The research, led by Mary Catherine Beach and colleagues at Johns Hopkins University, utilized advanced artificial intelligence (AI) tools to sift through more than thirteen million clinical notes authored between 2016 and 2023. The AI algorithms were meticulously designed to flag phrases that implicitly cast doubt on a patient’s reliability or narrative competence—terms such as “claims,” “insists,” or “adamant about” were used as indicators of skepticism. Additionally, expressions like “poor historian” flagged questions about a patient’s ability to coherently narrate their medical history. These subtle language cues, though rarely exceeding 1% of the total notes, disproportionately appeared in accounts of Black patients.

Delving into the quantitative findings, the study reported that approximately 0.82% of all notes contained language undermining patient credibility. This fraction split nearly evenly between expressions questioning patient sincerity (0.48%) and those doubting patient competence (0.40%). Notably, the adjusted odds ratios (aOR) reveal an unsettling racial disparity: notes about non-Hispanic Black patients were 29% more likely to contain credibility-undermining language overall. Breaking it down further, doubt cast upon sincerity increased by 16%, while skepticism toward competence soared by 50% compared to notes concerning White patients. Conversely, supportive language bolstering patient credibility was recorded less frequently in notes about Black individuals.

This form of bias, documented within medical narratives, points to a systemic issue that could exacerbate unequal health outcomes. When clinician notes express implicit disbelief or skepticism, it risks influencing clinical decisions, treatment plans, and ultimately patient trust. Prior research has highlighted that perceived dismissal by healthcare providers undermines patient engagement and adherence, both pivotal for positive health trajectories. The current study extends this knowledge by spotlighting how such biases are mirrored in clinical documentation, a crucial yet often overlooked dimension.

Technically, the research team employed natural language processing (NLP) models trained to detect linguistic markers associated with credibility judgments. Although the models demonstrated high accuracy, the authors acknowledge limitations, citing potential misclassification errors that could underestimate or overestimate the prevalence of biased language. Furthermore, the study was conducted within a single healthcare system, which might limit generalizability. The influence of clinician demographics such as race, gender, or age on the use of credibility-undermining language was not explored, suggesting avenues for future inquiry.

Despite these constraints, Beach and colleagues emphasize that these findings likely constitute “the tip of the iceberg.” They warn that unconscious biases entwined in medical documentation may silently perpetuate stigma against Black patients, subtly shaping care trajectories. The authors advocate for enhanced medical training to sensitize future clinicians about implicit biases manifesting not only in interpersonal interactions but also in written communication. Moreover, as healthcare increasingly integrates AI-assisted documentation tools, they stress the necessity of programming these technologies to avoid perpetuating biased rhetoric.

Understanding the operational mechanics behind such AI tools is paramount. They help expedite the creation of patient notes, yet if trained on biased data, they risk inheriting and amplifying human prejudices. This feedback loop could normalize skewed portrayals of patient credibility, thereby institutionalizing disparities. The call to action involves developing ethical AI frameworks that actively mitigate bias, prompting rigorous validation of algorithmic outputs before clinical integration.

The implications of these discoveries extend beyond academic discourse to public health policy and clinical practice reform. Medical institutions must grapple with the recognition that documentation practices are not neutral; they reflect and reinforce social inequities. Interventions aiming to improve equity in healthcare outcomes should consider strategies addressing documentation bias, alongside broader structural reforms. For example, hospital systems can implement routine audits of clinical notes using AI tools to identify and remediate biased language patterns.

Furthermore, patients’ voices remain indispensable. Incorporating patient feedback mechanisms about their perceived treatment and representation in medical narratives might enhance transparency and foster mutual trust. Encouraging dialogues where patients can express concerns about how their accounts are documented and interpreted may act as an antidote to entrenched stigma. Ultimately, fostering an environment that respects and validates diverse patient narratives is foundational for equitable care.

The study also sheds light on the complex interface between language, power dynamics, and clinical judgment. Words possess the capacity to either empower or marginalize, especially in healthcare settings where documentation can influence diagnostic pathways and accessibility to resources. By rendering these dynamics visible through data-driven analyses, this research contributes critical insights into the subtleties of racial disparities.

In conclusion, the investigation by Beach et al. underscores the urgent need to confront the latent racial biases embedded in healthcare documentation. As the medical community strives to achieve equity, acknowledging and addressing how language shapes patient credibility assessments is imperative. This research advocates for multidisciplinary efforts combining AI innovation, clinician education, and patient engagement to dismantle bias and cultivate a more just healthcare system.

Subject of Research: People

Article Title: Racial bias in clinician assessment of patient credibility: Evidence from electronic health records

News Publication Date: 13-Aug-2025

Web References: http://dx.doi.org/10.1371/journal.pone.0328134

References: Beach MC, Harrigian K, Chee B, Ahmad A, Links AR, Zirikly A, et al. (2025) Racial bias in clinician assessment of patient credibility: Evidence from electronic health records. PLoS One 20(8): e0328134.

Image Credits: Beach et al., 2025, PLOS One, CC-BY 4.0

Keywords: racial bias, clinician assessment, patient credibility, electronic health records, natural language processing, artificial intelligence, healthcare disparities, implicit bias, medical documentation, equity in healthcare

Prior to the pandemic, the average MMR vaccination rate at the county level stood at an already modest 93.92%. Post-pandemic data reflects a notable dip, with an average rate falling to 91.26%, marking a mean reduction of 2.67%. While seemingly small, this decline is epidemiologically significant, pushing many communities further away from the established 95% vaccination threshold required to sustain herd immunity against measles. The implications of slipping below this critical threshold risk a resurgence of outbreaks and loss of containment of viral transmission.

