- Preprint Article
- 10.21203/rs.3.rs-8564669/v1
GenAITEd Ghana as a Context-Aware and Curriculum-Aligned Conversational AI Agent for Teacher Education
- Mar 05, 2026
- Research Square
- Matthew Nyaaba + 7 more +7
Publications from 2021 to 2026
Showing 10 of 83 papers
GenAITEd Ghana as a Context-Aware and Curriculum-Aligned Conversational AI Agent for Teacher Education
Abstract PS4-11-10: Patient-centric development of shared decision-making aids: The ASSESS online personalized early breast cancer treatment decision support tool and resource website
Abstract People newly diagnosed with breast cancer spend a considerable amount of time researching their diagnosis, treatment options and associated side effects. Even with access to trusted evidence-based information, such as Susan G. Komen’s About Breast Cancer pages (https://www.komen.org/breast-cancer/), patients and doctors may struggle to account for the many factors in an individual's unique diagnosis that influence treatment and outcomes, making it hard to balance the potential benefits of therapy with the risks of side effects on a personalized basis. The discontinuation of the popular Adjuvant! Online tool compounded this challenge, creating a need for a new, publicly available tool to provide survival estimates for the early-stage breast cancer population in the U.S. To address this, Komen collaborated with teams from MD Anderson and Yale Cancer Centers to develop a web-based decision support tool that provides personalized five-year survival estimates for women with early-stage breast cancer. The tool, ASSESS, uses an algorithm developed with U.S.-based SEER data to estimate outcomes for various systemic adjuvant therapies based on an individual’s clinical and pathological characteristics. The ASSESS online tool was designed and built by a multidisciplinary team of experts, including scientists, clinicians, website developers and marketing professionals, using an iterative approach to incorporate feedback from patient advocates and breast cancer clinicians. Initial design requirements for ASSESS included a simple and engaging user interface and being both public-facing and suitable for use in a clinic as a shared decision-making tool. It was designed to be responsive and support use on multiple devices, incorporating best practices for communicating risks, and offering a summary feature to save and print results.Cognitive interviews were conducted with patient advocates and breast cancer clinicians to inform the design of the tool, resulting in changes that made the interface and results output clearer and more accessible to a lay audience. Once finalized, additional usability testing was conducted with patient advocates and breast cancer medical oncologists to ensure the tool was deployed as intended. Komen hosts the ASSESS tool on komen.org and has developed supporting information to empower those newly diagnosed with breast cancer to make informed decisions by offering tailored treatment options, along with education on each treatment option and how treatment combinations may affect survival. Within the tool, links are provided to Komen-generated and expert-vetted information that describes the significance of each input requested (age at diagnosis, menopause status, molecular subtype, tumor size/grade, etc.). By integrating these resources, the tool empowers patients by providing sound and understandable information, enabling them to be actively involved in their treatment decisions. The ASSESS tool, publicly launching later this year, should help providers visually demonstrate different treatment option outcomes and provide links to accessible information that can be shared with patients for each treatment, including details on how it works, its side effects, and references to the associated expert clinical guidelines. Built using a patient-centered approach, the ASSESS tool supports shared decision-making for people with early-stage breast cancer, helping them make the best individual decisions for their treatment and care. Citation Format: B. A. Kerr, J. D. Alexander, H. Zhao, M. Marczyk, L. C. Crocker, A. A. Erwin, E. Kuhn, H. Baker, S. Vaidhyanath, T. Polischuk, K. A. Sabelko, L. Pusztai, S. H. Giordano, R. J. Volk, G. M. Zinser. Patient-centric development of shared decision-making aids: The ASSESS online personalized early breast cancer treatment decision support tool and resource website [abstract]. In: Proceedings of the San Antonio Breast Cancer Symposium 2025; 2025 Dec 9-12; San Antonio, TX. Philadelphia (PA): AACR; Clin Cancer Res 2026;32(4 Suppl):Abstract nr PS4-11-10.
