Final presentation

Here is some of the information on my final poresentation with the apropriate source sightings. I will email you my powerpoint. A program for performing differential diagnosis on a microcomputer has been developed, utilizing a pattern recognition algorithm. The present configuration allows for input of 15 symptoms of 3 values (present, absent, or unknown), and compares the patient's symptom profile with 50 patterns which point to as many as 10 disease designations. The investigator may stipulate either a rigorous or permissive pattern matching, thus obtaining either a selective or exhaustive ranking of possible diagnoses. The program can record patient data, recall data given any one parameter, and can construct tables of incidence. This inexpensive system was designed for an office or community level practice, where the pattern arrays will be trained for its specific patient populations. Presently, data from the Georgetown University Student Health Service is being introduced as the program's first clinical trial. Background: Clinical decision support systems assist physicians in interpreting complex patient data. However, they typically operate on a per-patient basis and do not exploit the extensive latent medical knowledge in electronic health records (EHRs). The emergence of large EHR systems offers the opportunity to integrate population information actively into these tools. Methods: Here, we assess the ability of a large corpus of electronic records to predict individual discharge diagnoses. We present a method that exploits similarities between patients along multiple dimensions to predict the eventual discharge diagnoses. Results: Using demographic, initial blood and electrocardiography measurements, as well as medical history of hospitalized patients from two independent hospitals, we obtained high performance in cross-validation (area under the curve >0.88) and correctly predicted at least one diagnosis among the top ten predictions for more than 84% of the patients tested. Importantly, our method provides accurate predictions (>0.86 precision in cross validation) for major disease categories, including infectious and parasitic diseases, endocrine and metabolic diseases and diseases of the circulatory systems. Our performance applies to both chronic and acute diagnoses. Conclusions: Our results suggest that one can harness the wealth of population-based information embedded in electronic health records for patient-specific predictive tasks. [ABSTRACT FROM AUTHOR] This paper examines the diagnostic storytelling that medical residents perform in order to situate patients in a story trajectory with an imputed past and future. It is a study of “ordinary” expertise, as practiced by a family practice medical team in a small urban community hospital in the United States. Narrative storytelling—an activity that is at once cognitive and practical—allows residents to identify the sort of disease, the kind of patient, and the likely outcome for this patient, based on what the resident knows about patients like these. Residents acquire a set of narrative templates, or rough outlines, that they deploy when they encounter a new patient or his or her information. Going into an admissions interview, a resident already has a set of “facts” about the patient and his or her complaint. In a process that is routine, habitual, and iterative, a resident starts from this set of facts and draws on his or her repertoire of narrative templates to pursue a line of questioning that starts to define relevance for this patient, a relevance that is revised as the physician begins to settle on a story. These templates make a first organizing pass at answering, “What’s going on with this patient?” They provide the preliminary structure, the warp and weft, for building a patient story that holds together long enough to diagnose, treat, and discharge the patient. Diagnostic stories are shaped by what residents think they can do for the patient, practically speaking, and by habitual hospital activity. Most current model-based diagnosis formalisms and algorithms are defined only for static systems, which is often inadequate for medical reasoning. In this paper we describe a model-based framework plus algorithms for diagnosing time-dependent systems where we can define qualitative temporal scenarios. Complex temporal behavior is described within a logical framework extended by qualitative temporal constraints. Abstract observations aggregate from observations at time points to assumptions over time intervals. These concepts provide a very natural representation and make diagnosis independent of the number of actual observations and the temporal resolution. The concept of abstract temporal diagnosis captures in a natural way the kind of indefinite temporal knowledge which is frequently available in medical diagnoses. We use viral hepatitis B (including a set of real hepatitis B data) to illustrate and evaluate our framework. The comparison of our results with the results of Hepaxpert-I is promising. The diagnosis computed in our system is often more precise than the diagnosis in Hepaxpert-I and we detect inconsistent data sequences which cannot be detected in the latter system. Background: Deriving an appropriate differential diagnosis is a key clinical competency, but there is little data available on how medical students learn this skill. Software resources designed to complement clinical reasoning might be asset in helping them in this task. Aims: The goals of this study were to identify the resources third year medical students use to solve a challenging diagnostic case, and specifically to evaluate the usefulness of Isabel, a second-generation electronic diagnosis support system. Methods: Third year medical students (n = 117) were presented a challenging case and asked to identify and prioritize their top 3 diagnoses, report the time devoted to the exercise, and list the resources they used and their relative usefulness. Students were randomized to receive (or not) free access, instruction, and encouragement to use to a web-based decision support system (Isabel). Results: Students who identified the correct diagnosis as their first choice spent significantly more time on the case than did the other students (3.75 ± 0.28 hours vs 2.88 ± 0.15 hours, p < 0.05). Students used electronic resources extensively, in particular Google. Students who self-reported use of Isabel had greater success identifying the correct diagnosis (24/33 = 73% for users vs 45/84 = 53% for non-users) a difference of borderline statistical significance. Conclusions: These findings indicate that medical trainees use a