diagnosis, attempts at self-diagnosis, and the lengthy assessment process. Time was also a consideration in the disclosure process, in which participants shared how the diagnosis disclosure was the product of longstanding conversations with their care providers. It was described as rarely a shock to finally have confirmation. Additionally, participants shared their information seeking strategies and needs for a diagnosis that, for them, typically came with insufficient information on the disease, prognosis, and next steps. Significance: This project serves as an initial step in bridging the relevant gaps in our knowledge and understanding towards improved patient-centered care practices in the diagnosis and disclosure of ALS.
背景：肌萎缩侧索硬化症（ALS）是一种无法治愈的运动神经元疾病：肌萎缩侧索硬化症（ALS）是一种无法治愈的运动神经元疾病，主要影响 60-79 岁的人群，确诊后的预期寿命大约只有 2-5 年。这种疾病的发展轨迹难以预测，但最终会走向终结，这给患者、护理人员和医疗服务提供者带来了诸多挑战。虽然诊断和披露是干预和支持的关键时期，但有关诊断披露过程中发生的关系、沟通和心理动力的知识却相对有限。研究目的本研究旨在探讨 ALS 患者在诊断和病情披露过程中的经历，以及他们的照顾者的经历。研究方法我们对加拿大 ALS 患者（9 人）、家庭照顾者（7 人）、专业照顾者（1 人）和一位过去的照顾者（1 人）进行了焦点小组讨论和深入的个人访谈。访谈内容经过誊写、清理和匿名处理，然后输入 NVivo 11 进行主题分析。结果参与者讨论了诊断过程，包括诊断前的预兆和细微变化、自我诊断的尝试以及漫长的评估过程。在披露过程中，时间也是一个考虑因素，参与者分享了诊断披露是如何与他们的护理提供者进行长期对话的产物。据描述，最终得到确诊很少让人感到震惊。此外，参与者还分享了他们寻求信息的策略以及对诊断结果的需求，对他们来说，诊断结果通常伴随着关于疾病、预后和下一步措施的不充分信息。意义：本项目是弥补我们对 ALS 诊断和信息披露方面的相关知识和理解差距的第一步。
{"title":"“…but I know something’s not right here”: Exploring the diagnosis and disclosure experiences of persons living with ALS","authors":"Kathleen M. Foldvari, Paul Stolee, Elena Neiterman, Veronique M. Boscart, Catherine Tong","doi":"10.1101/2024.03.14.24304312","DOIUrl":"https://doi.org/10.1101/2024.03.14.24304312","url":null,"abstract":"Background: Amyotrophic Lateral Sclerosis (ALS), an incurable motor neuron disease, primarily affects those between the ages of 60-79, and has an approximate post-diagnosis life--expectancy of only two to five years. The condition has an unpredictable but ultimately terminal trajectory that poses a number of challenges for patients, caregivers and healthcare providers. While the diagnosis and disclosure are critical periods for intervention and support, knowledge regarding the relational, communicational and psychodynamic forces that occur within the process of diagnostic disclosure is relatively limited. Objectives: The purpose of this study was to explore the experiences of persons living with ALS in the diagnosis and disclosure of the condition, and the experiences of their caregivers. Methods: We conducted a focus group and in-depth individual interviews with Canadians living with ALS (n = 9), family caregivers (n = 7), a professional caregiver (n = 1), and one past caregiver (1). The interviews were transcribed, cleaned, and anonymized, and then entered into NVivo 11 for thematic analysis. Results: Participants discussed the diagnosis process, including the inklings and subtle changes prior to diagnosis, attempts at self-diagnosis, and the lengthy assessment process. Time was also a consideration in the disclosure process, in which participants shared how the diagnosis disclosure was the product of longstanding conversations with their care providers. It was described as rarely a shock to finally have confirmation. Additionally, participants shared their information seeking strategies and needs for a diagnosis that, for them, typically came with insufficient information on the disease, prognosis, and next steps. Significance: This project serves as an initial step in bridging the relevant gaps in our knowledge and understanding towards improved patient-centered care practices in the diagnosis and disclosure of ALS.","PeriodicalId":501556,"journal":{"name":"medRxiv - Health Systems and Quality Improvement","volume":"39 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140168957","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-03-18DOI: 10.1101/2024.03.16.24304403
Zequn Chen, Wesley J. Marrero
