PricewaterhouseCoopers (United States)

The increasing complexity of financial fraud schemes has necessitated the adoption of advanced data analytics, AI-driven fraud detection models, and forensic accounting tools to strengthen corporate fraud prevention and regulatory compliance. Traditional fraud detection techniques have proven inadequate in identifying sophisticated financial crimes, prompting organizations to integrate predictive analytics, machine learning algorithms, and real-time transaction monitoring systems to mitigate fraud risks. This paper examines how data analytics enhances financial risk mitigation, the role of AI in automating fraud detection, and the challenges associated with implementing data-driven fraud prevention models. Additionally, it explores the global impact of regulatory frameworks, such as the Sarbanes-Oxley Act (SOX) and international anti-money laundering directives, which drive the adoption of AI-powered risk assessment strategies. By analyzing case studies of multinational corporations that have implemented data-driven fraud detection mechanisms, this research highlights the effectiveness of forensic data analysis in improving corporate transparency and compliance. The findings suggest that AI and data analytics will continue to redefine financial fraud prevention, ensuring corporate integrity and investor confidence in an increasingly digitalized financial landscape. Keywords: Fraud detection, Data Analytics, Ai-Driven Fraud Prevention, Financial Risk Mitigation, Regulatory Compliance, Predictive Analytics, Forensic Auditing, Machine Learning in Fraud Detection, Blockchain Technology in Fraud Prevention, Corporate Financial Security.

Analyzing soft interval data for uncertainty quantification has attracted much attention recently. Within this context, regression methods for interval data have been extensively studied. As most existing works focus on linear models, it is important to note that many problems in practice are nonlinear in nature and the development of nonlinear regression tools for interval data is crucial. This paper proposes an interval-valued random forests model that defines the splitting criterion of variance reduction based on an L 2 type metric in the space of compact intervals. The model simultaneously considers the centers and ranges of the interval data as well as their possible interactions. Unlike most linear models that require additional constraints to ensure mathematical coherences, the proposed random forests model estimates the regression function in a nonparametric way, and so the predicted interval length is naturally nonnegative without any constraints. Simulation studies show that the new method outperforms typical existing regression methods for various linear, semi-linear, and nonlinear data archetypes and under different error measures. To demonstrate the applicability, a real data example is presented where the price range data of the Dow Jones Industrial Average index and its component stocks are analyzed.

Abstract Study question Can key elements of ovarian physiology be accurately modelled, thereby providing a tool to generate novel insights and guide development of new therapeutics? Summary answer A physiological computational model was developed to describe follicle growth and follicle size distributions observed in agonist and antagonist ovarian stimulation (OS) protocols. What is known already The outcome of OS remains unpredictable despite identification of several prognostic factors. The average first cycle pregnancy rate is 30-40% across fertility centres, highlighting the need for improved stimulation protocols. This is an active area of clinical research; however, clinical trials are costly, time-consuming, and frequently have outcomes that are unexpected or difficult to interpret. We integrated available physiological knowledge of human follicle growth and development and clinical trial data into a computational model to enable in silico simulations with the aim to optimise clinical trial design. Study design, size, duration Computational model building was performed using a mechanistic approach aimed at capturing well-understood physiology that is relevant in OS protocols. Model inputs included patient characteristics (such as anti-Müllerian hormone (AMH) level), OS regimen and pituitary downregulation with gonadotrophin releasing hormone (GnRH) agonist or antagonist. Key outputs of the model included follicle number and mean size, duration of stimulation and serum hormone concentrations (oestradiol, testosterone, inhibin B and androstenedione). Participants/materials, setting, methods Published physiological data on regulation of follicle development and hormone production informed model design. Following implementation of the model in the Python platform, data from two OS clinical trials were used to calibrate (partially censored) and test the model. The two trials provided data on the effects of the recombinant follicle stimulating hormone preparation follitropin delta over a range of fixed doses and compared the effects of follitropin delta in agonist and antagonist OS protocols. Main results and the role of chance The computational model describes the interplay between pituitary gonadotrophins ovarian steroid hormones and follicle growth and development. Processes spanning the cellular level (such as steroidogenesis and receptor dynamics in theca and granulosa cells), the ovaries (follicle number and size) and the organism (pharmacokinetics and hypothalamic-pituitary-ovarian axis) are included as a system of coupled differential equations. Approximately 70 compartments, 500+ parameters and 1700+ reactions constitute the model framework. Follicles are recruited in the model at variable times, starting from 7 days prior to the start of stimulation. Follicles are initialised