Digital Computer as Aid to Differential Diagnosis

Lipkin, Martin; Engle, Ralph L.; Davis, Betsy; Zworykin, V. K.; Ebald, R.; Sendrow, M.; Berkley, C

doi:10.1001/archinte.1961.03620070058008

Cited by 55 publications

(7 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The use of computers was introduced in medical education more than 40 years ago (Lipkin et al 1961). Although computer-assisted instruction (CAI) would naturally lend itself to a more complex presentation of content matter (Tegtmeyer et al 2001), early attempts mainly aimed at a linear transmission of knowledge.…”

Section: Introductionmentioning

confidence: 99%

Significant increase in factual knowledge with web-assisted problem-based learning as part of an undergraduate cardio-respiratory curriculum

Raupach

Münscher

Pukrop

et al. 2009

Adv in Health Sci Educ

View full text Add to dashboard Cite

In recent years, increasing attention has been paid to web-based learning although the advantages of computer-aided instruction over traditional teaching formats still need to be confirmed. This study examined whether participation in an online module on the differential diagnosis of dyspnoea impacts on student performance in a multiple choice examination of factual knowledge in cardiology and pneumology. A virtual problem-based learning environment for medical students supervised by postgraduate teachers was created. Seventy-four out of 183 fourth-year medical students volunteered to use the online module while attending a 6-week cardio-respiratory curriculum in summer 2007. Of these, 40 were randomly selected to be included (intervention group); the remaining 34 served as an internal control group. Analysis of all written exams taken during the preceding term showed that both groups were comparable (86.4 ± 1.1 vs. 85.9 ± 1.1%; p = 0.751). Students in the intervention group scored significantly higher in the final course assessment than students allocated to the control group (84.8 ± 1.3 vs. 79.5 ± 1.4%; p = 0.006; effect size 0.67). Thus, additional problem-based learning with an online module as part of an undergraduate cardio-respiratory curriculum lead to higher students' scores in an exam testing factual knowledge. Whether using this teaching format

show abstract

Section: Introductionmentioning

confidence: 99%

Significant increase in factual knowledge with web-assisted problem-based learning as part of an undergraduate cardio-respiratory curriculum

Raupach

Münscher

Pukrop

et al. 2009

Adv in Health Sci Educ

View full text Add to dashboard Cite

show abstract

“…The problems implicit in the deterministic approach can be compared with those in the use of Bayes' theorem, a mathematical technic employed by previous workers in research on computer programs related to hematology (12)(13)(14)(15). Bayes' theorem permits calculation of the odds that a particular patient has a particular disease.…”

Section: Results and Evaluationmentioning

confidence: 99%

“…Computer technology has been used to collect patient histories (1); to interpret electrocardiograms (2,3); and to assist in the diagnosis and management of acid-base (4,5), electrolyte (6), respiratory (7), surgical (8), dermatologic (9, 10), and thyroid (11) disorders. In the field of hematology, the pioneering efforts of Upkin and coworkers served as a model for early work in computer-assisted diagnosis (12). Subsequently, Bishop and Warner developed a program for the diagnosis of polycythemic disorders, a program that provided the first example of the use of Bayes' theorem with continuous variables (13).…”

Section: Introductionmentioning

confidence: 99%

A computer program for the diagnosis of hematologic disorders

1977

View full text Add to dashboard Cite

A computer program has been developed to assist medical personnel in the diagnosis of hematologic disorders. The program requests information such as the patient's hematocrit, white blood‐cell count, platelet count, and selected physical findings. Major problems are identified, and the program then requests further information as needed to determine whether the patient has 1 or more of 174 hematologic disorders. An evaluation note is then printed that summarizes the most important hematologic data and includes a list of selected hematologic diagnoses, a discussion of why each diagnosis is listed, a description of its pathophysiology and information concerning etiology and treatment. The printout concludes with pertinent references to the medical literature. When the program was tested with 135 patients referred for hematologic consultation, diagnoses produced by the program were in complete agreement with the hematologist in 87 cases, in partial agreement in 23 cases and not in agreement in 25 cases. The program was also tested with 34 hematologic cases from the New England Journal of Medicine's Clinical‐Pathological Conferences. In 24 patients, the computer and anatomic diagnoses were in complete or partial agreement, and in 10 they disagreed. Anecdotal evidence suggests that explanations of pathophysiology contained in the evaluation notes may be useful to students. It is concluded that the program could be useful as a memory aid for the practitioner and as a teaching aid for the student.

show abstract

“…These included the rule-based and hypothesis-list approaches used in the DENDRAL Project [9,10], which influenced MYCIN, as well as experimental, instructional, interview-based, and cognitive approaches to the analysis of clinical problem solving [11,12,13,14,15,16], and the causal-taxonomic representation of underlying processes of disease [4,11]. While earlier computer models for medical decision-making were predominantly statistical or algorithmic [16,17,18,19,20,21,22,23,24], the new AI approaches developed structured representations of specific clinical domain knowledge over which a general inference engine could reason with a variety of heuristics, and provide advice or suggestions to the consulting user [25].…”

Section: Introductionmentioning

confidence: 99%

An Opening Chapter of the First Generation of Artificial Intelligence in Medicine: The First Rutgers AIM Workshop, June 1975

Kulikowski¹

2015

Yearb Med Inform

View full text Add to dashboard Cite

SummaryThe first generation of Artificial Intelligence (AI) in Medicine methods were developed in the early 1970's drawing on insights about problem solving in AI. They developed new ways of representing structured expert knowledge about clinical and biomedical problems using causal, taxonomic, associational, rule, and frame-based models. By 1975, several prototype systems had been developed and clinically tested, and the Rutgers Research Resource on Computers in Biomedicine hosted the first in a series of workshops on AI in Medicine that helped researchers and clinicians share their ideas, demonstrate their models, and comment on the prospects for the field. These developments and the workshops themselves benefited considerably from Stanford's SUMEX-AIM pioneering experiment in biomedical computer networking. This paper focuses on discussions about issues at the intersection of medicine and artificial intelligence that took place during the presentations and panels at the First Rutgers AIM Workshop in New Brunswick, New Jersey from June 14 to 17, 1975.

show abstract

Digital Computer as Aid to Differential Diagnosis

Cited by 55 publications

References 1 publication

Significant increase in factual knowledge with web-assisted problem-based learning as part of an undergraduate cardio-respiratory curriculum

Significant increase in factual knowledge with web-assisted problem-based learning as part of an undergraduate cardio-respiratory curriculum

A computer program for the diagnosis of hematologic disorders

An Opening Chapter of the First Generation of Artificial Intelligence in Medicine: The First Rutgers AIM Workshop, June 1975

Contact Info

Product

Resources

About