The Role of Artificial Intelligence for Providing Scientific Content for Laboratory Medicine.

BACKGROUND: Artificial intelligence (AI) promises to become an important tool in the practice of laboratory medicine. AI programs are available online that can provide concise medical and laboratory information within seconds after a question is submitted. METHODS: We posed the following contemporary and relevant question for clinical chemists using an AI program: "Should labs eliminate CK-MB testing?" The results of this inquiry were critically reviewed by a cardiologist, emergency department physician, and clinical laboratorians for accuracy and appropriateness. RESULTS: An AI report answering this question was generated within 15 s. The experts felt that the information was inaccurate with the statements that CK-MB results are released earlier than cardiac troponin (cTn), and are more useful for detection of myocardial injury in patients with renal insufficiencies. The summary omitted discussion on the ongoing debate for periprocedural detection of acute myocardial infarction (MI), the perceived value for detection of reinfarction, the value in risk stratification compared to cTn, the economic justification for testing both CK-MB and cTn, and medicolegal aspects of testing when results are discordant. CONCLUSIONS: At this time, AI does not appear to be ready to be used by clinical laboratories for answering important practice questions.

BNP Consensus Panel 2004: A clinical approach for the diagnostic, prognostic, screening, treatment monitoring, and therapeutic roles of natriuretic peptides in cardiovascular diseases.

Among the most exciting developments in the field of heart failure in recent times has been the rediscovery of the natriuretic peptide system and its pleuripotent effects on cardiac structure and function. This is particularly true of its natriuretic and hemodynamic effects. There has been an explosion of the knowledge base seeking to understand the wide range of homeostatic, regulatory, and counter-regulatory functions in which the natriuretic peptide system participates. Additional interest has been stimulated by advances in technology such as point-of-care and core laboratory BNP assays and the use of the recombinant B-type natriuretic peptide nesiritide as a treatment option. Despite this recent interest, the available literature lacks a comprehensive expert review of the current science and roles of natriuretic peptides for diagnostic, prognostic, screening, treatment monitoring, and therapeutic purposes. More importantly, a summary updating and guiding the clinician on most of these advances was lacking. An expert Consensus Panel with basic, methodological, and clinical expertise was convened to summarize current knowledge in these areas and the findings and consensus statements are contained herein.

Effective observation unit treatment of decompensated heart failure.

There is little information on the effectiveness of emergency department (ED) observation unit (OU) heart failure (HF) therapy. The authors' objective was to evaluate outcomes after implementation of an ED-OU treatment protocol for HF exacerbation. Unblinded assessment of the effectiveness of an HF protocol was performed, controlled by outcome for 9 months prior to implementation. This included diagnostic and therapeutic algorithms, cardiology consultation, close monitoring, patient education, and discharge planning. Adverse outcomes were defined as the 90-day rates of ED HF revisits, hospital HF readmissions, or death, as determined by chart review, computer database search, and phone follow-up. One hundred fifty-four patients were enrolled; 50 entered before, and 104 after protocol implementation. Only six (12%) in the preprotocol and one (1%) of the postprotocol group were lost to follow-up. After an OU visit, postprotocol 90-day ED HF revisit rates declined 56% (0.90-0.51; p<0.0000) and the 90-day HF rehospitalization rate decreased 64% (0.77-0.50; p=0.007). The 90-day rates of death and OU HF readmission decreased from 4% to 1% (p=0.096) and 18% to 11% (p=0.099), respectively. An intensive outpatient ED OU HF management protocol safely decreases 90-day rates of emergency department visits and inpatient hospitalizations.

Prediction of short- and long-term outcomes by troponin t levels in low-risk patients evaluated for acute coronary syndromes.

STUDY OBJECTIVE: Recent reports suggest a short series of cardiac troponin (cTnT) testing effectively identifies patients at risk for cardiac events. However, there are few studies validating this strategy. The purpose of this study was to determine the ability of cTnT levels to predict short- and long-term outcomes in low-risk patients with suspected acute coronary syndromes. METHODS: This prospective longitudinal study was conducted in a 20-bed emergency department observation unit. Patients at low risk for acute coronary ischemia, with a normal creatine kinase-isoenzyme subunit MB (CKMB) index, were admitted to an observation unit for chest pain evaluation. Serum cTnT levels were measured at baseline and at 4, 8, and 16 hours after admission. The main outcome measures were adverse cardiac events (death, acute myocardial infarction, unstable angina, revascularization) during the index visit and within 6 months after discharge. Using manufacturer's recommendations, the cTnT level was considered abnormal if it exceeded 0.2 µg/L. RESULTS: Two hundred sixty-six patients were evaluated. Twenty-one (7.9%) had an adverse event during their index hospitalization. Troponin testing identified only 2 (9.5%) of these patients. Twenty (7.5%) had a cardiac event within 6 months; none were identified by cTnT testing. The sensitivity and specificity were 9.5% and 99.2%, respectively, at the index visit, and 0% and 98.4% at 6 months. The positive and negative predictive values were 50% and 93%, respectively, at the index visit; and 0% and 92% at 6 months. CONCLUSION: Determination of troponin T levels has a low sensitivity and high specificity for predicting outcomes in low-risk patients evaluated for suspected acute coronary syndromes. This study does not support a strategy of relying solely on troponin testing for disposition decisions. [Peacock WF IV, Emerman CL, McErlean ES, Deluca SA, van Lente F, Rao JS, Nissen SE: Prediction of short- and long-term outcomes by troponin T levels in low-risk patients evaluated for acute coronary syndromes. Ann Emerg Med. March 2000;35:213-220.].