Read moreAbstract PS5-11-17: An integrative approach to improving outcomes for inflammatory breast cancer (IBC) patients: creating a diagnostic tool, advocating for ICD-10-CM codes, and establishing a task force to address critical research gaps
Abstract Inflammatory Breast Cancer (IBC) is a rare, highly aggressive form of advanced breast cancer that has been historically challenging to diagnose due to its ambiguous clinical nature. A general lack of awareness about IBC within the clinical and patient communities further contributes to delays in diagnosis and treatment. Together, these issues hinder IBC research advancements, leaving patients with limited treatment options and poor prognoses. To address these challenges, Susan G. Komen partnered with IBCRF and the Milburn Foundation to form the IBC Collaborative and launch a multidimensional initiative, aimed at tackling systemic barriers to the advancement of IBC research and care. Early efforts of this initiative prioritized the development of the IBC Scoring System, a quantitative diagnostic scoring rubric for IBC. Available as an easy-to-use online tool (komen.org/ibc-calc), the IBC Scoring System has been steadily gaining global adoption, through the Collaborative’s targeted efforts to raise awareness including dissemination of informational pamphlets for clinician and patient communities. To date, the tool has been used by over 5300 users in more than 100 countries. Additionally, IBC-dedicated clinics, multi-institutional IBC networks and community oncology centers have reported using the tool to support clinical decision making when considering ambiguous patient cases. Recent validation studies have demonstrated that the system can distinguish IBC from non-IBC patients (AUC-ROC 0.84; 95% CI: 0.82 - 0.87) (Lynce et al. JNCI. 2025). Efforts to further enhance the clinical utility of this important diagnostic system are underway and funded by Komen. With a diagnostic system in hand, Komen led advocacy efforts to pursue formal disease recognition through the creation of IBC-specific diagnosis codes. By engaging with the U.S Centers for Disease Control and Prevention (CDC), three unique ICD-10-CM diagnosis codes for IBC (C50.A0, C50.A1, and C50.A2) were approved. Effective October 2025, the widespread utilization of these codes is expected to enhance the ability to track IBC incidence by facilitating inclusion in national health datasets and to improve the coordination of multidisciplinary care for IBC patients. In parallel, a task force was formed to identify current scientific barriers limiting research advancements in IBC and to provide tangible recommendations to address them. Through a series of structured working meetings, three overarching areas emerged as needing significant investigation and investment to drive progress in the biology of IBC: (1) onset and development, (2) detection and monitoring and (3) metastatic dissemination. The group identified a dearth of available IBC tools and resources as key barriers to progress with data silos and the lack of open-access data remaining major obstacles in the field. Additionally, the group prioritized research areas with high potential to improve the understanding and management of IBC. This integrative approach has made significant strides in supporting IBC research, diagnosis and care through the development of a validated diagnostic tool, the establishment of ICD-10-CM codes for IBC, and by defining critical research gaps and prioritizing resolutions. Continued momentum in these areas should ultimately lead to improved outcomes for people with IBC. Citation Format: L. J. Anstine, A. A. Erwin, M. L. Guthrie, H. D. Baker, S. S. Badve, M. L. Alpaugh, K. A. Sabelko, G. M. Zinser. An integrative approach to improving outcomes for inflammatory breast cancer (IBC) patients: creating a diagnostic tool, advocating for ICD-10-CM codes, and establishing a task force to address critical research gaps [abstract]. In: Proceedings of the San Antonio Breast Cancer Symposium 2025; 2025 Dec 9-12; San Antonio, TX. Philadelphia (PA): AACR; Clin Cancer Res 2026;32(4 Suppl):Abstract nr PS5-11-17.
