Individual Clients Research Articles

Lessons From the Design and Rollout of an Electronic Medical Record System for Cervical Cancer Screening in Rwanda.

In its commitment to delivering comprehensive women's cancer early detection services, the Rwanda Ministry of Health rolled out a new cervical cancer screening program. The paper-based medical record system that tracked clients at different points in the continuum of cervical cancer care had challenges with storing data, accessing client information for follow-up visits, and fragmenting information on individual clients. To support the rollout of the new cervical cancer screening program, a new electronic medical record system was designed and implemented to ensure clients were followed along the complete continuum of care. We document the development and implementation of the electronic medical record system and highlight challenges and lessons learned during implementation. Implementation took a participatory approach to ensure that the electronic medical record system was efficient in tracking clients along the continuum of care. At every stage, a wide range of stakeholders were engaged, including clinicians, program managers, and software developers. Health facility visits and conversations were conducted with health care providers and data managers to review the existing system and ensure that the design and development of the electronic record system were suitable for the context in which it would be used. Cervical cancer screening sites are currently using the electronic medical record system to document client information and track women along the continuum of care to reduce loss to follow-up. The system has been rolled out to all newly activated screening sites as part of national scale-up. Planning, collaboration, and adaptability were the key factors in this system's successful rollout and should be the foundation of future data systems development.

Unlocking success: The power of critical thinking in the group facilitation, coaching and team meetings

The absence of a unique and coordinated effort to adapt the promoting of the old philosophical principle to the present need of the people has inspired me to come up with a possible viable solution that I present for your further consideration. I propose two main ideas as the objectives of the paper that, later on, the reader can evaluate which is the best approach to maximize the usage of philosophical services and consulting for the general public. The first idea is to present the impact of mixt approaches between critical thinking and group coaching or group facilitating and the second idea is to target the companies as priority clients and their providers as secondary clients. I present three conflicts, five perspectives and two instruments that can be enhanced by elements of critical thinking in order to achieve the objectives above. What is the utility of philosophical skills in other fields and how should we promote philosophical practice so that philosophy can return to the people in the agora. What I propose is to focus on a bigger market - the profitable companies around us that could provide a big steady source of income - and to look at the other suppliers of services as therapy, coaching, training as partners and not as competitors. These suppliers could and should also become our paying clients and we should work with all of them and not compete against them for some individual residual clients. The practical applications from using philosophical skills in other fields are: controlling emotions using elements of critical thinking, facilitating or managing groups using philosophical counseling principles, increasing communication skills using elements of critical thinking skills, increasing coaching methods using elements of critical thinking skills and facilitating better meetings using elements of critical thinking. It doesn’t matter who was first - Philosophical Practice, critical thinking or coaching, mentoring, therapy or any other. We all know that philosophy was the root of all scientific branches that exist in our days. What really matters is whether all of these approaches can help each other grow and change people’s lives and the way they think about themselves and the world.

Perfednilm: a practical personalized federated learning-based non-intrusive load monitoring

Non-Intrusive Load Monitoring (NILM) is a valuable technique for breaking down overall power consumption into the energy usage of individual appliances. Understanding power usage patterns through NILM plays an important role in reducing energy costs and achieving carbon reduction goals. However, privacy concerns often deter consumers from sharing their electricity consumption data. To address these privacy concerns, Federated Learning (FL) has been introduced in NILM, which enables the training of NILM models while keeping power consumers’ data locally. However, FL’s reliance on a single global model leads to poor performance on clients with unique power consumption patterns. In response to this challenge, we present a Personalized Federated Learning NILM algorithm (PerFedNILM), a practical personalized FL approach for NILM. PerFedNILM limits the local update bias across clients and trains personalized models for individual clients to improve load-monitoring performance. In addition, it mitigates the negative impact of client dropout, which is a common issue in practice. Our experiments on using real-world energy data demonstrate that PerFedNILM outperforms previous FL-based NILM methods, especially in client dropout scenarios.

