Termo de consentimento livre e esclarecido e sua relação com os procedimentos de preenchimento labial / Free and informed consent terms and its relationship with lip filling procedures

Introdução: Na medida em que envelhecemos os lábios estreitam-se, ocasionando perda de volume e contorno e como forma de minimizar este efeito fisiológico o preenchimento labial de escolha utilizado é o ácido hialurônico. É possível perceber efeitos adversos advindos do emprego deste material, e pelo fato da informação ao paciente ser assegurada pelo Código de Defesa do Consumidor e pelo fato da necessidade dos Cirurgiões-Dentistas terem de esclarecer seus pacientes, o Termo de Consentimento Livre e Esclarecido tornase necessário. Objetivo: identificar, por meio de aplicação de questionário, a percepção de profissionais que trabalham com Harmonização Orofacial em relação a necessidade do emprego do Termo de Consentimento Livre e Esclarecido (TCLE). O questionário apresentou 6 perguntas objetivas, que foram disponibilizadas na plataforma Google Forms®. Material e Método: os dados obtidos foram tabulados em uma planilha eletrônica do programa Microsoft Excel e após analisados descritivamente através de tabelas de frequência, porcentagens e gráficos estatísticos. Resultados: dentre os entrevistados foi constatado que a maioria, 87,5% dos especialistas em Harmonização Orofacial realizam o procedimento de preenchimento labial em sua rotina clínica, e 12,5% não. Conclusão: no presente estudo identificamos que os especialistas realizam o emprego do TCLE, em sua maioria, porém, alguns destes ainda negligenciam o seu uso(AU)

Introduction: As we age, the lips become thinner and to minimize this effect, the lip filler used is hyaluronic acid. It is possible to notice adverse effects arising from the use of this material, and it is extremely important that Dental Surgeons have to clarify their patients, the Free and Informed Consent Form becomes necessary. Objective: to identify, through the application of a questionnaire, the perception of professionals who work with Orofacial Harmonization in relation to the need to use the Free and Informed Consent Form (TCLE). The questionnaire presented 6 objective questions, which were made available on the Google Forms® platform. Materials and Methods: the data obtained were tabulated in a Microsoft Excel spreadsheet and then analyzed descriptively using frequency tables, percentages and graphs. Results: among those interviewed, it was found that the majority, 87.5% of specialists in Orofacial Harmonization perform the lip filling procedure in their clinical routine, and 12.5% do not. With the high percentage of 59.4%, it was possible to verify that the majority of professionals perform 1 to 3 procedures per month; 31.3% perform 4 to 9 procedures per month; and 9.4% of 10 or more monthly procedures. Conclusion: in the present study it was possible to identify that the majority of specialists in Orofacial Harmonization use the informed consent form, however, some of them still neglect its use(AU)

Approaches and experiences implementing remote, electronic consent at the Leeds Clinical Trials Research Unit.

BACKGROUND: Use of electronic methods to support informed consent ('eConsent') is increasingly popular in clinical research. This commentary reports the approach taken to implement electronic consent methods and subsequent experiences from a range of studies at the Leeds Clinical Trials Research Unit (CTRU), a large clinical trials unit in the UK. MAIN TEXT: We implemented a remote eConsent process using the REDCap platform. The process can be used in trials of investigational medicinal products and other intervention types or research designs. Our standard eConsent system focuses on documenting informed consent, with other aspects of consent (e.g. providing information to potential participants and a recruiter discussing the study with each potential participant) occurring outside the system, though trial teams can use electronic methods for these activities where they have ethical approval. Our overall process includes a verbal consent step prior to confidential information being entered onto REDCap and an identity verification step in line with regulator guidance. We considered the regulatory requirements around the system's generation of source documents, how to ensure data protection standards were upheld and how to monitor informed consent within the system. We present four eConsent case studies from the CTRU: two randomised clinical trials and two other health research studies. These illustrate the ways eConsent can be implemented, and lessons learned, including about differences in uptake. CONCLUSIONS: We successfully implemented a remote eConsent process at the CTRU across multiple studies. Our case studies highlight benefits of study participants being able to give consent without having to be present at the study site. This may better align with patient preferences and trial site needs and therefore improve recruitment and resilience against external shocks (such as pandemics). Variation in uptake of eConsent may be influenced more by site-level factors than patient preferences, which may not align well with the aspiration towards patient-centred research. Our current process has some limitations, including the provision of all consent-related text in more than one language, and scalability of implementing more than one consent form version at a time. We consider how enhancements in CTRU processes, or external developments, might affect our approach.

