scholarly journals A Complex Model of Clinical Narrative Information for the Diagnostic Act

Author(s):  
David Chartash ◽  
Marc B Rosenman ◽  
Johan Bollen ◽  
Markus Dickinson ◽  
Stephen M Downs

AbstractBackgroundThe act of diagnosis is one which precipitates semiotic closure, the complex integration of signs and symptoms through cognitive perspectives to ultimately activate causal reasoning and calibrate the assignment of a disease entity to the patient. In writing about this act, physicians encode both structured and unstructured information into the medical record. Unstructured information contains a latent structure which entwines both the cognitive components of the diagnostic act and the linguistic patterns associated with clinical documentation. Existing models of clinical language primarily use a physical or dialogic model of information as their basis, and do not adequately account for the complexity inherent in the diagnostic act.MethodsFraming the diagnostic information collected in clinical care as a narrative, we developed a model representative of said information, accounting for its content and structure, as well as the inherent complexity therein. Using an exemplar text, we present the use of known predication and semantic relations from ontological (the Unified Medical Language System) and linguistic theory (Rhetorical Structure Theory) to facilitate the operationalization of the model, and analyze the result.ResultsThe resulting model is demonstrated to be complex, representative of the clinical narrative text, and is fundamentally aligned with the clinical acts of both documentation and diagnosis. We find the model’s representation of the cognitive aspects of narrative consistent with models of reading, as well as an adequate model of information as presented by clinical medicine and the clinical sub-language.ConclusionsWe present a model to represent diagnostic information in the physician’s note which accounts for the clinical and textual narrative precipitated by the cognition involved in encoding said information into the unstructured medical record. This model prepends the development of (computational) linguistic models of the clinical sublanguage within the physician’s note as it relates to diagnosis, beyond the information level of the lexical unit. Such analysis would facilitate better reflection on the structure and meaning of the clinical note, offering improvements to medical education and care.

2021 ◽  
pp. bmjqs-2020-011593
Author(s):  
Traber D Giardina ◽  
Saritha Korukonda ◽  
Umber Shahid ◽  
Viralkumar Vaghani ◽  
Divvy K Upadhyay ◽  
...  

BackgroundPatient complaints are associated with adverse events and malpractice claims but underused in patient safety improvement.ObjectiveTo systematically evaluate the use of patient complaint data to identify safety concerns related to diagnosis as an initial step to using this information to facilitate learning and improvement.MethodsWe reviewed patient complaints submitted to Geisinger, a large healthcare organisation in the USA, from August to December 2017 (cohort 1) and January to June 2018 (cohort 2). We selected complaints more likely to be associated with diagnostic concerns in Geisinger’s existing complaint taxonomy. Investigators reviewed all complaint summaries and identified cases as ‘concerning’ for diagnostic error using the National Academy of Medicine’s definition of diagnostic error. For all ‘concerning’ cases, a clinician-reviewer evaluated the associated investigation report and the patient’s medical record to identify any missed opportunities in making a correct or timely diagnosis. In cohort 2, we selected a 10% sample of ‘concerning’ cases to test this smaller pragmatic sample as a proof of concept for future organisational monitoring.ResultsIn cohort 1, we reviewed 1865 complaint summaries and identified 177 (9.5%) concerning reports. Review and analysis identified 39 diagnostic errors. Most were categorised as ‘Clinical Care issues’ (27, 69.2%), defined as concerns/questions related to the care that is provided by clinicians in any setting. In cohort 2, we reviewed 2423 patient complaint summaries and identified 310 (12.8%) concerning reports. The 10% sample (n=31 cases) contained five diagnostic errors. Qualitative analysis of cohort 1 cases identified concerns about return visits for persistent and/or worsening symptoms, interpersonal issues and diagnostic testing.ConclusionsAnalysis of patient complaint data and corresponding medical record review identifies patterns of failures in the diagnostic process reported by patients and families. Health systems could systematically analyse available data on patient complaints to monitor diagnostic safety concerns and identify opportunities for learning and improvement.


