SGSamiran Ghosh

Samiran Ghosh

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Samiran Ghosh has a total of 92 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Self‐Adapting Priors for Dynamic Borrowing in Three‐Arm Non‐Inferiority Trials With Pre‐Specified Margin

    by Yuansong Zhao, Ying Yuan, Ram Tiwari, Samiran Ghosh

    Non‐inferiority trials play a central role in clinical research by demonstrating that an experimental treatment is not unacceptably worse than an established reference treatment when superiority is unlikely, but the new treatment offers other advantages, such as reduced toxicity, easier administration, lower cost, or improved adherence. These trials are typically designed as active control studies, making historical data from previous clinical trials or real‐world evidence readily available. A key challenge, however, is how to appropriately incorporate multiple heterogeneous historical datasets into the design and analysis of a non‐inferiority trial, as each source may differ in relevance, quality, and similarity to the current study. Moreover, a conventional two‐arm non‐inferiority trial lacks a placebo or standard of care control, requiring the reference treatment effect to be justified using external evidence. When ethically and practically feasible, including a placebo arm allows assessment of assay sensitivity and provides internal validation of the reference treatment effect, thereby strengthening the credibility of the non‐inferiority conclusion. In this article, we propose two novel Bayesian self‐adapting priors, the Additive Self‐Adapting Mixture (ASAM) prior and the Cumulative Self‐Adapting Product (CSAP) prior, to incorporate information from multiple historical reference and placebo studies in three‐arm non‐inferiority trials. The ASAM prior constructs study‐specific priors and combines them through an adaptively weighted mixture, whereas the CSAP prior uses a cumulative product formulation with adaptive study‐specific weights. Both approaches dynamically borrow information by assigning greater weight to historical studies that are more compatible with the current trial while down‐weighting less comparable studies, thereby mitigating the impact of between‐study heterogeneity. Extensive simulation studies demonstrate that the proposed methods maintain appropriate control of the Type I error rate while achieving substantial gains in statistical power, providing a flexible and robust framework for Bayesian analysis of three‐arm non‐inferiority trials.

  • Open Access

    Community and Academic Synergy for Cancer Survivorship Care Delivery Enhancement (Project CASCADE): a study protocol for a pragmatic, stepped-wedge, cluster-randomized trial in Texas primary care community health centers

    by Mary-Louise E. Millett, Lauren Q. Malthaner, Katharine McCallister, Derek W. Craig, Rebecca Eary, Melissa A. Valerio-Shewmaker, L. Aubree Shay, Suja S. Rajan, Hilary Y. Ma, Samiran Ghosh, et al.

    Background: In the United States, over 18 million individuals are living with cancer. The majority of these cancer survivors also manage other chronic conditions and receive care from multiple specialists, including oncology, cardiology, and primary care clinicians. However, it remains unclear who holds primarily responsibility for coordinating their care across specialties. Because of its generalist nature, primary care is uniquely suited to deliver whole-person and coordinated care for all conditions for cancer survivors. However, primary care teams experience many challenges delivering high-quality survivorship care. While integrating care for all conditions including cancer is a core principle of high-quality primary care, few survivorship care delivery interventions have been developed and tested among patients with a history of cancer in primary care panels of community health centers (CHCs). These under- and uninsured cancer survivors experience disproportionately worse health outcomes and often rely solely on CHCs for consistent health care. Methods: Community and Academic Synergy for Cancer Survivorship Care Delivery Enhancement (Project CASCADE) is a theory-driven pragmatic hybrid trial testing implementation and effectiveness of a multi-component primary care-based survivorship care delivery intervention among 8 Texas CHC sites. The specific aims are: Aim 1: Implement a system-level cancer survivorship care delivery intervention in partnership with CHC clinicians, patients, and community representatives, which includes: (1) primary care clinician training in cancer survivorship care through provider-to-provider tele-mentoring, (2) identification and tracking of survivors by modifying existing clinic workflows, and (3) coordinating survivors’ care by designating a care coordinator champion. Practice facilitation and stakeholder engagement strategies will support intervention implementation; Aim 2: Test the effectiveness of the intervention on patient (screening for second primary cancers) and clinician outcomes (clinician knowledge of and confidence in survivorship care) using a stepped-wedge clinic-randomized design; and Aim 3: Evaluate implementation using a mixed-methods approach guided by the Practice Change Model. We will utilize electronic health record (EHR), survey, interview, and observation data to assess effectiveness and implementation outcomes. Discussion: Findings will inform a scalable, generalist primary care-based survivorship care model to enhance care delivery and outcomes in CHCs serving vulnerable populations. This study represents a critical step toward addressing gaps in cancer survivorship research and achieving equitable care for all survivors. Trial registration: This study is registered under clinical trial registration number NCT06883838; 2025–03-12.