Beyond Birth Work: Addressing Social Determinants of Health With Community Perinatal Support Doulas.

Adverse maternal and infant health outcomes among African Americans are increasingly recognized as indicators of a critical public health crisis in the United States. Research has found that stress is related to structural racism and the social determinants of health (SDOH) that cause avoidable, unfair inequities in resources, education, power, and opportunities across ethnic groups. This paper describes the SDOH needs and experiences of pregnant Black women from the perspective of doulas and Birthing Beautiful Communities (BBC) clients. The design was a qualitative description, using data collected over time (2017-2018, 2020-2021, and 2023). This study took place in Cleveland and Akron, Ohio and the sample included 58 clients, 26 doulas, and 2 resource intake specialist assistants (RISAs). Qualitative data included individual client interviews, three doula focus groups, and one interview with two BBC RISAs. Three coders used content analysis to deductively identify SDOHs and calculate the number of interviews that contained information about specific SDOHs. Although the sample reported issues with all SDOH, particular ones caused a cascade of SDOH effects. Transportation issues, for example, impeded women from being able to make it to work, doctor's appointments, and to purchase essential baby items (e.g., food, infant supplies). An inability to work-whether because of transportation challenges or pregnancy-related health complications-led to unstable housing and an inability to deal with transportation challenges. Many clients mentioned that housing was a major issue, with many clients experiencing housing instability. Implications include ensuring SDOH information is collected from a trusted source who can advocate and ensure access to a wide range of local resources, ensuring policies protect pregnant women from experiencing a cascade of SDOH that may contribute to continuing health disparate infant and maternal health outcomes in African American women.

Teaching and learning rural governance in law schools: an account of an experiment with clinical legal education

ABSTRACT Clinical legal education (CLE) strives to develop competent and socially relevant legal professionals who can render legal services to the masses. Clinics are largely known to focus on the needs of individual clients as opposed to imparting community legal education. However, a growing body of literature suggests that clinics must focus more on social justice lawyering. This article aims at contributing to this emerging body of work. The Rural Governance, Justice, and Citizen Participation clinic elective course (course) has been taught at the O.P. Jindal Global University by the lead author of this article since 2010. The co-author of this article was a student in the inaugural batch of the course. The course aims at familiarising students with the growing “disconnect” between the promise and reality of law. The authors recommend that the guarantee of “equal access to justice” can be achieved as follows: (i) law schools must offer clinical courses focused on rural communities; (ii) the Bar Council of India must introduce clinical courses that focus on the legal needs of rural communities; and (iii) law schools must adopt a “good practices” framework for teaching community-centric clinical courses to empower rural communities.

A personalized federated learning method based on the residual multi-head attention mechanism

Federated Learning (FL) is a distributed machine learning technique for training machine learning models across multiple clients collaboratively. It allows multiple local devices to cooperatively train global models without compromising data privacy or necessitating extensive data transfer. However, the inherent data heterogeneity across clients poses a challenge, as a single global model trained through FL struggles to adapt to the diverse distributions present in individual client data. This discrepancy leads to a marked decline in model accuracy, slows down FL convergence, and even makes FL divergent. To this end, this paper proposes a method termed Residual Attention for Federated Learning (RAFL), aimed at personalized federated learning (PFL) by applying a residual multi-head attention mechanism to enrich personalized feature information. Additionally, it leverages a global category embedding layer to learn global feature information. In order to evaluate our proposed method's effectiveness, we perform extensive experiments on three benchmark datasets, comparing it with eight benchmark methods. The experimental results demonstrate that RAFL has better personalized learning capability compared to the other benchmark methods. On three benchmark datasets, RAFL achieves the highest accuracy. Notably, the accuracy is about two and a half percentage points higher than the current sota PFL methods.

Concerns, Worries, and Fears During Pregnancy in Active-Duty United States Air Force Families.