2018 ◽  
Vol 32 (04) ◽  
pp. 166-171 ◽  
Author(s):  
Bradley Eisemann ◽  
Ryan Wagner ◽  
Edward Reece

AbstractDespite incredible advances in medical innovation and education, many students finish medical school, and physicians finish residency, without sound business acumen regarding the financial realities of the modern profession. The curriculum in medical schools and residency programs too often neglects teaching the business of medicine. This overview addresses how physicians can utilize effective negotiation strategies to help develop a medical practice or add value to an existing practice or institution. The authors applied the six foundations of effective negotiating, detailed by Richard Shell in his Bargaining for Advantage, to the medical field to demonstrate the processes involved in effective negotiating. They then outlined a strategy for physicians to adopt when negotiating and showed how this strategy can be used to add value. The six foundations include: developing a personal bargaining style, setting realistic goals, determining authoritative standards, establishing relationships, exploring the other party's interests, and gaining leverage. As physicians complete training, the ability to solely focus on medical knowledge and clinical patient care disappears. It is crucial that physicians invest the time and energy into preparing for the business aspects of this profession in much the same way they prepare for the clinical care of patients. This overview seeks to define the basics of negotiation, characterize the application of negotiation principles toward clinical medicine, and lay the foundation for further discussion and investigation.


2021 ◽  
Author(s):  
Liat Wasserman

BACKGROUND Healthcare is facing a growing threat of cyberattacks. Myriad data sources illustrate the same trends that healthcare is one of the industries with the highest risk of cyber infiltration and is seeing the rate of security incidents surge within just a few years. The circumstances thus begged the question: are US hospitals prepared for the risks that accompany clinical medicine in cyberspace? OBJECTIVE This study aimed to identify the major topics and concerns present in today’s hospital cybersecurity field, intended for the non-cyber professionals audience in hospital settings. METHODS Via a structured literature search of the National Institutes of Health’s PubMed database (including the MEDLINE database) and Tel Aviv University’s DaTa database, 35 journal articles were identified to form the core of the study. 86 additional sources were examined to inform the study findings RESULTS The literature review revealed a basic landscape of hospital cybersecurity, including the top ten methods of attack, the primary reasons hospitals are frequent targets, and the consequences hospitals face following attacks. The cyber technologies common in clinical medicine, as well as their risks, were also examined, with the major categories highlighted being medical devices, telemedicine software, and electronic data. By infiltrating any of these three components of clinical care, cyber attackers can access a trove of valuable information and manipulate, steal, ransom, or otherwise compromise the records, or can use the access to catapult themselves to access other parts of a hospital’s network. Multiple secondary issues that can increase the cyber risks associated with devices, telemedicine, and electronic data were also identified. Finally, strategies that hospitals tend to employ to combat the cyber risks were explored and found to be subpar. There exist within hospitals’ cybersecurity measures serious vulnerabilities and gaps that many of today’s hospitals fail to address. The COVID-19 pandemic was used to further illustrate this issue. CONCLUSIONS Comparison of the risks, strategies, and gaps revealed that many hospitals in the US are unprepared for cybersecurity risks. The focus of their efforts are misdirected, with external - often governmental - efforts negligible. Policy changes, such as training employees in cyber protocols, adding advanced technical protections, and collaborating with a variety of experts, are necessary. Overall, hospitals must recognize that, in cyber incidents, the real victims are the patients. They are the ones at risk, physically and in information confidentiality, when medical devices, hospital equipment, or treatments are compromised.