with individual sensitivity to gonadotrophins and growth rates. The fate of each follicle (dominance or atresia) is governed by these properties, which determine whether the balance shifts towards proliferation or atresia under the influence of gonadotrophins. Model-simulated numbers of follicles, their average size and mean serum hormone concentrations match closely with observed values in the two clinical trials. For each of these variables, their dependence on time, the dose of follitropin delta, AMH level and downregulation protocol were described with good precision. The inter-patient variability in the simulated number of follicles and in serum hormone levels matched closely with the observed variability based on comparison of the interquartile range. Limitations, reasons for caution The computational model currently describes follicle development during treatment with follitropin delta. We envision extending the model to encompass other treatment outcomes and additional preparations of exogenous gonadotrophins. While the model incorporates our current understanding of mechanisms important for follicle development, ongoing research in the field will likely drive improvements. Wider implications of the findings The computational model is hypothesis-generating and can improve the design of future clinical trials through in silico trial simulation. For instance, the effects of changing subject inclusion/exclusion criteria or of novel dosing regimens can be investigated. Trial registration number NCT01426386, NCT03809429

In recent years, there has been a growing emphasis within the healthcare community on social justice, equity and the global impact of health disparities.1 This trend has led health professional programs to initiate institutional efforts promoting Equity, Diversity, and Inclusion (EDI) and restorative justice, including indigenous reconciliation in healthcare training and practice settings. These initiatives respond to calls for action in health professions education, such as those outlined in the Truth and Reconciliation Calls to Action in Canada.2 Many efforts involve the development of curriculum content focusing on indigenous health care and an understanding of the historical impacts of colonization. Additional strategies encompass mandatory implicit bias training and cultural safety training. However, the impact of these efforts on patient safety and the quality of clinical education is unclear. Of most concern to us is that research in some domains has been dominated by interest in enhancing self-monitoring strategies and sadly, much of this research does not explicitly acknowledge a social justice lens in their research goal or study design. Motivated by a need to invigorate research and knowledge translation, a recent International Rethink Conference3 challenged us to consider ways to translate our expertise into meaningful clinical education that advances social justice within clinal reasoning and decision making. We considered that to truly advance social justice and EDI within our communities, we must critically examine how health care is delivered, what is taught in health professions education and who is included in our training environments. Moreover, it is crucial to scrutinize our epistemic assumptions that may hinder us from embodying our stated values or, at worst, contribute to the perpetuation of injustices we aim to address. In discussions about these topics, we found ourselves incorporating personal stories to explore the various contexts in which we have experienced inequity in clinical practice and education. These narratives proved very effective in creating shared models and a common language within our authorship group about behavior and attitudes that contribute to inequity for learners, patients and clinicians—the three perspectives represented in our author group. Essentially our personal stories helped us advance our individual and collective understanding of where social justice is most needed in clinical education and practice. Therefore, our primary contribution to the conversation started by the reThink conference is to emphasize the importance of stories as a form of teaching and learning. To help our community join this conversation we have curated a set of our personal stories that reflect systemic biases that undermine efforts to enhance social justice. These stories were previously shared at the International Rethink Conference,3 and subsequent discussions and feedback were integrated into the final manuscript. In this editorial piece, we return to these stories and offer a way forward. Through our stories we explore the impact of generalized algorithms, medicalized terms, medical jargon and medical culture on patients, learners and physicians. Yet, we must approach the stories we hear with caution. There is no magical illumination that occurs simply by contemplating another's story. Instead, it is the attention to multiple stories and the recursive acts of mindful and deliberate (radical) inclusion, conscious expansion and self-interrogation with each story around which we must center our practice and education. Chimamanda Ngozi Adichie speaks of this in her talk titled 'The Danger of a single story'.4 She asserts: 'Stories matter. Many stories matter. Stories have been used to dispossess and to malign, but stories can also be used to empower and to humanize. Stories can break the dignity of a people, but stories can also repair that broken dignity'. And '[t]he consequence of the single story is this: It robs people of dignity. It makes our recognition of our equal humanity difficult. It emphasizes how we are different rather than how we are similar'. We encourage everyone to reflect on how to enrich our practice and education by actively engaging with and amplifying multiple stories of others? How might this