wide range of electronic decision support products to solve challenging cases. Medical education needs to adapt to this reality, and address the need to teach future clinicians how to use these tools to advantage. [ABSTRACT FROM AUTHOR] Time per visit Objectives. To use an innovative videotape analysis method to examine how clinic time was spent during elderly patients' visits to primary care physicians. Secondary objectives were to identify the factors that influence time allocations. Data Sources. A convenience sample of 392 videotapes of routine office visits conducted between 1998 and 2000 from multiple primary care practices in the United States, supplemented by patient and physician surveys. Research Design. Videotaped visits were examined for visit length and time devoted to specific topics—a novel approach to study time allocation. A survival analysis model analyzed the effects of patient, physician, and physician practice setting on how clinic time was spent. Principal Findings. Very limited amount of time was dedicated to specific topics in office visits. The median visit length was 15.7 minutes covering a median of six topics. About 5 minutes were spent on the longest topic whereas the remaining topics each received 1.1 minutes. While time spent by patient and physician on a topic responded to many factors, length of the visit overall varied little even when contents of visits varied widely. Macro factors associated with each site had more influence on visit and topic length than the nature of the problem patients presented. Conclusions. Many topics compete for visit time, resulting in small amount of time being spent on each topic. A highly regimented schedule might interfere with having sufficient time for patients with complex or multiple problems. Efforts to improve the quality of care need to recognize the time pressure on both patients and physicians, the effects of financial incentives, and the time costs of improving patient–physician interactions. [ABSTRACT FROM AUTHOR] The objectives of this study were to assess the relationship between wait time and parent satisfaction and determine whether time with the physician potentially moderated any observed negative effects of long wait time. Data were collected from parents in a pediatric outpatient clinic. Parent satisfaction with the clinic visit was significantly negatively related to wait times. More time spent with the physician was positively related to satisfaction independent of wait times. Furthermore, among clinic visits with long wait times, more time with the physician showed a relatively strong positive relationship with parent satisfaction. Therefore, although long wait times was related to decreased parent satisfaction with pediatric clinic visits, increased time with the physician tended to moderate this relationship. This paper reports a study exploring patients' views about consulting with a primary care nurse practitioner. United Kingdom based randomized controlled trials comparing the work of doctors and nurse practitioners add considerable weight to the view that patients tend to be more satisfied with primary care nurse practitioner consultations. However, there is a need for qualitative research to explore issues raised by the trials. A judgement sample of 10 patients consulting with a primary care nurse practitioner was drawn. In-depth interviews were conducted and analysed thematically. The data were collected in 2000-2001. The following themes were identified in the data: time spent in the consultation; and time as a commodity in patients' lives. Time matters to patients when they consult on their health, whether it is time to discuss problems or time saved as a result of having issues resolved, thus minimizing further visits. Factors associated with the style and emphasis of consultations are also important. Understanding the relationship between time, and style and emphasis of consultation may help to explain patients' satisfaction with primary care nurse practitioners. Question: Why Do I Wait In the Waiting Room for Such a Long Time at a Doctors Appointment? Patients are often frustrated that they make an appointment for a certain time, they arrive on time, yet they are kept in the waiting room for too long a time before they see the doctor. When we understand why this happens, we can take steps to change it, or make it easier to tolerate. Answer: Like too many questions in healthcare, the answer to why we are kept in the waiting room for so long is, "follow the money." Doctors are paid by insurance and Medicare for every patient they see according to why they see the patient, and what procedures they perform for the patient, and (this is key) not by the amount of time they spend with the patient. Since their goal is to maximize their income, they will schedule as many patients into their day as possible. More patients plus more procedures equals more income. In any given day, they may not be sure what services they'll be performing for individual patients, and some patients require more time for their services than others. Equipment may break down. An obstetrician may be delivering a baby. There may even be emergencies. We lose our patience because we believe the time just has not been scheduled well. Understanding that it's the volume of patients and procedures, not the time spent per patient, that comprises a doctors' income, it's easier to understand why they get so far behind, and why we are kept waiting. Nationwide, the average wait time to see a doctor last year was 23 minutes, according to the health care consultants Press Ganey. Neurosurgeons have the longest wait times (30 minutes) and optometrists the shortest (17 minutes), according to the report. Fisher, Paul. "Micro Computers in Medical Diagnosis." ACM Digital Library. 01 01 1980: 75-79. Web. 13 Dec. 2013. . (Fisher 75-79) Davenport, Nancy. "Medical residents’ use of narrative templates in storytelling and diagnosis." Social Science & Medicine. 01 09 2011: 1. Web. 13 Dec. 2013. (Davenport 1) Johann, Christopher. "Abstract temporal diagnosis in medical domains." Artificial Intellegence in Medicine. 01 07 1997: 1. Web. 13 Dec. 2013. . (Johann 1) Feddock, Christopher. "Is Time Spent With the Physician Associated With Parent Dissatisfaction Due to Long Waiting Times?." Evaluation & The HEalth Profession. 10 05 2010: 1. Web. 13 Dec. 2013. . (Feddock 1) Torrey, Trisha. "Why Do I Wait In the Waiting Room for Such a Long Time at a Doctors Appointment?." Patient Empowerment. 14 11 2008: 1. Web. 13 Dec. 2013. . (Torrey 1) Alderman, Lesley. "The Doctor Will See You Eventually." New York Times. 01 08 2011: 1. Web. 13 Dec. 2013. . (Alderman 1)