Lee B. Lusted’s research while affiliated with University of Rochester and other places

... Within this distinctive setting, AMIE outperformed an unassisted board-certified physician in both top-1 and top-n accuracy. Whereas the CPCs have long been used as benchmarks for difficult diagnosis, it is also well-known that performance in CPCs in no way reflects a broader measure of competence in a physician's duties 16 . Furthermore, the act of forming a DDx comprises many other steps that are not scrutinized in this study, including the goal-directed acquisition of information under uncertainty (which is known to be challenging for AI systems despite recent technical progress in this direction [17][18][19]. ...

Reference:

Towards accurate differential diagnosis with large language models

... In this paper, mainly the fifth stage of medical diagnostics is studied, namely the stage of establishment of the diagnosis. However, due to the extreme importance of the fourth stage, this stage of medical diagnostics is briefly discussed from the perspective of possibility to apply mathematical methods, in particular, from the decision-making theory perspective, and in the context of the possibility of using computers to increase the capabilities of a physician, in particular, allowing to automate the processing as well as to improve the reliability and accuracy of the collected data assessment; to draw up such a treatment plan and to clarify the diagnoses, which could maximize the likelihood of giving the highest positive effect; to minimize the amount of required laboratory and instrumental medical research and procedures for a given patient; to receive an objective assessment of the results of current and further analyzes, etc. (for instance, see Melnikov, 1974;Ledley, 1962;Cutler, 1998;Pendyala & Figueira, 2017 and references given there). ...

Reference:

Logical-probabilistic diagnosis of human cardiovascular diseases based on Boolean algebra

... Multiple national initiatives [1], focus on cost cutting [2] and medical error reduction [3], and the need for healthcare quality improvement have given rise to the concept of Clinical Decision Support (CDS). The notion of CDS goes back to a concept called ''medical data processing'' in the 1960s [4], which for the first time entertained the idea that medical data processing by computers could make the physician's job easier. In order to utilize a computer program, the physician must learn how to communicate with it and how to correctly evaluate the information obtained from it. ...

Reference:

Clinical decision support: Converging toward an integrated architecture

... Without sufficient storage, computation or knowledge of the clinical decision, the clients frequently prefer outsourcing their data to the Cloud for model training and disease predicting. Ledley and lusted [24] firstly proposed a clinical decision support system which can help physicians to solve diagnostic problems. Later, a large number of disease prediction system based on various data mining techniques have been presented. ...

Reference:

PPCD: Privacy-preserving clinical decision with cloud support

... Clinicians and other healthcare leaders have been utilizing computers and other technology to support and/or guide their decision-making processes since the 1950s. (85)(86)(87) Computers are often used in healthcare to improve patient outcomes by improving precision of diagnoses or treatment planning or to improve system-level outcomes by increasing operational efficiency. In these capacities computers and other technological tools supplement human-level decision-making by confirming or questioning a clinician's medical decision given some clinical ...

Reference:

An Industrial Engineering-Based Approach to Designing and Evaluating Healthcare Systems to Improve Veteran Access to Care

... There are at least two important issues not approached by the reviewed papers: the risk of bias introduced by giving previous information to a clinician, before patient evaluation, and the risk of bias to language misinterpretation by the patient [72]. In HT, a clinician acts as a translator for subjective illness experience to medical language, where clinical reasoning and diagnostic algorithms may work upon [73]. ...

Reference:

Structured Solutions For Medical History Taking: A Historical Review

... By 1960, AI techniques were already beginning to be applied to model clinical reasoning and medical decision-making [9]. Work on the reasoning foundations for medical diagnosis, in which Bayes' formula was adapted to find conditional probabilities of disease given a set of symptoms [10], led to applying probabilistic approaches to model clinical reasoning over the next decade. ...

Reference:

Designing and Evaluating an Ensemble Reasoning-based Clinical Decision Support System

... Interventions include Computer-Aided Detection (CAD), where regions of interest are highlighted for later interpretation; Computer-Aided Diagnosis (CADx), where the computer presents a diagnosis but does not necessarily highlight regions of interest; and patient history/metadata presentation. These interventions generally function within the tool radiologists use to view images, the Picture Archiving and Communication System (PACS), though some will interface with the Radiology Information System (RIS) that houses scheduling/billing/patient metadata, Voice Recognition system (VR) used for report dictation, or in an external purpose built clients [7][8][9][10][11][12][13][14][15][16][17]. ...

Reference:

Theory of radiologist interaction with instant messaging decision support tools: A sequential-explanatory study

... In 1959, Ledley and Lusted reported that computers could help doctors in the diagnostic process [27]. Many papers have been published demonstrating the accuracy of computational medical diagnosis, generally in a very limited field such as thyroid disease or congenital heart disease. ...

Reference:

Sustainable Health Informatics: Health Informaticians as Alchemists

... Academics and industry collaborators apply AI to a variety of biomedical issues ranging from clinical prediction to phenotyping complex disease states, or for guiding diagnosis, prognosis, treatment, and lifestyle change. [1][2][3][4][5][6][7][8][9][10][11] While public perceptions of AI center on strong or artificial general intelligence (the ability for smart agents to think as humans do), most if not all published efforts in biomedicine focus on weak or applied AI. ...

Reference:

Stigma, biomarkers, and algorithmic bias: recommendations for precision behavioral health with artificial intelligence