Augmented Intelligence to Identify Patients With Advanced Heart Failure in an Integrated Health System

BACKGROUND

Timely referral for specialist evaluation in patients with advanced heart failure (HF) is a Class 1 recommendation. However, the transition from stage C HF to advanced or stage D HF often goes undetected in routine care, resulting in delayed referral and higher mortality rates.

OBJECTIVES

The authors sought to develop an augmented intelligence-enabled workflow using machine learning to identify patients with stage D HF and streamline referral.

METHODS

We extracted data on HF patients with encounters from January 1, 2007, to November 30, 2020, from a HF registry within a regional, integrated health system. We created an ensemble machine learning model to predict stage C or stage D HF and integrated the results within the electronic health record.

RESULTS

In a retrospective data set of 14,846 patients, the model had a good positive predictive value (60%) and low sensitivity (25%) for identifying stage D HF in a 100-person, physician-reviewed, holdout test set. During prospective implementation of the workflow from April 1, 2021, to February 15, 2022, 416 patients were reviewed by a clinical coordinator, with agreement between the model and the coordinator in 50.3% of stage D predictions. Twenty-four patients have been scheduled for evaluation in a HF clinic, 4 patients started an evaluation for advanced therapies, and 1 patient received a left ventricular assist device.

CONCLUSIONS

An augmented intelligence-enabled workflow was integrated into clinical operations to identify patients with advanced HF. Endeavors such as this require a multidisciplinary team with experience in design thinking, informatics, quality improvement, operations, and health information technology, as well as dedicated resources to monitor and improve performance over time.

Hemorrhage risk with transjugular intrahepatic portosystemic shunt (TIPS) insertion at the main portal vein bifurcation with stent grafts

PURPOSE

The purpose of this study was to assess the incidence of major hemorrhage after transjugular intrahepatic portosystemic shunt (TIPS) insertion using a stent graft at the main portal vein bifurcation.

PATIENTS AND METHODS

TIPS insertion using stent grafts was performed in 215 patients due to non-variceal hemorrhage indications. There were 137 men and 78 women, with a mean age of 57 years±10.6 (SD) (range: 19-90 years). Based on retrospective review of portal venograms, TIPS inserted within 5mm from the portal vein bifurcation were considered "bifurcation TIPS", while those inserted 2cm or greater from the bifurcation were considered intrahepatic. Suspicion for acute major periprocedural hemorrhage were categorized as low, moderate, and high, based on the number of signs of hemorrhage.

RESULTS

Of 215 TIPS inserted for purposes other than hemorrhage, the TIPS was inserted at the portal bifurcation in 41 patients (29 men, 12 women; mean age, 55.9±11.7 (SD); range: 26-79 years) and intrahepatic in 62 patients (37 men, 25 women; mean age, 57.6±10.6 (SD), range: 34-82 years), whereas 112 were indeterminate in location. No active extravasations were identified on post-TIPS portal venograms. Suspicion for acute major hemorrhage was moderate or high in 3/41 (7%) of patients in the TIPS bifurcation group compared to 5/62 (8%) in the intrahepatic TIPS group (P>0.99). There were no significant differences in 30-day mortality rates (1/41 [2%] and 3/62 [5%] respectively; P> 0.99). No deaths or interventions were attributed to acute hemorrhage.

CONCLUSION

TIPS insertion at the portal bifurcation with stent grafts did not incur an elevated risk of hemorrhagic complications.

Obstructive sleep apnea patients use more health care resources ten years prior to diagnosis

Because Obstructive Sleep Apnea Syndrome (OSAS) patients may be treated for comorbidities prior to OSAS diagnosis, we examined the health care utilization records of 181 OSAS patients and those of matched controls. We compared OSA patient health care utilization for a ten-year interval prior to diagnosis to those of randomized age-, gender-, and geographically-matched controls from the general population. We found that OSAS patients used approximately twice the resources (as defined by physician claims and stays in hospital) in the ten years prior to their diagnosis. Physician claims for cases totaled $686,365 ($3,972 per patient) compared to $356,376 ($1,969 per patient) for the controls for the length of the study. Utilization was significantly higher in 7 of 10 years prior to diagnosis. OSAS patients also had more hospitalizations: they had 1,118 nights (6.2 per patient) in hospital versus 676 nights (3.7 per patient) for controls over the ten-year period. Thus OSA patients are heavy users of health care resources ten years prior to diagnosis.