  • Open Access

    Developing eHealth Interventions to Improve Diabetes Management in Emerging Adulthood: Qualitative Formative Study

    by April Idalski Carcone, Deepika Baskar, Aishah Mahmood, Karen MacDonell, Susan Eggly, Samiran Ghosh, Colleen Buggs-Saxton, Steven J Ondersma, Deborah A Ellis

    Background: Emerging adulthood is a high-risk period during which many with type 1 diabetes demonstrate suboptimal diabetes management and glycemic control. There is a need for effective, scalable interventions designed specifically for this population. Technology-based approaches are readily accessible to this age group. Furthermore, interventions consistent with self-determination theory—which posits that the fulfillment of psychological needs for autonomy, self-efficacy, and relatedness promotes intrinsic motivation for change—may resonate well with emerging adults’ developmental needs for establishing independence and autonomy, and growing their social network. Objective: This study aimed to enhance the potential relevance, sustainability, and efficacy of 3 self-determination theory–informed mobile health intervention components and content for emerging adults with type 1 diabetes. Key areas of interest included emerging adults’ perspectives on the use of cultural tailoring, developmental relevance of content, and delivery preferences. Methods: In this qualitative formative study, 20 emerging adults reviewed and provided feedback on 3 newly developed intervention components via individual interviews. Ten reviewed the motivation enhancement system, a 2-session counseling intervention grounded in motivational interviewing and designed to enhance emerging adults’ autonomy and self-efficacy for diabetes self-management. Ten reviewed the SMS text messaging reminder intervention (one-way text message reminders to complete diabetes care) and the question prompt list (a list of questions related to diabetes care designed to increase patients’ active participation during medical visits). Interviews were analyzed using framework matrix analysis, an efficient approach to inductive thematic analysis. Results: Emerging adults found all 3 interventions acceptable and helpful. They noted the interventions’ integration into the technology they already use as a strength. Across interventions, emerging adults also expressed a preference for culturally tailored intervention content, including intervention examples, actors, and language representing their illness experience, identity, and personal preferences. Intervention-specific feedback suggested emerging adults liked motivation enhancement system intervention elements that were engaging (videos) and relatable (peer testimonials), and supported their growing autonomy and independence. For SMS text messaging reminders, emerging adults appreciated the straightforward nature of the reminders and recommended more directive messages. They appreciated the range of topics and variety of messages. Suggestions included making the messages more impactful (eg, direct, personalized, and engaging, such as using emojis). Emerging adults saw the question prompt list content areas as relevant and well-aligned with their concerns highlighting the topic of transitioning to adult life with diabetes as particularly salient. Conclusions: Emerging adult feedback supports the acceptability and use of these intervention components and will be used to refine the interventions. Feedback was especially positive regarding cultural and other tailoring efforts, as well as content directed at their pending transition to full independence. At the same time, their input suggests the need for multiple specific modifications, highlighting the importance of intensive and detailed feedback from end users.


  • Open Access

    Penalized K-Means Clustering: Another Look at Its Statistical Properties

    by Prithish Banerjee, Shreyo Ghosh, Samiran Ghosh

    Unsupervised learning is a major class of machine learning techniques where response information is missing or unavailable. Among these techniques, clustering plays a central role by grouping objects based on a chosen similarity measure. K-Means is one of the most established and widely used clustering methods, known for its simplicity and computational efficiency. For continuous data, K-Means performs well when the number of clusters ( K ) is known and correctly specified. However, it faces convergence and overfitting challenges when K is unknown. These issues stem from K-Means’ objective function, which monotonically decreases as the number of clusters increases—leading to a tendency to overfit. In this article, we propose an augmented K-Means algorithm that introduces a penalized version of the standard K-Means objective, designed to guard against overfitting and promote model parsimony when K is unknown. We establish key optimality properties of both the traditional K-Means loss function and the proposed penalty term. Extensive simulation studies on benchmark datasets demonstrate the improved performance of the proposed method, including accurate identification of the true number of clusters. Extensive simulation studies on benchmark datasets demonstrate the improved performance of the proposed method, including accurate identification of the true number of clusters. Additionally, we apply our approach to the clustering of globular galaxy datasets—an example of truly large-scale (“Big”) data—to further illustrate its effectiveness.