Of the 2,066 counties analyzed, a staggering 1,614—approximately 78%—reported decreases in the county-level vaccination rates. This widespread trend underscores the pandemic’s disruptive effect on routine childhood immunization programs. The altered healthcare access, resource reallocation to COVID-19 response, vaccine hesitancy exacerbated by misinformation, and interruptions to school-based vaccination campaigns likely contributed to this decline. Only a handful of states, including California, Connecticut, Maine, and New York, demonstrated a reversal with increases in median county vaccination rates, highlighting the considerable heterogeneity of vaccination dynamics across the nation.

This dataset, published in the highly regarded journal JAMA, coincides with an alarming rise in measles cases reported within the United States this year. Over one thousand instances have been confirmed, representing one of the highest annual case counts in more than thirty years, second only to the historically severe spike documented in 2019. Notably, the vast majority of these cases involve unvaccinated children, emphasizing the direct consequences of declining immunization coverage and underscoring the urgent need for targeted public health interventions.

Lauren Gardner, the senior author and director of Johns Hopkins University’s Center for Systems Science and Engineering, remarked on the critical importance of this dataset. Gardner, renowned for leading the data collection effort behind the globally utilized Johns Hopkins COVID-19 dashboard, highlighted the utility of high-resolution vaccination data to dissect complex epidemiological patterns. This granular information provides an essential tool for health authorities to predict measles transmission risk and to tailor vaccination strategies locally rather than relying on coarse state or national averages, which can mask underlying vulnerabilities.

The dataset expands upon existing state and national level statistics available from the Centers for Disease Control and Prevention (CDC), furnishing a more detailed landscape of MMR vaccination coverage variation. The evaluation reveals that vaccination patterns vary not only between states but also significantly within states, reflecting diverse socio-economic, cultural, and political factors influencing healthcare behaviors and access. Understanding these fine-scale disparities is crucial for designing precision public health approaches capable of arresting potential outbreaks before they escalate.

Researchers compiled two-dose MMR vaccination rates among kindergarteners by extracting data from individual state health department websites spanning from 2017 through 2024 where available. This extensive timeframe captures trends before, during, and after the COVID-19 pandemic. Overall, the dataset includes vaccination information from 2,237 counties across 38 states, rendering it one of the most comprehensive county-level vaccine coverage databases currently available in the United States.

This thorough documentation enables researchers and policymakers to monitor vaccination trends over time and spatially throughout the country. Equally, the data highlights the urgency to reverse declining vaccine uptake and to reinforce education and outreach programs to combat misinformation and vaccine hesitancy, which have intensified during the pandemic era. Strengthening public trust in vaccination programs is imperative to restore population immunity and to prevent future outbreaks of measles, mumps, and rubella, diseases that, although vaccine-preventable, can cause severe morbidity and mortality.

Continuous surveillance provided by this dataset empowers stakeholders to identify vulnerable counties exhibiting significant vaccination declines, enabling timely public health responses. Furthermore, such high-resolution data can inform mathematical models predicting the risk and spread of measles outbreaks, facilitating resource allocation targeted to high-risk communities. The data-driven approach advocated by Gardner’s team epitomizes a shift towards leveraging big data and advanced analytics in infectious disease control and prevention.

While the pandemic itself disrupted routine healthcare delivery and preventive measures, this dataset illustrates that the reprocussions extend beyond COVID-19, amplifying susceptibility to other infectious diseases with established prevention methods. The resurgence of measles cases paired with declining vaccination rates is a stark reminder that maintaining robust immunization systems is essential for safeguarding public health resilience, especially in the face of emerging global health challenges.

As measles remains one of the most transmissible human viruses, even slight reductions in vaccine coverage can precipitate outbreaks. The findings underscore the delicate balance of herd immunity and the consequences of perturbations within vaccination programs. The Johns Hopkins team’s research not only maps this landscape but also provides a transparent resource with open data available for download, encouraging collaborative efforts across academia, public health agencies, and policymakers to confront this emerging threat effectively.

The dataset authors include former adjunct assistant research scientist Ensheng Dong, graduate student Samee Saiyed, former research assistant Andreas Nearchou, undergraduate student Yamato Okura, and senior author Lauren Gardner, all affiliated with Johns Hopkins University. Their collective expertise in epidemiology, data science, and disease modeling fortifies the rigorous approach underpinning this pivotal contribution to infectious disease surveillance.

As public health communities digest these findings, there is a renewed call to action to bolster vaccination campaigns, enhance surveillance systems, and deploy innovative communication strategies aimed at increasing vaccine acceptance. Reinforcing and expanding routine immunizations amid the lingering challenges of the COVID-19 pandemic is critical to protecting the most vulnerable populations and restoring the United States’ hard-won gains against vaccine-preventable diseases.

Subject of Research: Decline in county-level MMR vaccination rates in the United States post-COVID-19 pandemic.

Article Title: Not specified in the content.

News Publication Date: Not specified beyond "published today" relative to dataset release.

Web References: None provided.

References: Data published in JAMA.

Image Credits: Johns Hopkins University.

Keywords: Viral infections, Preventive medicine