iterative reflective practice cultivate a more resilient moral imagination, empowering us to practice and teach with increased wisdom and care? Figure 1 outlines some ways to engage with recursive acts of mindfulness within clinical reasoning. *Authors' Note: 'Our author group reached a consensus to challenge the conventional approach to authorship in academia and adopt an equitable stance. In this manuscript, we aimed for an equitable representation, as evidenced by the shared authorship order and the acknowledgment of each author as an expert in their lived experience'. For years, J had struggled with self-image. From a young age, she received consistent messages from the media, clothing stores, family, and even her family doctor that she needed to lose weight — to fit in, to be healthy—to be accepted. Her family doctor validated those messages by referencing the BMI [body mass index]. According to the BMI, J has been obese and unhealthy her whole adult life. But her high level of fitness and healthy lifestyle contradicted the BMI index and the 'high-risk' label. All of which created a strong distrust of her family doctor. Indices designed to describe various aspects of the patient profile can offer clinical efficiency, standardizing discussions around clinical risk factors, diagnostic measures, or therapeutic targets across different individuals. Such indices play a crucial role in helping practitioners 'speak the same language' in clinical care. Shared mental models are indispensable in health professions, given the intricate nature of patients, medical conditions and the systems within which we operate. However, these models also create an illusion that all patients can, want to and should fit the model. It is crucial to recognize how these models affect clinicians' attitudes towards patients, mainly how these attitudes are conveyed through the language used in practice.5 Unfortunately, our clinical language has incorporated phrases that, whether intentionally or unintentionally, may cause harm to those we care for and those with whom we work. We have a schizophrenic here tonight, brought in by paramedics because he tried to commit suicide. This is his third attempt. We'll try to manage him, but inevitably, we know once he is cleared by psychiatry, he'll leave again against medical advice. In the diagnostic process, clinicians aiming for language efficiency, such as referring to an individual as a 'schizophrenic' instead of a 'person with schizophrenia', may unintentionally emphasize the 'problematic' aspects of the individual in the clinical encounter, potentially overshadowing the person at the center. This approach risks overlooking the individual's humanity and personhood, which extend beyond their discrete clinical diagnosis(es). Placing the 'pathology' first can diminish the person's value with the condition.6 Moreover, the use of healthcare language that characterizes, for instance, a suicide attempt as 'committing' introduces implicit judgments of criminality into clinical assessments and perpetuates stigma towards individuals dealing with substance misuse and mental health challenges.7 Although shared mental models used to describe pathology can be beneficial, the risk exists of them being employed to pathologize and dehumanize patients. For instance, patients with sickle cell disease are frequently referred to as 'sicklers', a term associated with negative connotations among healthcare providers.8 This biased language can, in turn, influence the quality of care patients receive. For instance, patients with sickle cell disease have received less analgesia if their healthcare records contained stigmatizing language compared to patients described using neutral language.9 While in college, as a full-time racialized student in biochemistry, I also worked full-time in my family's hair business, worked part-time on campus, and participated in many extracurricular activities. While balancing all of this, I nearly failed a biology class. Two White medical school mentors at my college told me that I couldn't withstand the rigors of medical school and should consider pursuing another career. I experienced previous encounters like this … I had a 3.6 GPA, which included rigorous high-level chemistry classes, but I was constantly told it wasn't enough. Rethinking clinical reasoning10, 11 through the lens of social justice empowers us to scrutinize the structures and systems within which we practice and learn. Exploring the epistemological viewpoints influencing program development and delivery requires active participation from administrators and admissions committees. This work involves conducting a critical review of admission criteria. Key questions include the following: Are these criteria genuinely selecting individuals best suited for the profession? Is there an implicit bias that confers legitimacy on applicants with privileged identities and access to resources while deeming others unsuitable? Marginalization can begin as prospective matriculants seek admission into health professions education programs. Within the admissions processes, systems that perpetuate social injustice and inequity may be identified. Examining bias in recruitment requires a deep dive into the foundational aspects of our education programs – who we permit entry, and the criteria prospective students must meet to justify their entry. Once learners 'gain entry into' our educational programs, they are exposed to curricula that might inadvertently perpetuate the very inequities and injustice their institutional mission statements oppose. Teachers may unintentionally contribute to perpetuating inequity, and learners' development of clinical reasoning may become entrenched within oppressive, exclusionary practices that students then internalize and integrate into their own practice. I was