There are no published studies on pregnancy-related concerns, worries, and fears (CWFs) in primiparous and multiparous women and men in U.S. Air Force (USAF) families. Reflecting a biopsychosocial model of behavioral health, women's and men's pregnancy-related CWF Questionnaires were developed. Usable data were obtained from 260 women and 243 men in USAF families. Similarities and differences in pregnancy-related CWFs were found when USAF and general population data were compared. The present findings can inform not only the general provision of pregnancy health-related services but also USAF secondary prevention pregnancy-related programs (e.g., USAF nurse home visiting programs for first-time parents). If CWF Questionnaires are individually administered, the information can be used to tailor services to individual client needs.

Exploring the Impact of Therapeutic Presence on Working Alliance in Metaverse Counseling

This study investigated the role of a therapeutic presence in metaverse counseling, considering the growing interest in virtual reality psychotherapy. To examine the relationship between therapeutic presence and working alliance over time in metaverse counseling, we conducted a multilevel analysis with sessions at level 1, clients at level 2, and therapists at level 3. The dataset consisted of 75 sessions, nested within 25 clients and seven therapists. The study revealed that therapeutic presence positively affected the working alliance, at the between-sessions (within individual clients) and between-clients levels (across different clients). The findings also indicated that, during the early stages of treatment, a higher level of therapeutic presence in a session was associated with a stronger working alliance for that particular session. The final model explained approximately 45% of the working alliance variance. The implication for the potential influence of a therapeutic presence was discussed particularly during the initial sessions of metaverse counseling.

Effects of Therapy at a Community Based Trauma Therapy Service Treating Child Abuse and Neglect: A Pre-Post Study Using Administrative Data

This repeated-measures study examined the effects of a hybrid of Trauma-Focused Cognitive Behavioural Therapy (TF-CBT) with other therapeutic approaches at a community-based clinic in Perth Western Australia among a sample of children and young people overwhelmingly experiencing multiple forms of maltreatment and with complex family situations (i.e., family and domestic violence, parental mental health, parental substance abuse). Drawing on 1713 individual client records from between 2017 and 2020, the researchers identified 113 children and young people with viable pre-post treatment assessments including 78 on the TSCC, 36 on the TSCYC, and 12 on the CBCL. Significant improvements on most clinical scales were identified on the TSCC and TSCYC. Sub-analysis of the TSCC results found no differences across gender, age, care status, therapy funding source, and the presence of sexual abuse in the rate of improvement on trauma symptoms. Overall, the study highlights that integrating different therapy approaches for populations with multiple and complex trauma symptoms accessing community-based services can be useful for supporting the delivery of TF-CBT for difficult to treat populations.

FedGCR: Achieving Performance and Fairness for Federated Learning with Distinct Client Types via Group Customization and Reweighting

To achieve better performance and greater fairness in Federated Learning (FL), much of the existing research has centered on individual clients, using domain adaptation techniques and redesigned aggregation schemes to counteract client data heterogeneity. However, an overlooked scenario exists where clients belong to distinctive groups, or, client types, in which groups of clients share similar characteristics such as device specifications or data patterns. Despite being common in group collaborations, this scenario has been overlooked in previous research, potentially leading to performance degradation and systemic biases against certain client types. To bridge this gap, we introduce Federated learning with Group Customization and Reweighting (FedGCR). FedGCR enhances both performance and fairness for FL with Distinct Client Types, consisting of a Federated Group Customization (FedGC) model to provide customization via a novel prompt tuning technique to mitigate the data disparity across different client-types, and a Federated Group Reweighting (FedGR) aggregation scheme to ensure uniform and unbiased performances between clients and between client types by a novel reweighting approach. Extensive experiment comparisons with prior FL methods in domain adaptation and fairness demonstrate the superiority of FedGCR in all metrics, including the overall accuracy and performance uniformity in both the group and the individual level. FedGCR achieves 82.74% accuracy and 12.26(↓) in performance uniformity on the Digit-Five dataset and 81.88% and 14.88%(↓) on DomainNet with a domain imbalance factor of 10, which significantly outperforms the state-of-the-art. Code is available at https://github.com/celinezheng/fedgcr.