When describing harms and benefits to potential trial participants, participant information leaflets are inadequate.

BACKGROUND: Providing informed consent for trials requires providing trial participants with comprehensive information about the trial, including information about potential risks and benefits. It is required by the ethical principle of respecting patient autonomy. Our study examines the variation in the way information about potential trial benefits and harms is shared in participant information leaflets (PILs). METHODS: A total of 214 PILs and informed consent forms from clinical trials units (CTUs) and Clinical Research Facilities (CRFs) in Ireland and the UK were assessed by two authors independently, to check the extent to which they adhered to seven recently developed principles. Discrepancies were resolved by a third. RESULTS: Usage of the seven principles varied widely between PILs regardless of the intended recipient or trial type. None of the PILs used more than four principles, and some (4%) used none. Twenty-seven per cent of PILs presented information about all known potential harms, whereas 45% presented information on all known potential benefits. Some PILs did not provide any potential harms or potential benefits (8%). There was variation in the information contained in adult and children PILs and across disease areas. CONCLUSION: Significant variation exists in how potential trial benefits and harms are described to potential trial participants in PILs in our sample. Usage of the seven principles of good practice will promote consistency, ensure informed ethical decision-making and invoke trust and transparency. In the long term, a standardised PIL template is needed.

Clear aligner therapy informed consent forms: A quality and readability evaluation.

OBJECTIVE: The aim of the present study was to evaluate the quality and readability of content contained within clear aligner therapy (CAT) informed consent forms. METHODS: CAT informed consent forms were identified via an online search. The presence of details related to CAT-related processes, risks, benefits and alternatives in each form was recorded. A 4-point Likert type scale was used to determine the quality of content (QOC). The readability of content was evaluated with the Simple Measure of Gobbledegook (SMOG) and Flesch Reading Ease Score (FRES). RESULTS: A total of 42 forms satisfied selection criteria. Nineteen (45.2%) were authored by companies who provided aligners to patients via clinicians. The QOC regarding CAT-related treatment processes [median 2.0; IQR 0, 2] and benefits [median 2.0; IQR 1, 2] was adequate. The QOC scores regarding treatment alternatives, consequences of no treatment and relapse were poor. There was no difference (P=0.59) in the median (IQR) QOC of the informed consent forms provided by direct-to-consumer (DTC) aligner providers [10 (8.25, 16.25)] and non-DTC aligner providers [12 (10, 14)]. The median (IQR) SMOG score was 12.1 (10.9, 12.7) and FRES was 39.0 (36.0, 44.25). CONCLUSIONS: The QOC of the evaluated forms was incomplete and poor. The content was difficult to read and failed to reach recommended readability standards. Consent is unlikely to be valid if it is based solely on the content of the forms. Clinicians need to be aware of the limitations of informed consent forms for CAT particularly in relation to alternatives, prognosis, risks, and the need for long-term maintenance of results.

Understanding the language barriers to translating informed consent documents for maternal health trials in Zambia: a qualitative study.

OBJECTIVE: Providing comprehensible information is essential to the process of valid informed consent. Recruitment materials designed by sponsoring institutions in English-speaking, high-income countries are commonly translated for use in global health studies in other countries; however, key concepts are often missed, misunderstood or 'lost in translation'. The aim of this study was to explore the language barriers to informed consent, focusing on the challenges of translating recruitment materials for maternal health studies into Zambian languages. DESIGN: We used a qualitative approach, which incorporated a multistakeholder workshop (11 participants), in-depth interviews with researchers and translators (8 participants) and two community-based focus groups with volunteers from community advisory boards (20 participants). Content analysis was used to identify terms commonly occurring in recruitment materials prior to the workshop. The framework analysis approach was used to analyse interview data, and a simple inductive thematic analysis approach was used to analyse focus group data. SETTING: The study was based in Lusaka, Zambia. RESULTS: The workshop highlighted difficulties in translating research terms and pregnancy-specific terms, as well as widespread concern that current templates are too long, use overly formal language and are designed with little input from local teams. Framework analysis of in-depth interviews identified barriers to participant understanding relating to design and development of recruitment materials, language, local context and communication styles. Focus group participants confirmed these findings and suggested potential solutions to ensure the language and content of recruitment materials can be better understood. CONCLUSION: Our findings demonstrate that the way in which recruitment materials are currently designed, translated and disseminated may not enable potential trial participants to fully understand the information provided. Instead of using overly complex institutional templates, recruitment materials should be created through an iterative and interactive process that provides truly comprehensible information in a format appropriate for its intended participants.