  • Open Access

    Developing eHealth Interventions to Improve Diabetes Management in Emerging Adulthood: A Qualitative Formative Study (Preprint)

    by April Idalski Carcone, Deepika Baskar, Aishah Mahmood, Karen MacDonell, Susan Eggly, Samiran Ghosh, Colleen Buggs-Saxton, Steven J. Ondersma, Deborah A. Ellis

    BACKGROUND Emerging adulthood is a high-risk period during which many with type 1 diabetes (T1D) demonstrate suboptimal diabetes management and glycemic control. There is a need for effective and scalable interventions designed specifically for this population. Technology-based approaches are readily accessed by this age group. Further, interventions that are consistent with self-determination theory (SDT) – which posits the fulfillment of psychological needs for autonomy, self-efficacy, and relatedness promote intrinsic motivation for change – may resonate well with emerging adults’ (EAs) developmental needs for establishing independence, autonomy, and growing their social network. OBJECTIVE To gather patient feedback on three SDT-informed mHealth interventions for EAs with T1D: a Motivational Interviewing-based counseling intervention, one-way text message reminders to complete diabetes care, and a question prompt tool to empower EAs to actively participate during medical visits. METHODS In this qualitative formative study, 20 EAs reviewed and provided feedback on the newly developed interventions via individual interviews. Interviews were analyzed using Framework Matrix Analysis, an efficient approach to inductive thematic analysis. RESULTS EAs provided high ratings for intervention acceptability and helpfulness. EAs appreciated the technology-based approach and the tailoring to their demographic characteristics, illness experiences, and personal preferences. They also highlighted SDT-related intervention elements that aligned with SDT. Recommendations for intervention improvement included additional tailoring to personal preferences including the frequency and duration of intervention, intervention content, and personalizing reminders with the recipient’s name. CONCLUSIONS EA feedback supports the acceptability and utility of this intervention and will be used to refine the interventions. The unique contribution of each intervention to improvements in glycemic control will be tested in a randomized controlled trial using the multiphase optimization strategy (MOST) to build the most efficacious multicomponent intervention. CLINICALTRIAL N/A

  • Sample size determinations in four-level longitudinal cluster randomized trials with random slope

    by Priyanka Majumder, Siuli Mukhopadhyay, Bo Wang, Samiran Ghosh

    Cluster or group randomized trials (CRTs) are increasingly used for behavioral as well as system-level interventions in many areas e.g. medicine, psychotherapy, policy, and health service research etc. Sample size determination for each level at the design stage is always a key requirement for any intervention trial including CRT. This work addresses this important issue for a four-level longitudinal CRT via detecting the intervention effect over time. A random intercept and random slope mixed effects linear regression model, including a time-by-intervention interaction is used for modeling. Closed-form expression of the power function and sample size for each level are determined to detect the interaction effect. Other than statistical power consideration, several other factors need attention while designing such CRTs. Optimal allocations accounting for subject attrition and cost constraints have been determined here. How sample size determination based on fixed and random slope models affects when between-subject variations in outcome are anticipated to be significant is also studied. The effect of ignoring cluster levels in a four-level CRT, which is often the case in the absence of an appropriate four-level model, is studied in details. Lastly, the proposed model is illustrated via a real-life human immunodeficiency virus prevention study conducted in the Bahamas.


  • A framework for testing non-inferiority in a three-arm, sequential, multiple assignment randomized trial

    by Erina Paul, Bibhas Chakraborty, Alla Sikorskii, Samiran Ghosh

    Sequential multiple assignment randomized trial design is becoming increasingly used in the field of precision medicine. This design allows comparisons of sequences of adaptive interventions tailored to the individual patient. Superiority testing is usually the initial goal in order to determine which embedded adaptive intervention yields the best primary outcome on average. When direct superiority is not evident, yet an adaptive intervention poses other benefits, then non-inferiority testing is warranted. Non-inferiority testing in the sequential multiple assignment randomized trial setup is rather new and involves the specification of non-inferiority margin and other important assumptions that are often unverifiable internally. These challenges are not specific to sequential multiple assignment randomized trial and apply to two-arm non-inferiority trials that do not include a standard-of-care (or placebo) arm. To address some of these challenges, three-arm non-inferiority trials that include the standard-of-care arm are proposed. However, methods developed so far for three-arm non-inferiority trials are not sequential multiple assignment randomized trial-specific. This is because apart from embedded adaptive interventions, sequential multiple assignment randomized trial typically does not include a third standard-of-care arm. In this article, we consider a three-arm sequential multiple assignment randomized trial from an National Institutes of Health-funded study of symptom management strategies among people undergoing cancer treatment. Motivated by that example, we propose a novel data analytic method for non-inferiority testing in the framework of three-arm sequential multiple assignment randomized trial for the first time. Sample size and power considerations are discussed through extensive simulation studies to elucidate our method.

  • Open Access

    Survivorship Care for Women Living With Ovarian Cancer: Protocol for a Randomized Controlled Trial

    by Elizabeth Kvale, Farya Phillips, Samiran Ghosh, Jayanthi Lea, Claire Hoppenot, Anthony Costales, Jan Sunde, Hoda Badr, Eberechi Nwogu-Onyemkpa, Nimrah Saleem, et al.