supervising a medical student during their first clerkship rotation. We reviewed the patient's chart with diabetes, whose Hemoglobin A1c is still not on target. I expressed my frustration about medication noncompliance in diabetics. My student overheard me and asked how access to healthy food might play a role. It made me pause… Here, we observe how our clinical language and patient descriptors might contribute to depersonalization. Depersonalizing our patients can hinder us from taking proactive measures against shifting the sole responsibility for a patient's situation onto the individual themselves and, instead, actively moving towards understanding and exploring the social determinants of health that might impact our patient's ability to follow or 'adhere to' medical advice. In simpler terms, acts of conscious expansion and self-interrogation enable us to step back and scrutinize our assumptions, replacing judgments such as 'of course, he'll just leave against medical advice again' and 'medication noncompliance in diabetics' with empathy and patient/client-centeredness. Word choices in the patient's chart can also impact billing. Charts mired with 'noncompliance' and 'needs placement' do not accurately portray the severity of the patient's illness. In specific contexts, this can affect health insurance reimbursement for visits. Some private care hospitals might actively resist or restrict these hospital admissions, anticipating potential revenue loss. Using such language may contribute to bias for future clinicians and impact their willingness to engage deeply with the patient to establish a patient-centered plan. From the patient's perspective, this language signals a loss of tolerance or compassion before they are even seen. Moreover, the term 'noncompliance' sends a message to patients, learners and society that individuals should be submissive to their prescribed care and dismiss other challenges they may be facing. Rather than demonstrating conscious expansion and seeking to understand the context surrounding patients' behaviors and actions (or inaction), the language clinicians use, instead, shifts blame and attributes the entire responsibility for health management failures to individuals, thereby de-emphasizing the clinicians' role in adjusting the resources needed to better care for the patient. For instance, is a patient's 'non-compliance' due to limited health literacy? If so, the patient may benefit from additional support and follow-up instructions. Does the person have a concurrent substance use disorder or mental health diagnosis? If so, the patient may need focused resources for concurrent disorders. Unfortunately, while denouncing this language in health care is not a new critique, terms like 'noncompliance' and 'poor adherence' persist in the modern practice environment.6 Shared decision-making is a vital component of clinical reasoning, often presented as one of the final steps in the patient encounter. It is crucial to explore the potential epistemic injustice that may complicate and permeate the decision-making process clinicians navigate with their patients.12 The works of Carel and Kidd call us to consider that 'in terms of the patient-professional interaction, stereotypes of the "ill patient" lead to a form of injustice whereby training, expertise, and formal knowledge are legitimized in the biomedical context and elevated to gold standard status, while the stories of patients are viewed as irrelevant, illogical, or unworthy'.13, 14 Thomas et al.12 state that '[i]n a health care encounter, this requires constant reflexive mindfulness on the part of the provider not to slip into the monological mode that is characteristic of most […] interactions—not just to solicit patient opinions but to co-construct the knowledge of the individual patient's disease and its treatment, including goals and objectives that are being made in the encounter'. As we contemplate the potential injustice that may be perpetuated through our epistemological stance, and within this stance, the sources of knowledge we deem legitimate, worth paying attention to, or relevant, the need for self-interrogation extends beyond examining our words and actions. It delves into challenging our presuppositions and enculturated assumptions. In this, '…educational programs that foster critical reflexivity in learners as future health care professionals can help illuminate forms of epistemic injustice and, ultimately, empower clinicians to enact [shared decision-making] in a more authentic manner'.12 In one of my residency interviews, I was asked why I was applying for my specialty when I had so much experience in global health and was clearly passionate about it – wouldn't I be better suited for public health? I explained that global health is also local health. In a country where we see the adverse outcomes of colonialism, where health outcomes vary drastically from one location to another, it is essential to recognize and address the upstream causes … when a bottle of soda costs less than a bottle of water, and you cannot drink tap water because your community has a Boil-Water Advisory for the past decade, how does that impact your health? I explained that global health encompasses narratives such as that. I was met with a blank stare – medicine needs to normalize social justice as one of our central tenets. Furthermore, our academic institutions must recognize and reward work beyond the traditional confines of 'research' and publications as the primary (and often, sole) metrics for academic contributions and productivity. Learners are introduced to a 'language' of health care and a 'culture of practice' within their clinical environments. The language used by the healthcare team can contribute to further traumatizing and harming patients and clients; it can exacerbate the disempowerment