Read moreAbstract PS5-05-18: How Susan G. Komen’s ShareForCures® Research Hub will connect researchers with real-world data shared by breast cancer patients and survivors in the United States
Abstract Background: To optimize care and improve outcomes for all breast cancer patients, multi-modal data need to be integrated with the experiences of patients. However, access to these datasets that reflect the diversity of patients is often limited and siloed within single institutions. To address these challenges, Susan G. Komen® (Komen) launched ShareForCures® (SFC), a direct-to-consumer, online, IRB-approved breast cancer research registry, designed to integrate real-world, longitudinal data from adults who have been diagnosed with breast cancer and live in the United States and to provide this data for research. Methods: We analyzed data from participants who enrolled in SFC within the first two years and developed the SFC Research Hub, which facilitates data exploration, cohort creation and data access application. A taskforce of research experts (clinical oncologists, translational scientists, and research advocates) provided guidance and feedback throughout the development of the SFC Research Hub by completing surveys, meeting with Komen staff, and participating in user testing. Results: From July 2023 to June 2025, 1,214 participants enrolled in SFC (median age = 55 years [range: 27-93], 99% women, 75% non-Hispanic White). Only four participants withdrew after enrollment, resulting in a retention rate of 99.7%. Participants were geographically dispersed across the United States, including Puerto Rico. Most participants received oncology care outside of NCI-designated comprehensive cancer centers and were diagnosed within the past five years. The majority of participants reported their first breast cancer diagnosis as invasive ductal carcinoma (57%), with 39% reporting ER+/HER2- disease. Notably, 18% of participants reported living with metastatic breast cancer (18%) and 14% experienced a recurrence (14%). All participants reported demographic and diagnostic information, and 53% of participants completed additional questionnaires and/or shared saliva samples for germline whole genome sequencing. Medical records were requested for 52% of participants, 30% were retrieved and curated, and 13% have access to a summary of their records in the platform. The SFC Research Hub was designed and developed with end users in mind, offering secure access to integrated, deidentified data shared by SFC participants. To access SFC data, researchers must agree to a code of conduct, acknowledge their institution’s data use agreement with Komen, and receive approval of their data access application describing their research project from Komen. In return, researchers will share their findings with SFC participants. Conclusions: Through SFC, Komen is creating a real-world database that connects researchers with data contributed by participants with diverse experiences. The SFC Research Hub is expected to launch in 2026, enabling researchers to leverage SFC data to enhance our understanding of real-world breast cancer patient experiences, ultimately accelerating discoveries and improving outcomes for all breast cancer patients. Citation Format: K. O. West, J. Epps, E. G. Marks, A. L. Gyden, K. A. Sabelko, M. L. Bondy, J. Jourquin. How Susan G. Komen’s ShareForCures® Research Hub will connect researchers with real-world data shared by breast cancer patients and survivors in the United States [abstract]. In: Proceedings of the San Antonio Breast Cancer Symposium 2025; 2025 Dec 9-12; San Antonio, TX. Philadelphia (PA): AACR; Clin Cancer Res 2026;32(4 Suppl):Abstract nr PS5-05-18.
Read moreIdentifying symptom clusters associated with acute and chronic fatigue in patients with breast cancer treated with neoadjuvant therapy on the I-SPY 2 trial.
271 Background: Many studies have shown that fatigue is associated with poor outcomes such as quality of life and physical function in breast cancer survivors.Early treatment of symptoms that result in persistent fatigue may be a strategy to mitigate long-term fatigue.As a result, we studied symptoms and developed risk estimates for patients that are most likely to develop fatigue by pre-surgery and follow up among patients treated on the I-SPY 2 neoadjuvant trial. I-SPY 2 is a phase-II adaptive trial for high-risk early-stage breast cancer patients. Methods: In this retrospective cohort study of 306 women undergoing neoadjuvant chemotherapy +/- targeted therapy, patients complete electronic surveys of symptoms via 34 PRO-CTCAE items and QOL via 9 PROMIS instruments. Fatigue is collected as part of the PROMIS survey and scored using Health Measures. Study timepoints are screening (SC), weekly study treatment (ST), 12 weeks (12w), pre-surgery (PS) and at 1, 6, 12 and 24 months (FU1-FU4) following surgery. Correlation between symptoms and fatigue at equal timepoints was quantified using spearman correlations and BH-adjusted p-values. For symptom odds analysis, symptoms were binarized such that those that had an average grade of mild or above (severity), rarely or above (frequency) or a little bit or above (interference) between ST weeks 1-6 were considered present. Clinically significant (CS) increase in fatigue was defined as an increase >=0.5 standard deviation (SD) in mean from baseline. Logistic regression was used to determine odds ratios of factors associated with fatigue. Results: Baseline PROMIS fatigue mean score was 47.14 (SD 9.31) with a median of 47.45. A CS increase in fatigue from baseline was seen in 55% of patients at 12w, and 61% of patients pre-surgery. Of the patients that had a CS increase in fatigue at any point prior to surgery, 45.7% had persistent fatigue through FU1-4. Symptoms associated with Fatigue at 12w were shortness of breath, headache, and nausea (P< 0.03). At PS, fatigue was significantly correlated with GI symptoms, neuropathy, and shortness of breath (P< 0.03). Risk estimates for patients that filled out symptom surveys at early timepoints (weeks 1-6) and also had fatigue were evaluated. Patients with early GU (genitourinary) symptoms had higher risk of fatigue at IR (OR=9.33, p=0.02, 88.9% in cases vs 33.3% in controls). Patients with early GI symptoms at PS (OR=8.56, p=0.03, 90.1% vs 50%), or FU2-4 (OR= 5.88 and 7.36, p= 0.04 and 0.02, 80% vs 39.1% and 81.8% vs 36.3%) also had a higher risk of developing fatigue. Conclusions: A CS increase in fatigue during treatment and follow up is seen in the majority of patients and is associated with a large number of persistent symptoms.