FedFixer: Mitigating Heterogeneous Label Noise in Federated Learning

Federated Learning (FL) heavily depends on label quality for its performance. However, the label distribution among individual clients is always both noisy and heterogeneous. The high loss incurred by client-specific samples in heterogeneous label noise poses challenges for distinguishing between client-specific and noisy label samples, impacting the effectiveness of existing label noise learning approaches. To tackle this issue, we propose FedFixer, where the personalized model is introduced to cooperate with the global model to effectively select clean client-specific samples. In the dual models, updating the personalized model solely at a local level can lead to overfitting on noisy data due to limited samples, consequently affecting both the local and global models’ performance. To mitigate overfitting, we address this concern from two perspectives. Firstly, we employ a confidence regularizer to alleviate the impact of unconfident predictions caused by label noise. Secondly, a distance regularizer is implemented to constrain the disparity between the personalized and global models. We validate the effectiveness of FedFixer through extensive experiments on benchmark datasets. The results demonstrate that FedFixer can perform well in filtering noisy label samples on different clients, especially in highly heterogeneous label noise scenarios.

Robust Distributed Gradient Aggregation Using Projections onto Gradient Manifolds

We study the distributed gradient aggregation problem where individual clients contribute to learning a central model by sharing parameter gradients constructed from local losses. However, errors in some gradients, caused by low-quality data or adversaries, can degrade the learning process when naively combined. Existing robust gradient aggregation approaches assume that local data represent the global data-generating distribution, which may not always apply to heterogeneous (non-i.i.d.) client data. We propose a new algorithm that can robustly aggregate gradients from potentially heterogeneous clients. Our approach leverages the manifold structure inherent in heterogeneous client gradients and evaluates gradient anomaly degrees by projecting them onto this manifold. This algorithm is implemented as a simple and efficient method that accumulates random projections within the subspace defined by the nearest neighbors within a gradient cloud. Our experiments demonstrate consistent performance improvements over state-of-the-art robust aggregation algorithms.

High-Fidelity Gradient Inversion in Distributed Learning

Distributed learning frameworks aim to train global models by sharing gradients among clients while preserving the data privacy of each individual client. However, extensive research has demonstrated that these learning frameworks do not absolutely ensure the privacy, as training data can be reconstructed from shared gradients. Nevertheless, the existing privacy-breaking attack methods have certain limitations. Some are applicable only to small models, while others can only recover images in small batch size and low resolutions, or with low fidelity. Furthermore, when there are some data with the same label in a training batch, existing attack methods usually perform poorly. In this work, we successfully address the limitations of existing attacks by two steps. Firstly, we model the coefficient of variation (CV) of features and design an evolutionary algorithm based on the minimum CV to accurately reconstruct the labels of all training data. After that, we propose a stepwise gradient inversion attack, which dynamically adapts the objective function, thereby effectively and rationally promoting the convergence of attack results towards an optimal solution. With these two steps, our method is able to recover high resolution images (224*224 pixel, from ImageNet and Web) with high fidelity in distributed learning scenarios involving complex models and larger batch size. Experiment results demonstrate the superiority of our approach, reveal the potential vulnerabilities of the distributed learning paradigm, and emphasize the necessity of developing more secure mechanisms. Source code is available at https://github.com/MiLab-HITSZ/2023YeHFGradInv.

MiniPFL: Mini federations for hierarchical personalized federated learning

Personalized federated learning trains personalized models tailored to meet individual client’s specific data distributions. However, global models often introduce irrelevant information into personalized models, reducing communication efficiency and accuracy. We propose MiniPFL, a bi-component framework that selectively prioritizes valuable clients for personalized learning. The first component, a shallow layer holds information that is similar across clients, making it ideal for managing traditional federated aggregations. The second component, a deep layer, harbors more personalized information and allows identifying beneficial clients through mini-federations. Extensive experiments on CIFAR-10, CIFAR-100, and Tiny-Imagenet datasets using the Resnet18 architecture in Pytorch demonstrated that MiniPFL reduces communication rounds by 30% and increases accuracy by 2.7% compared to state-of-the-art methods.