What Is "Key Information"? Consideration of the Reasons People Do or Do Not Take Part in Research.

We performed a qualitative review of 50 consent forms posted on Clinicaltrials.gov, examining the content of key information sections. We found that key information disclosures are typically focused on procedures, risks, potential benefits, and alternatives. Drawing upon reviews of the large literature examining the reasons people do or do not take part in research, we propose that these disclosures should be based more directly on what we know to be the real reasons why people choose to take part or refuse participation. We propose key information language for consideration by researchers and institutional review boards.

Comparing Attitudes Toward Different Consent Mediums: Semistructured Qualitative Study.

BACKGROUND: As consent for data sharing evolves with the digital age, plain-text consent is not the only format in which information can be presented. However, designing a good consent form is highly challenging. The addition of graphics, video, and other mediums to use can vary widely in effectiveness; and improper use can be detrimental to users. OBJECTIVE: This study aims to explore the expectations and experiences of adults toward consent given in infographic, video, text, newsletter, and comic forms in a health data sharing scenario to better understand the appropriateness of different mediums and identify elements of each medium that most affect engagement with the content. METHODS: We designed mock consent forms in infographic, video, text, newsletter, and comic versions. Semistructured interviews were conducted with adults who were interviewed about their expectations for consent and were then shown each consent medium and asked about engaging elements across mediums, preferences for consent mediums, and the value of document quality criteria. We transcribed and qualitatively co-coded to identify themes and perform analyses. RESULTS: We interviewed 24 users and identified different thematic archetypes based on participant goals, such as the Trust Seeker, who considered their own understanding and trust in organizations when making decisions. The infographic was ranked first for enhancing understanding, prioritizing information, and maintaining the proper audience fit for serious consent in health data sharing scenarios. In addition, specific elements such as structure, step-by-step organization, and readability were preferred engaging elements. CONCLUSIONS: We identified archetypes to better understand user needs and elements that can be targeted to enhance user engagement with consent forms; this can help inform the design of more effective consent in the future. Overall, preferences for mediums are highly contextual, and more research should be done.

Returning Clinically Relevant Research Results to Participants: Guidelines for Investigators and the IRB.

In 2019, the revised Common Rule required informed consent documents for research to include a statement about whether clinically relevant research results would be returned to research participants. While there are national discussions regarding the return of results, these do not provide specific guidance about how institutional review boards (IRBs) should address this issue. Through a year-long process involving IRB staff and leadership, science and bioethics faculty members, community IRB members, and others, Indiana University's human research protection program created a framework that offers a clear categorization of types of results for researchers to consider returning, provides language for informed consent documents, and describes an active but intentionally limited role for the IRB. In this article, we describe this framework and its rationale as a model for other universities and, more generally, as a model for balancing the need to protect human subjects with efforts to limit the burdens on researchers and the IRB.

Development of a New Tool for Writing Research Key Information in Plain Language.

BACKGROUND: The complexity of research informed consent forms makes it hard for potential study participants to make informed consent decisions. In response, new rules for human research protection require informed consent forms to begin with a key information section that potential study participants can read and understand. This research study builds on exiting guidance on how to write research key information using plain language. OBJECTIVE: The aim of this study was to develop a valid and reliable tool to evaluate and improve the readability, understandability, and actionability of the key information section on research informed consent forms. METHODS: We developed an initial list of measures to include on the tool through literature review; established face and content validity of measures with expert input; conducted four rounds of reliability testing with four groups of reviewers; and established construct validity with potential research participants. KEY RESULTS: We identified 87 candidate measures via literature review. After expert review, we included 23 items on the initial tool. Twenty-four raters conducted 4 rounds of reliability testing on 10 informed consent forms. After each round, we revised or eliminated items to improve agreement. In the final round of testing, 18 items demonstrated substantial inter-rater agreement per Fleiss' Kappa (average = .73) and Gwet's AC1 (average = .77). Intra-rater agreement was substantial per Cohen's Kappa (average = .74) and almost perfect per Gwet's AC1 (average = 0.84). Focus group feedback (N = 16) provided evidence suggesting key information was easy to read when rated as such by the Readability, Understandability and Actionability of Key Information (RUAKI) Indicator. CONCLUSION: The RUAKI Indicator is an 18-item tool with evidence of validity and reliability investigators can use to write the key information section on their informed consent forms that potential study participants can read, understand, and act on to make informed decisions. [HLRP: Health Literacy Research and Practice. 2024;8(1):e29-e37.].