Read moreHTA307 Evolving Principles for Defining and Assessing the Economic and Societal Value of Cancer Therapies
Experiences of genetic counselors in referring young and metastatic breast cancer patients to support services: A needs assessment
Die Spreu vom Weizen trennen. : Erklärvideos für den Literaturunterricht mit einem Qualitätsraster auswählen
Podcasts, webquests, wikis, webblogs und vor allem Lern- und Erklärvideos sind heute vielfach als digitale Lernhelfer verbreitet. In Folge der vorangegangenen Schulschließungen im Zuge der Covid-19-Pandemie werden sie nun auch verstärkt im formalen Bildungskontext eingesetzt. So gab in einer forsa-Umfrage unter rund 1000 Lehrer*innen im April 2020 nahezu jede zweite Lehrperson aus dem Sekundarstufenbereich an, Erklärvideos während der Schulschließungen genutzt zu haben (vgl. forsa, 2020). Vor dem Hintergrund der stark differenzierenden Qualität von Lernvideos widmet sich der vorliegende Beitrag der Vorstellung eines empirisch validierten mehrdimensionalen Kriterienrasters. Für die Qualitätsanalyse vereint das Raster fachwissenschaftliche sowie fachdidaktische Kriterien zur Vermittlung gattungstypologischen Wissens zur Kurzgeschichte und mediendidaktische Erkenntnisse zur Qualität von Erklärvideos. (Angehende) Lehrpersonen sollen durch die Arbeit mit dem Raster einerseits für unterschiedliche Qualitätsebenen von Erklärvideos sensibilisiert und dadurch andererseits in ihrer Rolle als Gatekeeper in einer zunehmend digitalisierten Lernwelt gestärkt werden. Bevor die zentralen Dimensionen des Qualitätsrasters und zwei damit verbundene exemplarische Analysen ausführlich vorgestellt werden, gibt der Beitrag einen Überblick zu Lernvideos als Lerngegenstand und problematisiert in einem nächsten Schritt die Notwendigkeit von Qualitätskriterien zu diesen.
Read morePENGEMBANGAN MEDIA KOMIK PADA MATERI KERAGAMAN BUDAYA SISWA KELAS IV SD NEGERI TRANS CIPTODADI MUSI RAWAS
Penelitian ini bertujuan untuk menghasilkan media pembelajaran komik pada materi keragaman budaya pembelajaran IPS siswa kelas IV SD Negeri Trans Ciptodadi yang valid dan praktis. usi Rawas dengan sampel sebanyak 5 siswa untuk uji one to one dan 10 siswa untuk uji small group. Jenis pengembangan yang digunakan adalah jenis pengembangan model 4D (four-D model). Teknik pengumpulan data menggunakan angket validasi ahli bahasa, ahli materi dan angket kepraktisan guru dan siswa. Berdasarkan hasil penelitian dan pengembangan dapat diambil beberapa kesimpulan sebagai berikut 1) Berdasarkan hasil validasi diketahui bahwa Komik berbasis tematik dikategorikan baik dengan persentase kevalidan 79,59% sehingga Komik pada Tema 1 Keberagaman Budaya dikategorikan valid. 2) Kepraktisan Komik di uji coba perorangan atau one to one melibatkan 3 orang siswa yang dipilih secara acak dengan kemampuan yang berbeda dikategorikan baik dengan persentase kepraktisan 82,67% sedangkan uji coba kelompok kecil (small group) melibatkan 10 orang siswa dikategorikan sangat baik dengan persentase 91,33%. Berdasarkan hasil uji coba tersebut diketahui respon siswa dikategorikan baik yang diartikan bahwa Komik Tema 1 Keberagaman Budaya praktis atau mudah untuk digunakan.
Read moreThe impact of reproductive factors on DNA methylation-based telomere length in healthy breast tissue
Estrogen promotes breast tissue proliferation and telomerase activation. We investigated the effects of reproductive history on cell cycling and telomere length using a DNA methylation-based estimate of telomere length (DNAmTL) in breast and blood from healthy women donors. We demonstrate that DNAmTL is shorter in breast than in blood, and that nulliparous women have longer age-adjusted DNAmTL in both breast and blood, potentially explaining their higher risk of breast cancer.
Read more