Clinical Insights Into the Use of Speech Amplification Devices for Managing Hypophonia: Interviews With Speech-Language Pathologists.

The purpose of this qualitative interview study was to identify themes regarding considerations in the usage of speech amplification device usage for people with Parkinson's disease (PD) and hypophonia from the perspective of speech-language pathologists (SLPs). Eligible participants included SLPs currently practicing in the United States or Canada with experience working with clients with PD for at least 2 years. Ten SLPs participated in 60-min interviews conducted via Zoom. A semistructured interview guide was created prior to the interviews. The interviews were transcribed following their completion, and an iterative coding process was used to identify themes using thematic analysis. Three main themes were identified from the interviews. The first theme encapsulated how clinicians described amplification devices as a potential treatment tool, which highlighted the nuances that may impact selecting an amplification device as a treatment option such as increased hypophonia or dysarthria severity and cognitive decline. The second theme highlighted how device selection depends on the individual needs of the user. Individual client characteristics (such as disease symptoms and individual needs and preferences) may impact the choice of amplification device. The last theme outlined the importance of involving family members in all stages of device use and involving other health care team members on a case-by-case basis. The insights provided by the SLP participants help to understand the clinical decisions that are made when determining device candidacy, selecting a device, and evaluating device success. These insights can be used to improve research studies of augmentative management of hypophonia and guide more personalized management decisions.

Privacy preserving and secure robust federated learning: A survey

SummaryFederated learning (FL) has emerged as a promising solution to address the challenges posed by data silos and the need for global data fusion. It offers a distributed machine learning framework with privacy‐preserving features, allowing model training without the need to collect user data. However, FL also presents significant security and privacy threats that hinder its widespread adoption. The requirements of privacy and security in FL are inherently conflicting. Privacy necessitates the concealment of individual client updates, while security requires the disclosure of client updates to detect anomalies. While most existing research focused on the privacy and security aspects of FL, very few studies have addressed the compatibility of these two demands. In this work, we aim to bridge this gap by proposing a comprehensive defense scheme that ensures privacy, security, and compatibility in FL. We categorize the existing literature into two key directions: privacy defense and security defense. Privacy defense includes methods based on additive masks, differential privacy, homomorphic encryption, and trusted execution environment, whereas security defense encompasses distance‐, performance‐, clustering‐, and similarity‐based anomaly detection techniques and statistical information‐based anomaly update bypassing techniques when the server is trusted and privacy‐compatible anomaly update detection techniques when the server is not trusted. In addition, this article presents decentralized FL solutions based on blockchain. For each direction, we discuss specific technical solutions, their advantages, and disadvantages. By evaluating various defense methods, we identify the most suitable approach to address the primary challenge of “achieving a secure and robust FL system against malicious adversaries while protecting users' privacy.” We then propose a theoretical reference framework for end‐to‐end protection of privacy and security in FL for the key problem, which summarizes the attack surface of FL systems from the client to the server under the security model where the client and server are malicious. Leveraging the strengths and characteristics of existing schemes, our proposed framework integrates multiple techniques to strike a balance between privacy, usability, and efficiency. This framework serves as a valuable reference and provides insights for future work in the field. Finally, we also provide recommendations for future research directions in this field.

Evaluating the Educational Experience of Physiotherapy Students Using the Fitness and Mobility Exercise (FAME) Programme to Learn about Neurological Conditions: An Exploratory Study.