PLAIN LANGUAGE SUMMARY: Research informed consent forms describe key information about research studies. People need this information to decide if they want to be in a study or not. A helpful form begins with a short, easy-to-read key information section. This study created a tool researchers can use to write the key information about their research people can read, understand, and use.

Pediatric Consent on FHIR.

BACKGROUND: Standardizing and formalizing consent processes and forms can prevent ambiguities, convey a more precise meaning, and support machine interpretation of consent terms. OBJECTIVES: Our goal was to introduce a systematic approach to standardizing and digitizing pediatric consent forms, which are complex due to legal requirements for child and legal guardian involvement. METHODS: First, we reviewed the consent requirements from the Arizona regulation, and we used 21 pediatric treatment consents from five Arizona health care organizations to propose and evaluate an implementation-agnostic Consent for Treatment Framework. Second, we assessed the adequacy of the Fast Healthcare Interoperability Resources (FHIR) to support the proposed framework. RESULTS: The resulting Consent for Treatment Framework supports compliance with the state consent requirements and has been validated with pediatric consent forms. We also demonstrated that the FHIR standard has the required expressiveness to compute the framework's specifications and express the 21 consent forms. CONCLUSION: Health care organizations can apply the shared open-source code and FHIR implementation guidelines to standardize the design of machine-interpretable pediatric treatment consent forms. The resulting FHIR-based executable models may support compliance with the law and support interoperability and data sharing.

Assessing the Readability of Clinical Trial Consent Forms for Surgical Specialties.

INTRODUCTION: To evaluate the readability of surgical clinical trial consent forms and compare readability across surgical specialties. METHODS: We conducted a cross-sectional analysis of surgical clinical trial consent forms available on ClinicalTrials.gov to quantitatively evaluate readability, word count, and length variations among different specialties. The analysis was performed between November 2022 and January 2023. A total of 386 surgical clinical trial consent forms across 14 surgical specialties were included. RESULTS: The main outcomes were language complexity (measured using Flesch-Kincaid Grade Level), number of words (measured as word count), time to read (measured at reading speeds of 240 per min), and readability (measured by Flesch Reading Ease Score, Gunning Frog Index, Simple Measures of Gobbledygook Index, FORCAST, and Automated Readability Index). The surgical consent forms were a mean (standard deviation) of 2626 (1668) words long, with a mean of 12:53 min to read at 240 words per min. None of the surgical specialties had an average readability level of sixth grade or lower across all six indices, and only 16 out of 386 (4%) clinical trials met the recommended reading level. Furthermore, there was no significant difference in reading grade level between surgical specialties based on the Flesch-Kincaid Grade Level and Flesch Reading Ease indices. CONCLUSIONS: Our findings suggest that current surgical clinical trial consent documents are too long and complex, exceeding the recommended sixth-grade reading level. Ensuring readable clinical trial consent forms is not only ethically responsible but also crucial for protecting patients' rights and well-being by facilitating informed decision-making.

"Uninformed consent" in clinical trials with cancer patients: A qualitative analysis of patients' and support persons' communication experiences and needs.

OBJECTIVE: Cancer patients are often overwhelmed when being informed about clinical trials. However, there is a lack of evidence-based strategies to improve physician-patient communication in this area. This study assessed the experiences and needs of cancer patients and their support persons (SPs) during the informed consent (IC) process prior to participation in clinical trials. METHODS: 17 semi-structured interviews with cancer patients and their SP were conducted and analysed using a framework analysis. RESULTS: Most respondents reported feeling well informed about the clinical trial. However, core aspects of the study were often not understood highlighting a dissonance between perceived and actual recall and understanding. Many participants trusted that the trial recommended was the best available care and only skimmed the consent form or did not read it at all. CONCLUSIONS: This is the first German study to analyse both cancer patients' and SPs' perspectives on IC processes. Although many feel well informed, our results suggest a significant gap in recall and understanding of core components of clinical trials which hinders IC. PRACTICE IMPLICATIONS: Further interventional research is required to improve the consent processes prior to clinical trials in order to provide optimal, patient-centred care.

