Computer aided decision making in medicine

Empowering Medical Students: Harnessing Artificial Intelligence for Precision Point-of-Care Echocardiography Assessment of Left Ventricular Ejection Fraction

Introduction

Point-of-care ultrasound (POCUS) use is now universal among nonexperts. Artificial intelligence (AI) is currently employed by nonexperts in various imaging modalities to assist in diagnosis and decision making.

Aim

To evaluate the diagnostic accuracy of POCUS, operated by medical students with the assistance of an AI-based tool for assessing the left ventricular ejection fraction (LVEF) of patients admitted to a cardiology department.

Methods

Eight students underwent a 6-hour didactic and hands-on training session. Participants used a hand-held ultrasound device (HUD) equipped with an AI-based tool for the automatic evaluation of LVEF. The clips were assessed for LVEF by three methods: visually by the students, by students + the AI-based tool, and by the cardiologists. All LVEF measurements were compared to formal echocardiography completed within 24 hours and were evaluated for LVEF using the Simpson method and eyeballing assessment by expert echocardiographers.

Results

The study included 88 patients (aged 58.3 ± 16.3 years). The AI-based tool measurement was unsuccessful in 6 cases. Comparing LVEF reported by students' visual evaluation and students + AI vs. cardiologists revealed a correlation of 0.51 and 0.83, respectively. Comparing these three evaluation methods with the echocardiographers revealed a moderate/substantial agreement for the students + AI and cardiologists but only a fair agreement for the students' visual evaluation.

Conclusion

Medical students' utilization of an AI-based tool with a HUD for LVEF assessment achieved a level of accuracy similar to that of cardiologists. Furthermore, the use of AI by the students achieved moderate to substantial inter-rater reliability with expert echocardiographers' evaluation.

AIM: a personal view of where I have been and where we might be going

My own career in medical informatics and AI in medicine has oscillated between concerns with medical records and concerns with knowledge representation with decision support as a pivotal integrating issue. It has focused on using AI to organise information and reduce 'muddle' and improve the user interfaces to produce 'useful and usable systems' to help doctors with a 'humanly impossible task'. Increasingly knowledge representation and ontologies have become the fulcrum for orchestrating re-use of information and integration of systems. Encouragingly, the dilemma between computational tractability and expressiveness is lessening, and ontologies and description logics are joining the mainstream both in AI in Medicine and in Intelligent Information Management generally. It has been shown possible to scale up ontologies to meet medical needs, and increasingly ontologies are playing a key role in meeting the requirements to scale up the complexity of clinical systems to meet the ever increasing demands brought about by new emphasis on reduction of errors, clinical accountability, and the explosion of knowledge on the Web.

The design of an algorithm for pharmacists to evaluate ADRs in the elderly

An algorithm has been developed to help pharmacists who monitor patients being admitted to hospital to evaluate identified adverse drug reactions (ADRs). The design features six operational axes, comprising four subdivisions, with a unique score assigned to each. The final total of the sum of the individual scores for the six axes provides a measure of the probability that a suspicious event is drug-related.

Combining clinical judgement and statistical data in expert systems: over-the-telephone management decisions for critical congenital heart disease in the first month of life

When a new-born baby with congenital heart disease is referred to a regional specialist centre, the transportation management is crucial but must be decided on the basis of clinical information obtained over the telephone. We consider algorithmic and naive statistical approaches to helping in this decision, and on the basis of preliminary results the relative strengths and weaknesses are discussed. A synthesised logical and probabilistic approach appears to have the best potential and could be implemented on hand-held computers.

Better health data with a portable microcomputer at the periphery: an anthropometric survey in Cape Verde

A portable microcomputer was programmed to record anthropometric nutritional data from children aged under 7 years in either a clinic or a population survey situation. An alarm sounds when the anthropometric measurements of a child are below a predetermined value; an immediate check thus avoids the need for subsequent data cleaning and discarding of doubtful information. Data cut-off points in the computer can be adjusted to suit the survey or service needs of the situation. A print-out at the end of the clinic session provides immediate feedback for the staff and a record of the nutritional status of the group.In Cape Verde, 14 670 children attending clinics were surveyed; 26% were identified as stunted, 3% as wasted, and 1% as stunted and wasted. While a portable microcomputer can improve precision, speed and motivation, nutrition surveys still depend on accurate scales, careful measurements and competent staff.

The acute abdomen: management with microcomputer aid

This paper describes the management consequences of the use of a microcomputer as a special investigation in patients with an acute abdomen. Results in 812 patients seen by 42 junior doctors are compared six monthly and with baseline data from 295 cases from the preceding 2 years. Improvement in diagnostic ability from 48.5% to 71.8% (X2 = 25.8, P less than 0.001) resulted in a fall in negative appendicectomy from 37.5% to 9.71% (X2 = 16.2, P = less than 0.001). Bad management errors were also reduced from 22% to 10% (P = less than 0.01). The number of emergency investigation fell from 4 to 2 and inpatient stay of patients with non-surgical abdominal pain was reduced from 3 to 2 days. These results demonstrate that the use of microcomputers as investigative tools improves the surgical management of patients with acute abdominal pain.

Technology and medicine

Technology, which is older than science, has been of vital importance in the development of modern medicine. Even so, there are voices of dissent to be heard. The disenchantment with technology expressed by Aldous Huxley in Brave new world has been echoed by contemporary writers on the technology of modern medicine. Medicine is seen by some to have been dehumanized by technology, and techniques that are expensive are thought to be consuming a greater proportion of health resources than they deserve. The practice of medicine has, nevertheless, been transformed by modern technology and diagnostic techniques and therapeutic measures undreamed of a few short decades ago are now commonplace. There is no reason why these developments should be any more dehumanizing than the use of similar techniques in modern transportation or communication, nor is their expense out of proportion when compared with other demands on the nation's purse. British workers have been at the forefront of many recent advances. Yet, even though the National Health Service provides a ready market for the products of British medical technology, the nation depends to an inordinate degree on imported products. In the development of appropriate medical technology there is an urgent need for better communication between inventors, scientists, industrialists and the National Health Service. At the same time there is an equal need for improved evaluation of untried techniques. The pressure for a central integrating body to coordinate resources could well be supported by the establishment of evaluation units in the different health authorities in this country.