Linkage of plasma Abeta42 to a quantitative locus on chromosome 10 in late-onset Alzheimer's disease pedigrees

Plasma Abeta42 (amyloid beta42 peptide) is invariably elevated in early-onset familial Alzheimer's disease (AD), and it is also increased in the first-degree relatives of patients with typical late-onset AD (LOAD). To detect LOAD loci that increase Abeta42, we used plasma Abeta42 as a surrogate trait and performed linkage analysis on extended AD pedigrees identified through a LOAD patient with extremely high plasma Abeta. Here, we report linkage to chromosome 10 with a maximal lod score of 3.93 at 81 centimorgans close to D10S1225. Remarkably, linkage to the same region was obtained independently in a genome-wide screen of LOAD sibling pairs. These results provide strong evidence for a novel LOAD locus on chromosome 10 that acts to increase Abeta.

Health care utilization in males with obstructive sleep apnea syndrome two years after diagnosis and treatment

OBJECTIVE

To document changes in health care utilization (physician claims and hospitalizations) two years after diagnosis and treatment of patients with OSAS.

DESIGN

Prospective observational cohort study.

SETTING

The study was done in the Canadian Province of Manitoba. OSAS patients were selected from a University-based sleep disorders center. Control subjects were selected from the general population.

PATIENTS AND CONTROLS

There were 344 OSAS patients on whom there was utilization data for the period of the study. They were matched to controls from the general population by gender, age, and geographic location.

MEASUREMENTS AND RESULTS

The difference in physician claims between the patients and their matched controls two years after diagnosis and treatment ($174+/-32.4 (SE) per year in Canadian dollars) was significantly less than the difference in the year before diagnosis ($260+/-35.7 (SE), p=0.038). Examining the subgroups of patients adhering (PAT) or not adhering (PNAT) to treatment revealed that the changes were only significant in the patients adhering to treatment. Hospital stays for the entire OSAS group decreased from 1.27 days+0.25(SE) per patient per year one year before diagnosis to 0.54+0.13 per patient per year (p=0.01). The changes in the PAT group (1.25+0.28 per patient per year one year before diagnosis to 0.53+0.14 per patient per year (p=0.034) were significant while in the PNAT group they were not.

CONCLUSIONS

Adherence to treatment in patients with OSAS results in a significant reduction in physician claims and hospital stays.

Health care utilization in the 10 years prior to diagnosis in obstructive sleep apnea syndrome patients

Obstructive sleep apnea syndrome (OSAS) patients may have symptoms for years prior to recognition of their disorder, or they may be treated for the associated comorbidities. We hypothesized that such patients would be heavy consumers of health care resources for several years prior to diagnosis. We therefore compared health service utilization for a 10-year interval prior to diagnosis of 181 OSA patients to those of randomly selected age-, gender-, and geographically matched controls from the general population. OSAS patients used approximately twice as many health care services (as defined by physician claims and overnight stays in hospital) in the 10 years prior to their initial diagnostic evaluation for apnea. Physician claims for the OSA patients totaled $686,365 ($3972 per patient), compared to $356,376 ($1969 per patient) for the controls for the 10-year period examined in this study. Use of health services was significantly higher in 7 of 10 years prior to diagnosis. The OSAS patients also had more overnight hospitalizations: they spent 1118 nights (6.2 per patient) in hospital vs 676 nights (3.7 per patient) for controls in the decade prior to diagnosis. We conclude that by the time patients are finally diagnosed for sleep apnea, they have already been heavy users of health services for several years. It is possible that our findings reflect not OSAS per se, but the presence of some of the risk factors that predispose to OSAS, such as obesity, alcohol usage and perhaps tobacco consumption.

Myoelectric prostheses for below-elbow amputees: the Trent experience

Experience of myoelectric prostheses for unilateral below-elbow amputees in a large region of Great Britain is presented. Of the cases considered, 14 were adults and 29 were 16 years of age or less. The rejection rate was 25% overall but it was lower in adults, at 17%. Comparisons with published data and other aspects of myoelectric prostheses are discussed. Just over half the 37 amputees interviewed were independent in activities of daily living; independence was more common in the adults, at 77%. A very large proportion of myoelectric prosthesis users also used body-powered prostheses, demonstrating a need for both types of prosthesis for optimum rehabilitation. It is recommended that myoelectric prosthetic programmes should be carried out from specialized centres with comprehensive facilities for this expensive rehabilitation aid.

Lead poisoning in rural Scotland

Nine people from four families living in rural parts of Scotland have been found to suffer from clinical or biochemical effects of lead poisoning. Five had symptoms and four had unequivocal evidence of excessive lead exposure. The source of lead has been traced to the domestic water supply which in all cases was grossly contaminated with lead acquired from lead plumbing systems, including lead storage tanks. Clinical improvement followed the replacement of lead piping in two families studied. Lead poisoning is a possible cause of chronic ill health in areas of plumbosolvent water.