2021 ◽  
Author(s):  
Gorka G Leiceaga ◽  
Robert Balch ◽  
George El-kaseeh

Abstract Reservoir characterization is an ambitious challenge that aims to predict variations within the subsurface using fit-for-purpose information that follows physical and geological sense. To properly achieve subsurface characterization, artificial intelligence (AI) algorithms may be used. Machine learning, a subset of AI, is a data-driven approach that has exploded in popularity during the past decades in industries such as healthcare, banking and finance, cryptocurrency, data security, and e-commerce. An advantage of machine learning methods is that they can be implemented to produce results without the need to have first established a complete theoretical scientific model for a problem – with a set of complex model equations to be solved analytically or numerically. The principal challenge of machine learning lies in attaining enough training information, which is essential in obtaining an adequate model that allows for a prediction with a high level of accuracy. Ensemble machine learning in reservoir characterization studies is a candidate to reduce subsurface uncertainty by integrating seismic and well data. In this article, a bootstrap aggregating algorithm is evaluated to determine its potential as a subsurface discriminator. The algorithm fits decision trees on various sub-samples of a dataset and uses averaging to improve the accuracy of the prediction without over-fitting. The gamma ray results from our test dataset show a high correlation with the measured logs, giving confidence in our workflow applied to subsurface characterization.


2020 ◽  
Vol 10 (1_suppl) ◽  
pp. 10S-16S
Author(s):  
Sarah Hopkins ◽  
Polly Brune ◽  
Jens R. Chapman ◽  
Marc Horton ◽  
Rod Oskouian ◽  
...  

Our health care system is an evidenced-based quality-centric environment. Pursuit of quality is a process that encompasses knowledge development and care advancements through collaboration and expertise. Depicted here is the foundational knowledge, process, and contributions that hallmark successful clinical quality programs. Beginning with methodology, followed by process and form, we create the foundational knowledge and exemplars demonstrating framework and continuum of process in pursuit and attainment of successful clinical quality and care development for patients. Although our protocol has been devised for complex spine care, this could be implemented across all health care specialties to provide individualized and high-quality care for all current and future patients, all while creating a culture of accountability for physicians.


2004 ◽  
Vol 43 (03) ◽  
pp. 302-307 ◽  
Author(s):  
E. Ammenwerth ◽  
R. Brandner ◽  
B. Brigl ◽  
G. Fischer ◽  
S. Garde ◽  
...  

Summary Objectives: To summarize the challenges facing clinical applications in the light of growing research results in genomic medicine and bioinformatics. Methods: Analysis of the contents of the Yearbook of Medical Informatics 2004 of the International Medical Informatics Association (IMIA). Results: The Yearbook of Medical Informatics 2004 includes 32 articles selected from 22 peer-reviewed scientific journals. A special section on clinical bio-informatics highlights recent developments in this field. Several guest editors review the promises and limitations of available methods and resources from biomedical informatics that are relevant to clinical medicine. Integrated data and knowledge resources are generally regarded to be central and key issues for clinical bioinformatics. Further review papers deal with public health implications of bioinformatics, knowledge management and trends in health care education. The Yearbook includes for the first time a section on the history of medical informatics, where the significant impact of the Reisensburg protocol 1973 on international health and medical informatics education is examined. Conclusions: Close collaboration between bio-informatics and medical informatics researchers can contribute to new insights in genomic medicine and contribute towards the more efficient and effective use of genomic data to advance clinical care.


2010 ◽  
Vol 2 (3) ◽  
pp. 478-484 ◽  
Author(s):  
Colleen Christmas ◽  
Samuel C. Durso ◽  
Steven J. Kravet ◽  
Scott M. Wright

Abstract Background The provision of high-quality clinical care is critical to the mission of academic and nonacademic clinical settings and is of foremost importance to academic and nonacademic physicians. Concern has been increasingly raised that the rewards systems at most academic institutions may discourage those with a passion for clinical care over research or teaching from staying in academia. In addition to the advantages afforded by academic institutions, academic physicians may perceive important challenges, disincentives, and limitations to providing excellent clinical care. To better understand these views, we conducted a qualitative study to explore the perspectives of clinical faculty in prominent departments of medicine. Methods Between March and May 2007, 2 investigators conducted in-depth, semistructured interviews with 24 clinically excellent internal medicine physicians at 8 academic institutions across the nation. Transcripts were independently coded by 2 investigators and compared for agreement. Content analysis was performed to identify emerging themes. Results Twenty interviewees (83%) were associate professors or professors, 33% were women, and participants represented a wide range of internal medicine subspecialties. Mean time currently spent in clinical care by the physicians was 48%. Domains that emerged related to faculty's perception of clinical care in the academic setting included competing obligations, teamwork and collaboration, types of patients and productivity expectations, resources for clinical services, emphasis on discovery, and bureaucratic challenges. Conclusions Expert clinicians at academic medical centers perceive barriers to providing excellent patient care related to competing demands on their time, competing academic missions, and bureaucratic challenges. They also believe there are differences in the types of patients seen in academic settings compared with those in the private sector, that there is a “public” nature in their clinical work, that productivity expectations are likely different from those of private practitioners, and that resource allocation both facilitates and limits excellent care in the academic setting. These findings have important implications for patients, learners, and faculty and academic leaders, and suggest challenges as well as opportunities in fostering clinical medicine at academic institutions.