of those marginalized within the healthcare system. However, this disenfranchisement can start well before any learner reaches the patient care environment and extend to their preclinical and didactic experiences. Learners have the agency to challenge these experiences. Clinical workplaces can empower learners by creating a psychologically safe environment and fostering a culture where it is acceptable to question norms and practices. Unfortunately, students may quickly become 'acclimatized' to the education and practice microcultures within which they are learning. Initially, students may find a particular language offensive, but over time, there is a risk that they will internalize it. This exposure may lead not only to using such language themselves but also to internalizing the belief systems that perpetuate inequities in practice. Historically, faculty activity directed towards advancing equity and social justice within higher education and health professions education contexts received, at best, only cursory acknowledgment in considerations for tenure and academic promotion. This work promotes 'evidence-based advocacy' or 'evidence-based equity'. The diversity tax or cultural taxation refers to the disproportionate burden that those in historically marginalized groups carry to promote justice, health equity, diversity and inclusion (JEDI efforts) on their university campuses.15 Participation in JEDI work should not be viewed as an extra activity or activity that is not given weight or credit when assessing an academic clinician's qualifications for promotion or advancement. While JEDI work is starting to be recognized across academic centers, the recognition varies across institutions, and criteria for what constitutes 'important' or 'significant' contributions vary. We must redefine what constitutes productivity in academia, where traditional research productivity metrics are overvalued. Social justice work and advancing EDI should be normalized as an expectation for healthcare workers. By doing so, we increase opportunities for those passionate about these topics to consider careers in academic medicine. Furthermore, formal institutional processes are in place to recognize and reward this work. In their qualitative study, Browne et al.16 defined key dimensions of providing equity-oriented services in primary health care and highlighted strategies to guide organizations in enhancing their capacity for these services. In their work, structural factors were crucial, such as advocating for funding and policy change, revising traditional metrics (such as time and outcomes), flattening hierarchies and creating opportunities for participatory engagement.16 Nonacademic members of the healthcare and education continuum often contribute a significant backbone of health equity efforts. These include social workers, case managers, nurses, allied health professionals and other community members and organizations critical for providing support and advocacy. As we rethink clinical reasoning in social justice, especially in exploring how current structures and systems can be reimagined to recognize, promote and advance social justice, we pose additional questions for further consideration. How might we involve our colleagues working in the community? What incentives might we offer to support participation in research projects if they do not require a publication for bonus pay, a salary increase, recognition, or promotion? To apply this discussion to the practice context, how might we incentivize community partners and healthcare colleagues to engage in teaching, provide feedback and assess our learners? Translational research is crucial because everyday situations in academic centers often do not directly apply to those in the community, considering the variable resources available. Overall, the question remains: 'how might we empower our colleagues in the community with evidence-based advocacy or evidence-based equity efforts if they are not incentivized to pursue scientific inquiry?' The stories shared here, as experienced, described and received by the authors, are intended to provide depth and personalization to our discussion of how we might advance social justice and equity in our clinical reasoning education and practice. The threads we gather from every story that we weave together form a broader, vibrant tapestry that will—we hope—move us from greater understanding to action. If we approached our clinical practice and education from this perspective and more deliberately attended to the collective individual stories in our practice, teaching and institutional culture, how might this help us to effect change, equity and social justice? After all, as Adichie reminds us, 'Stories matter. Many stories matter'. Through these narratives, we can improve and reshape the experience of our patients, learners and communities in health care. Collective narratives are essential to aligning social justice and clinical reasoning. We encourage individuals and institutions to attend to the stories and lived experiences of our learners, patients and communities, examining whose voices and perspectives we may deny and those we validate. We ask ourselves to explore actively an understanding of the contexts, systems and structures within which we teach and practice that may be supporting or upholding the unjust and inequitable systems we seek to address. We encourage a process of continuous self-interrogation with ourselves and others in our healthcare education and practice environments to examine how our words, actions and beliefs might perpetuate and maintain systems of inequity and injustice. In this, we continue the process of moving from understanding to action. Through this, we take small steps towards advancing social justice and equity in our healthcare education and practice.