    Background: Ovarian cancer ranks 12th in cancer incidence among women in the United States and 5th among causes of cancer-related death. The typical treatment of ovarian cancer focuses on disease management, with little attention given to the survivorship needs of the patient. Qualitative work alludes to a gap in survivorship care; yet, evidence is lacking to support the delivery of survivorship care for individuals living with ovarian cancer. We developed the POSTCare survivorship platform with input from survivors of ovarian cancer and care partners as a means of delivering patient-centered survivorship care. This process is framed by the chronic care model and relevant behavioral theory. Objective: The overall goal of this study is to test processes of care that support quality of life (QOL) in survivorship. The specific aims are threefold: first, to test the efficacy of the POSTCare platform in supporting QOL, reducing depressive symptom burden, and reducing recurrence worry. In our second aim, we will examine factors that mediate the effect of the intervention. Our final aim focuses on understanding aspects of care platform design and delivery that may affect the potential for dissemination. Methods: We will enroll 120 survivors of ovarian cancer in a randomized controlled trial and collect data at 12 and 24 weeks. Each participant will be randomized to either the POSTCare platform or the standard of care process for survivorship. Our population will be derived from 3 clinics in Texas; each participant will have received some combination of treatment modalities; continued maintenance therapy is not exclusionary. Results: We will examine the impact of the POSTCare-O platform on QOL at 12 weeks after intervention as the primary end point. We will look at secondary outcomes, including depressive symptom burden, recurrence anxiety, and physical symptom burden. We will identify mediators important to the impact of the intervention to inform revisions of the intervention for subsequent studies. Data collection was initiated in November 2023 and will continue for approximately 2 years. We expect results from this study to be published in early 2026. Conclusions: This study will contribute to the body of survivorship science by testing a flexible platform for survivorship care delivery adapted for the specific survivorship needs of patients with ovarian cancer. The completion of this project will contribute to the growing body of science to guide survivorship care for persons living with cancer. Trial Registration: ClinicalTrials.gov NCT05752448; https://clinicaltrials.gov/study/NCT05752448 International Registered Report Identifier (IRRID): PRR1-10.2196/48069


  • Open Access

    Survivorship Care for Women Living With Ovarian Cancer: Protocol for a Randomized Controlled Trial (Preprint)

    by Elizabeth Kvale, Farya Phillips, Samiran Ghosh, Jayanthi Lea, Claire Hoppenot, Anthony Costales, Jan Sunde, Hoda Badr, Eberechi Nwogu-Onyemkpa, Nimrah Saleem, et al.

    BACKGROUND Ovarian cancer ranks 12th in cancer incidence among women in the United States and 5th among causes of cancer-related death. The typical treatment of ovarian cancer focuses on disease management, with little attention given to the survivorship needs of the patient. Qualitative work alludes to a gap in survivorship care; yet, evidence is lacking to support the delivery of survivorship care for individuals living with ovarian cancer. We developed the POSTCare survivorship platform with input from survivors of ovarian cancer and care partners as a means of delivering patient-centered survivorship care. This process is framed by the chronic care model and relevant behavioral theory. OBJECTIVE The overall goal of this study is to test processes of care that support quality of life (QOL) in survivorship. The specific aims are threefold: first, to test the efficacy of the POSTCare platform in supporting QOL, reducing depressive symptom burden, and reducing recurrence worry. In our second aim, we will examine factors that mediate the effect of the intervention. Our final aim focuses on understanding aspects of care platform design and delivery that may affect the potential for dissemination. METHODS We will enroll 120 survivors of ovarian cancer in a randomized controlled trial and collect data at 12 and 24 weeks. Each participant will be randomized to either the POSTCare platform or the standard of care process for survivorship. Our population will be derived from 3 clinics in Texas; each participant will have received some combination of treatment modalities; continued maintenance therapy is not exclusionary. RESULTS We will examine the impact of the POSTCare-O platform on QOL at 12 weeks after intervention as the primary end point. We will look at secondary outcomes, including depressive symptom burden, recurrence anxiety, and physical symptom burden. We will identify mediators important to the impact of the intervention to inform revisions of the intervention for subsequent studies. Data collection was initiated in November 2023 and will continue for approximately 2 years. We expect results from this study to be published in early 2026. CONCLUSIONS This study will contribute to the body of survivorship science by testing a flexible platform for survivorship care delivery adapted for the specific survivorship needs of patients with ovarian cancer. The completion of this project will contribute to the growing body of science to guide survivorship care for persons living with cancer. CLINICALTRIAL ClinicalTrials.gov NCT05752448; https://clinicaltrials.gov/study/NCT05752448 INTERNATIONAL REGISTERED REPORT PRR1-10.2196/48069