Group exercise has the potential to be a cost-effective way to improve functional outcomes for those living with neurological injury. Leading group exercise is a foundational competency for entry-to-practice for physiotherapy students. The overall objective of this study was to examine the student experience of using the Fitness and Mobility Exercise (FAME) programme to learn about neurological conditions in a group setting. Sixteen physiotherapy students filled out a single point in time survey at the end of their placement during which they had the opportunity to use FAME with their clients twice a week. The survey had Likert and open-ended questions and demographic information. Likert responses were calculated as means. Open-ended questions were analyzed using thematic analysis. The Likert questions were answered with almost entirely positive results. The main themes from the open-ended questions were how to personalize the class, characteristics of individual clients shape the class experience and factors that make the class successful. Overall, the physiotherapy students found using FAME to be a positive experience. From the student perspective, using FAME during placement was an effective way to learn about neurological conditions as well as to develop skills to manage a group exercise class.

“It’s About Going From Good to Great”: Expert Approaches to Conducting a First Sport Psychology Session

The aim of this study was to investigate expert practitioners’ approaches to conducting a first sport psychology session with individual clients as there is sparse empirical literature on this topic. Nine expert Certified Mental Performance Consultants completed a semistructured interview where they discussed experiences conducting a first meeting with an athlete. Primary objectives included establishing the relationship, setting guidelines and expectations, understanding the client’s background, identifying presenting concerns, and formulating the treatment plan and building skills. Building rapport was an aspect used to establish the relationship while discussing confidentiality was utilized to set guidelines. Important strategies employed to increase the perceived benefits to services included conveying the consulting approach and philosophy. Lessons learned centered around doing too much and not appreciating individual differences of clients. Findings show expert consultants aim to achieve similar broad objectives in the first session and provide a basis for best practices in this area.

Effects of Individual Client’s Competencies on Construction Project Performance: Mediating Participation Attitude and Partnership

Within a construction project, the clients are categorized as private individuals, private companies, public institutions, etc. In this research, the private client is identified as a non-professional individual building owner and is involved in making decisions and solving problems for successful construction project performance. However, irrational decision-making and conflicts frequently occur with project delay and poor performance because the individual clients are normally non-professionals and lack the capacity to lead various stakeholders on the project. This study analyzes the effects of the project managerial competencies of the private individual clients on the construction performance. The client’s competencies were defined as ‘personal’, ‘social’, and ‘professional’ factors, and participation attitude and partnership were used as the mediating factors. The offline survey was conducted with 241 building owners in South Korea. The result indicates that personal and professional competencies had a positive effect on project performance, whereas social competency did not have an effect. Personal competency had the greatest effect on participation attitude and partnership. Social and professional competencies had a positive effect on partnership, not participation attitude. Hence, this shows that the personal competencies of the building owner as the end user of the project related to cognition, planning, and decision-making are important for project success.

‘Meeting the Client Where They Are Rather Than Where I'm At’: A Qualitative Survey Exploring CBT and Psychodynamic Therapist Perceptions of Psychotherapy Integration

This qualitative study explored therapists' attitudes towards psychotherapy integration. Twenty‐nine psychoanalytic/psychodynamic and cognitive‐behavioural therapy (CBT) therapists completed an open‐ended survey that focused on their personal understanding of psychotherapy integration, examples from their own practice and reflections on improving integrative therapy. Participants were also encouraged to share attitudes and perceptions towards the other therapeutic paradigm (CBT towards psychoanalysis, and vice versa). Thematic analysis revealed three main themes: (1) Positive perceptions and benefits of psychotherapy integration, (2) Negative perceptions and challenges of psychotherapy integration and (3) Proposals for strengthening integration in clinical practice. While most participants had a strong allegiance to their modality, they recognised the need for flexibility and additional techniques from other paradigms to address individual client needs. However, participants raised concerns about the level of knowledge required for integrative work and the epistemological compatibility between CBT and psychoanalysis. Some responses reflected the ongoing ‘turf wars’ between the two paradigms, with some referring to ‘outdated’ psychoanalytic ideas and ‘dogmatic’ evidence‐based hierarchies. Suggestions were made for further development of psychotherapy integration during the training and post‐qualification. The study reflects a generally positive outlook towards integration while recognising the challenges as well as the continuing resistances between CBT and psychoanalytic paradigms.