Randomized study of two different consent procedures on recall: a study within a digital alcohol intervention trial.

INTRODUCTION: Individuals' comprehension of the information provided in consent forms should fundamentally influence whether to participate initially in a study and later whether to remain a participant. Existing evidence, however, suggests that participants do not thoroughly read, comprehend, or recall the information in consent forms. This study aimed to better understand how well participants recalled trial procedure information in the consent materials they received prior to taking part in a trial of a digital alcohol intervention. METHOD: This study was nested within an online effectiveness trial. The study included a contrast between two layout approaches to present the trial procedure information: one where all materials were shown on the same page (One page) and one where participants had to click on links to get materials for certain parts of the study information (Active request). Recall of trial procedures was measured 2 months post-randomization with four questions. Participants were also asked to leave a comment after each question. RESULT: Of the 2437 individuals who registered interest in the parent trial, 1197 were randomized to One page and 1240 were randomized to Active request. Approximately 90% consented to participate and 53% of the participants responded to the recall questionnaire. Contrasting the consent layout showed no marked differences between groups in three out of the four questions on recall of trial procedures. There was, however, evidence that recall of aspects of how personal data would be handled during the trial did differ between the two groups, with the Active request group reporting less recall than the One page group. Free-text comments were used to give nuance to the quantitative analysis. CONCLUSION: Participants exposed to different layouts of trial procedure information exhibited varying levels of information recall 2 months after consenting. The findings highlight the influence of the presentation of consent forms, which should be given attention when designing trials. TRIAL REGISTRATION: ISRCTN ISRCTN48317451. Registered 6 December 2018, https://www.isrctn.com/ISRCTN48317451.

Evaluating the Decisional Capacity for Informed Consent of Transition age Children to Adolescents in Human Subject Research.

This study aimed to evaluate children's capacity for informed consent. We translated into Azerbaijani language and adapted the University of California, San Diego Brief Assessment of Capacity to Consent (UBACC). We enrolled four healthy groups: children aged 11, 12, and 13 years and adults. We provided the participants with information about the simulated research proposal and a related informed consent form. Subsequently, they were administered the UBACC. The mean total UBACC scores were 11.9 (11-year-olds), 12.7 (12-year-olds), 14.0 (13-year-olds), and 16.0 (adults). The gradual increase in the mean UBACC scores with age suggests the continuous maturation of the capacity to comprehend the informed consent process. There was no specific cutoff age to decide whether the children were competent enough to provide informed consent.

Content and Readability of US Procedure Consent Forms.

This qualitative study uses data from the American Hospital Association National Survey Database to analyze the content and readability of a sample of US procedures consent forms.

An absence of translated consent forms limits oncologic clinical trial enrollment for limited English proficiency participants.

OBJECTIVES: A lack of diversity amongst participants in cancer clinical trials has raised scrutiny over the past decade. Patients with limited English proficiency (LEP) are further excluded. One modifiable reason for low LEP participation is a lack of non-English consent forms. METHODS: We queried the clinical trials registry database at an academic hospital serving a predominantly Spanish-speaking patient population. Clinical trials related to gynecology oncology were evaluated for the availability of fully translated Spanish consent forms, the racial and ethnic identification of enrolled patients, and the number of signed Spanish consents. Enrolment data was compared before and after 2019, when institutional financial support for document translation was withdrawn. RESULTS: Sixteen gynecologic oncology clinical trials were opened between 2014 and 2022, with 10 trials enrolling 128 patients. Eight trials opened prior to 2019, all with fully translated consent forms. Seven of these trials enrolled 99 participants, 70% of whom identified as Hispanic and 60% who signed a Spanish consent. Eight trials opened after 2019 and one had a fully translated consent form. Three of the trials enrolled 29 participants, with 10% of subjects identifying as Hispanic and none signing a Spanish consent form. CONCLUSIONS: There was a decrease in fully translated clinical trial consent forms for gynecologic oncology studies following the loss of subsidized translation services in our single institution with a predominantly LEP population. This correlated with a decrease in enrollment of Hispanic subjects. To increase enrollment of diverse participants, including those with LEP, simple actions such as fully translating consent forms would help maintain equity in research conduct and improve clinical outcomes through trial involvement.

