Parker Jewish Institute for Health Care and Rehabilitation

Background: Clinically significant valvular heart disease (VHD) affects 1 in 10 adults over 65. Cardiac auscultation, the current point of care clinical standard, has shown a 44% sensitivity for detecting VHD, leaving most patients undiagnosed. A deep learning based artificial intelligence (AI) platform that detects cardiac murmurs associated with clinically significant VHD (moderate severity or higher, confirmed by echocardiogram) was used to assess its real-time impact on the point of care. Hypothesis: Use of AI during point of care auscultation may lead to higher discovery rates and earlier diagnosis of VHD compared to conventional practice. Aim: Evaluate real world performance of AI vs. primary care physician (PCP) auscultation in identifying previously undiagnosed VHD. Methods: This blinded, prospective study enrolled 369 patients aged 50 and older without a prior VHD diagnosis or history of murmur from three different primary care clinics. Four-point cardiac auscultation was performed on each patient by (1) PCP with a standard stethoscope, and (2) coordinator with an Eko digital stethoscope to collect phonocardiogram (PCG) data for analysis by the AI. Each patient received an echocardiogram to confirm whether clinically significant VHD was present, and their PCG recordings were reviewed by an outside expert panel to confirm whether audible murmurs were present. PCP and expert panel were blinded to AI and echocardiogram results. Performance metrics were calculated for both PCP auscultation and the AI in detecting audible VHD. Results: The AI showed over twofold improvement in sensitivity vs. PCP auscultation for detecting audible VHD (94.1% vs. 41.2%) with limited impact on specificity (84.5% vs. 95.5%). The AI identified 22 patients with moderate-or-greater VHD who were previously undiagnosed, while PCPs identified eight previously undiagnosed patients with VHD. Conclusion: When applied in a primary care setting, a digital stethoscope with structural murmur detection AI showed meaningful impact on new discovery of VHD as compared to conventional practice. These results suggest that AI-powered auscultation at the point of care may significantly increase earlier VHD discovery, facilitate appropriate patient care, and improve outcomes.

We studied prospectively the concordance between chief complaint as given by 100 geriatric patients and the chief complaint perceived by their caregiver compared with the principal medical problem identified by the physician. Caregiver's additional information further strengthened this concordance. In demented patients, the presence of a caregiver was virtually essential to reach a concordance approaching that of non-demented elderly. Health Care practitioners should strongly encourage the presence, and the participation, of a caregiver during the assessment of geriatric patients.

This article reports the findings of a retrospective study of elderly Medicare patients (N = 8,915) discharged from New York City hospitals prior to the implementation of the Medicare Prospective Payment System in New York State. Its purpose was to investigate physical comorbidity, mental comorbidity, age, and other factors for their relationship with hospital use. Study findings suggest that age, as used in the diagnosis-related group (DRG) classification scheme, is less powerful than comorbidity as a predictor of hospital use. Dementia, which is not recognized as a valid comorbid condition by the DRG system, was also found to be positively associated with use.

During an 11-month period, 70 tube-fed patients aged 65 to 95 years were studied prospectively to determine the indications, benefits, and complications of enteral alimentation. Indications for alimentation were refusal to swallow (35 patients [50%], dysphagia without obstruction (33 [47%]), and esophageal obstruction (two [3%]). Nasogastric tubes (NGTs) were used initially in 69 patients; 15 of these subsequently required a gastrostomy tube (GT). One patient was treated initially with a gastrostomy. Indicators of nutritional status included weight, hemoglobin level, hematocrit, and serum albumin level. During the first two weeks the most common problems in the NGT group were agitation and self-extubation (36 patients [67%]) and aspiration pneumonia (23 [43%]). In GT patients the most common early problems were aspiration pneumonia (nine patients [56%]), tube dysfunction (eight [50%]), and agitation and extubation (seven [44%]). The common late problems were aspiration pneumonia (24 patients [44%] in the NGT group and nine [56%] in the GT group), and feeding tube dysfunction in six (38%) of the GT group. Self-extubation as a late problem was limited to the NGT group (21 patients [39%]). Twenty-eight (40%) of the 70 patients died during the study period.

To the Editor:—The geropsychiatrist must have access to a complete medical evaluation as part of any initial workup. Our experience indicates that the compounded effect of medical and psychiatric problems in the elderly is additive, increasing both morbidity and mortality. In many cases, the psychiatrist will insist on additional medical workup to help in diagnosis and treatment planning.1 The geriatricians are aware of the necessity of a careful medical evaluation, preanesthesia, or preelectroconvulsive therapy as well as perioperative follow-up in a group of patients in which multiple disease is the rule and cardiovascular problems are extremely frequent. Alexopoulos, in his study of medical complications in 293 patients receiving electroconvulsive therapy (ECT) (September 1984) fails to demonstrate the cause-effect relationship between ECT and the so-called complications. These could be the result of multiple factors including: l)exacerbations of the patient's current or preexisting medical condition; 2) recent psychiatric or chronic psychiatric illness, causing an exacerbation of medical illnesses; or 3) the altered effect of anesthetics in the elderly. Most importantly is the possibility that ECT had no effect on the development of medical complications. A comparison of a matched population of medically ill depressed patients who received antidepressant medication and/or psychotherapy v ECT would have been more significant. The different problems cited by Alexopoulos could have occurred spontaneously. His final stressing of the need of medical evaluation in these patients is commonplace in the geriatric literature, no matter what the particular situation is, and ECT is no exception. We believe it is premature to implicate ECT as a cause of significant medical problems in this population. Electroconvulsive therapy is an important part of the therapeutic armamentarium of the geropsychiatrist, and there is a consensus in affirming that age is not a contraindication.2