2013 ◽  
Vol 31 (31_suppl) ◽  
pp. 248-248
Author(s):  
Vishal Kukreti ◽  
Sara Lankshear ◽  
Arthur G. Manzon ◽  
Nancy Wolf ◽  
Shafiq Habib ◽  
...  

248 Background: The use of ambulatory electronic medical record (EMR) systems within oncology provides an opportunity for aligning provincial, local and end-user patient-centred quality indicators in the design, delivery and evaluation of clinical care and resource utilization. The aim of this provincial initiative is to define the “meaningful use” for the Oncology EMR by identifying the essential data elements and functional requirements required to facilitate integrated care, information standards (both local and provincial), and system integration needs. This paper presents the results of a provincial field study designed to determine end-user needs for information and quality metrics. Methods: Data collection included two separate onsite focus groups at each of the 13 regional cancer programs, with a focus on Clinical and Operational requirements. A total of 141 participants, representing physicians, interprofessional clinical team members, administrators and health information specialists were involved. An additional online survey was used for optimal engagement, with a total of 194 respondents, primarily nurses and physicians. Inclusion and exclusion criteria were developed to assist in coding and distillation of concepts generated. Results: A total of 1,598 ideas were generated (Clinical = 997, Operational = 601). Multiple rounds of content analysis were used to eliminate duplicates, identify common themes and distill the wealth of information down to the “vital few” discrete information requirements that should be included in the oncology EMR. At this time, 63 clinical and 55 operational concepts have been identified to support clinical care as well as operational planning and system evaluation. The online survey has helped define the data required for a Provincial Oncology Patient Profile within the EMR. Conclusions: The study employed significant consultation to merge end user and existing provincial quality measurement needs in order to define the Ontario Oncology EMR. A full spectrum of quality indicators identified through these processes will inform the future provincial priorities for information standards and quality monitoring that will be facilitated by a standardized EMR.


2002 ◽  
Vol 16 (2) ◽  
pp. 35-45 ◽  
Author(s):  
Onora O'Neill

Most work in medical ethics across the last twenty-five years has centered on the ethics of clinical medicine. Even work on health and justice has, in the main, been concerned with the just distribution of (access to) clinical care for individual patients. By contrast, the ethics of public health has been widely neglected. This neglect is surprising, given that public health interventions are often the most effective (and most cost-effective) means of improving health in rich and poor societies alike.In this essay I explore two sources of contemporary neglect of public health ethics. One source of neglect is that contemporary medical ethics has been preoccupied—in my view damagingly preoccupied—with the autonomy of individual patients. Yet individual autonomy can hardly be a guiding ethical principle for public health measures, since many of them must be uniform and compulsory if they are to be effective. A second source of neglect is that contemporary political philosophy has been preoccupied—in my view damagingly preoccupied—with the requirements for justice within states or societies, and (until very recently) has hardly discussed justice across borders. Yet public health problems often cross borders, and public health interventions have to measure up to the problems they address.


2006 ◽  
Vol 6 (2) ◽  
pp. 91-95 ◽  
Author(s):  
Kimberly E. Stone ◽  
Lori Burrell ◽  
Susan M. Higman ◽  
Elizabeth McFarlane ◽  
Loretta Fuddy ◽  
...  

Sign in / Sign up

Export Citation Format

Share Document