Impact of Using a Precompleted Consent Form for Procedural Sedation in the Pediatric Emergency Department.

OBJECTIVES: This study aimed to compare elements discussed during the consent process for procedural sedation in the pediatric emergency department to documentation and parental recall before and after implementation of a standardized consent form. METHODS: This is a mixed-methods study combining retrospective electronic record review and cross-sectional surveys of providers and parents after consent for procedural sedation. Surveys were obtained before and after implementation of a precompleted consent form. Providers' survey responses were compared with consent documentation. Recall of consent elements discussed by linked parent-provider dyads were compared. RESULTS: Six hundred fifty-five encounters were reviewed. Pediatric emergency medicine fellows and pediatric emergency department-based pediatricians were more likely to document any benefit (odds ratio [OR], 1.5; 95% confidence interval [CI], 1.0-2.4) or alternative (OR, 2.7; 95% CI, 1.8-3.9) compared with PEM attendings. Providers were more likely to report discussion of failure to complete the procedure (OR, 7.3; 95% CI, 2.3-23.3) and parents were more likely to recall discussion of this risk (OR, 5.3; 95% CI, 1.0-27.8) in the postintervention group. Based on provider recall, using the precompleted consent form was associated with providers discussing at least 2 of the 3 benefits (84.0% vs 97.2%, P < 0.01), 5 of the 5 risks (31% vs 67.7%, P < 0.01), and improved parental recall of risks (5.7% vs 22.9%, P = 0.03). More providers reported taking less than 1 minute to complete the form in the postimplementation group (12.0% vs 43.7%, P < 0.01). CONCLUSIONS: Implementing a precompleted consent form for procedural sedation was associated with providers reporting decreased time spent completing the consent form and better alignment of key consent elements between reported provider discussion and parental recall.

Generating Informed Consent Documents Related to Blepharoplasty Using ChatGPT.

PURPOSE: This study aimed to demonstrate the performance of the popular artificial intelligence (AI) language model, Chat Generative Pre-trained Transformer (ChatGPT) (OpenAI, San Francisco, CA, U.S.A.), in generating the informed consent (IC) document of blepharoplasty. METHODS: A total of 2 prompts were provided to ChatGPT to generate IC documents. Four board-certified plastic surgeons and 4 nonmedical staff members evaluated the AI-generated IC documents and the original IC document currently used in the clinical setting. They assessed these documents in terms of accuracy, informativeness, and accessibility. RESULTS: Among board-certified plastic surgeons, the initial AI-generated IC document scored significantly lower than the original IC document in accuracy ( p < 0.001), informativeness ( p = 0.005), and accessibility ( p = 0.021), while the revised AI-generated IC document scored lower compared with the original document in accuracy ( p = 0.03) and accessibility ( p = 0.021). Among nonmedical staff members, no statistical significance of 2 AI-generated IC documents was observed compared with the original document in terms of accuracy, informativeness, and accessibility. CONCLUSIONS: The results showed that current ChatGPT cannot be used as a distinct patient education resource. However, it has the potential to make better IC documents when improving the professional terminology. This AI technology will eventually transform ophthalmic plastic surgery healthcare systematics by enhancing patient education and decision-making via IC documents.

Machine learning-based donor permission extraction from informed consent documents.

BACKGROUND: With more clinical trials are offering optional participation in the collection of bio-specimens for biobanking comes the increasing complexity of requirements of informed consent forms. The aim of this study is to develop an automatic natural language processing (NLP) tool to annotate informed consent documents to promote biorepository data regulation, sharing, and decision support. We collected informed consent documents from several publicly available sources, then manually annotated them, covering sentences containing permission information about the sharing of either bio-specimens or donor data, or conducting genetic research or future research using bio-specimens or donor data. RESULTS: We evaluated a variety of machine learning algorithms including random forest (RF) and support vector machine (SVM) for the automatic identification of these sentences. 120 informed consent documents containing 29,204 sentences were annotated, of which 1250 sentences (4.28%) provide answers to a permission question. A support vector machine (SVM) model achieved a F-1 score of 0.95 on classifying the sentences when using a gold standard, which is a prefiltered corpus containing all relevant sentences. CONCLUSIONS: This study provides the feasibility of using machine learning tools to classify permission-related sentences in informed consent documents.