Background. Unintended biases introduced by optimization and machine learning (ML) models are of great interest to medical professionals. Bias in healthcare decisions can cause patients from vulnerable populations (e.g., racially minoritized, low-income) to have lower access to resources, exacerbating societal unfairness. Purpose. This review aims to identify, describe, and categorize literature regarding bias types, fairness metrics, and bias mitigation methods in healthcare decision making. Data Sources. Google Scholar database was searched to identify published studies. Study Selection. Eligible studies were required to present 1) types of bias 2) fairness metrics and 3) bias mitigation methods within decision-making in healthcare. Data Extraction. Studies were classified according to the three themes mentioned in the Study Selection. Information was extracted concerning the definitions, examples, applications, and limitations of bias types, fairness metrics, and bias mitigation methods. Data Synthesis. In bias type section, we included studies (n=15) concerning different biases. In the fairness metric section, we included studies (n=6) regarding common fairness metrics. In bias mitigation method section, themes included pre-processing methods (n=5), in-processing methods (n=16), and post-processing methods (n=4). Limitations. Most examples in our survey are from the United States since the majority of studies included in this survey were conducted in the United States. In the meanwhile, we limited the search language to English, so we may not capture some meaningful articles in other languages. Conclusions. Several types of bias, fairness metrics, and bias mitigation methods (especially optimization and machine learning-based methods) were identified in this review, with common themes based on analytical approaches. We also found topics such as explainability, fairness metric selection, and integration of prediction and optimization are promising directions for future studies.
{"title":"A Survey on Optimization and Machine -learning-based Fair Decision Making in Healthcare","authors":"Zequn Chen, Wesley J. Marrero","doi":"10.1101/2024.03.16.24304403","DOIUrl":"https://doi.org/10.1101/2024.03.16.24304403","url":null,"abstract":"Background. Unintended biases introduced by optimization and machine learning (ML) models are of great interest to medical professionals. Bias in healthcare decisions can cause patients from vulnerable populations (e.g., racially minoritized, low-income) to have lower access to resources, exacerbating societal unfairness. Purpose. This review aims to identify, describe, and categorize literature regarding bias types, fairness metrics, and bias mitigation methods in healthcare decision making. Data Sources. Google Scholar database was searched to identify published studies. Study Selection. Eligible studies were required to present 1) types of bias 2) fairness metrics and 3) bias mitigation methods within decision-making in healthcare. Data Extraction. Studies were classified according to the three themes mentioned in the Study Selection. Information was extracted concerning the definitions, examples, applications, and limitations of bias types, fairness metrics, and bias mitigation methods. Data Synthesis. In bias type section, we included studies (n=15) concerning different biases. In the fairness metric section, we included studies (n=6) regarding common fairness metrics. In bias mitigation method section, themes included pre-processing methods (n=5), in-processing methods (n=16), and post-processing methods (n=4). Limitations. Most examples in our survey are from the United States since the majority of studies included in this survey were conducted in the United States. In the meanwhile, we limited the search language to English, so we may not capture some meaningful articles in other languages. Conclusions. Several types of bias, fairness metrics, and bias mitigation methods (especially optimization and machine learning-based methods) were identified in this review, with common themes based on analytical approaches. We also found topics such as explainability, fairness metric selection, and integration of prediction and optimization are promising directions for future studies.","PeriodicalId":501556,"journal":{"name":"medRxiv - Health Systems and Quality Improvement","volume":"26 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140168960","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：