Closing the loop: automatically identifying abnormal imaging results in scanned documents.

OBJECTIVES: Scanned documents (SDs), while common in electronic health records and potentially rich in clinically relevant information, rarely fit well with clinician workflow. Here, we identify scanned imaging reports requiring follow-up with high recall and practically useful precision. MATERIALS AND METHODS: We focused on identifying imaging findings for 3 common causes of malpractice claims: (1) potentially malignant breast (mammography) and (2) lung (chest computed tomography [CT]) lesions and (3) long-bone fracture (X-ray) reports. We train our ClinicalBERT-based pipeline on existing typed/dictated reports classified manually or using ICD-10 codes, evaluate using a test set of manually classified SDs, and compare against string-matching (baseline approach). RESULTS: A total of 393 mammograms, 305 chest CT, and 683 bone X-ray reports were manually reviewed. The string-matching approach had an F1 of 0.667. For mammograms, chest CTs, and bone X-rays, respectively: models trained on manually classified training data and optimized for F1 reached an F1 of 0.900, 0.905, and 0.817, while separate models optimized for recall achieved a recall of 1.000 with precisions of 0.727, 0.518, and 0.275. Models trained on ICD-10-labelled data and optimized for F1 achieved F1 scores of 0.647, 0.830, and 0.643, while those optimized for recall achieved a recall of 1.0 with precisions of 0.407, 0.683, and 0.358. DISCUSSION: Our pipeline can identify abnormal reports with potentially useful performance and so decrease the manual effort required to screen for abnormal findings that require follow-up. CONCLUSION: It is possible to automatically identify clinically significant abnormalities in SDs with high recall and practically useful precision in a generalizable and minimally laborious way.

Cardiovascular Complications of Marijuana and Related Substances: A Review.

The recreational use of cannabis has sharply increased in recent years in parallel with its legalization and decriminalization in several countries. Commonly, the traditional cannabis has been replaced by potent synthetic cannabinoids and cannabimimetics in various forms. Despite overwhelming public perception of the safety of these substances, an increasing number of serious cardiovascular adverse events have been reported in temporal relation to recreational cannabis use. These have included sudden cardiac death, vascular (coronary, cerebral and peripheral) events, arrhythmias and stress cardiomyopathy among others. Many of the victims of these events are relatively young men with few if any cardiovascular risk factors. However, there are reasons to believe that older individuals and those with risk factors for or established cardiovascular disease are at even higher danger of such events following exposure to cannabis. The pathophysiological basis of these events is not fully understood and likely encompasses a complex interaction between the active ingredients (particularly the major cannabinoid, Δ9-tetrahydrocannabinol), and the endo-cannabinoid system, autonomic nervous system, as well as other receptor and non-receptor mediated pathways. Other complicating factors include opposing physiologic effects of other cannabinoids (predominantly cannabidiol), presence of regulatory proteins that act as metabolizing enzymes, binding molecules, or ligands, as well as functional polymorphisms of target receptors. Tolerance to the effects of cannabis may also develop on repeated exposures at least in part due to receptor downregulation or desensitization. Moreover, effects of cannabis may be enhanced or altered by concomitant use of other illicit drugs or medications used for treatment of established cardiovascular diseases. Regardless of these considerations, it is expected that the current cannabis epidemic would add significantly to the universal burden of cardiovascular diseases.

Posttraumatic stress disorder after myocardial infarction and coronary artery bypass grafting.

Post traumatic stress disorder is a psychiatric disease that is usually precipitated by life threatening stressors. Myocardial infarction, especially in the young can count as one such event. The development of post traumatic stress after a coronary event not only adversely effects psychiatric health, but leads to increased cardiovascular morbidity and mortality. There is increasing evidence that like major depression, post traumatic stress disorder is also a strong coronary risk factor. Early diagnosis and treatment of this disease in patients with acute manifestations of coronary artery disease can improve patient outcomes.

Acute Acalculous Cholecystitis as a Presenting Manifestation in Systemic Lupus Erythematosus.

Systemic lupus erythematosus (SLE) is known to involve the gastrointestinal tract, but gallbladder involvement is rare. The authors report the case of a 26-year-old postpartum female who presented with acute right upper quadrant abdominal pain and was diagnosed with acute acalculous cholecystitis (AAC). In the presence of concomitant features of nephritis, pericardial effusion, anaemia and positive ANA titre, the diagnosis of SLE was confirmed during hospitalisation. Histopathological analysis of the gall bladder revealed evidence of vasculitis. Although rare, AAC can be the first presentation of patients diagnosed with SLE. Prompt diagnosis and management results in a better patient outcome. LEARNING POINTS: Although rare, acute acalculous cholecystitis is to be suspected in patients in the setting of right upper quadrant pain associated with multisystem disease as it may manifest as an initial symptom of the multisystem disease.In women with pre-existing rheumatological disease, a high index of suspicion for manifestations of postpartum flares should be maintained.Definitive treatment includes cholecystectomy; high-dose steroid therapy has been reported to be successful in a few cases.

Can the time course of systemic inflammatory response syndrome score predict future organ failure in acute pancreatitis?

OBJECTIVES: In patients with acute pancreatitis (AP), we aimed to precisely quantify the association between systemic inflammatory response syndrome score (SIRSS), an easily measured bedside tool, and various adverse outcomes of AP. METHODS: We prospectively identified patients admitted to Mayo Clinic on day 1 of AP. Patients with positive SIRSS (≥2) on day 1 were further followed up with daily measurement of SIRSS and organ failure status for 14 days or until discharge. Positive SIRSS on day 1, persistent SIRSS on day 3, and time course of SIRSS were correlated with development of organ failure. RESULTS: SIRSS and persistent SIRSS were associated with all the complications of AP with a high sensitivity and negative predictive value, ranging from 73.1% to 100.0%. Persistent SIRSS at day 3 added significantly higher specificity to this association (71.7%-80.0%). All patients who developed late-onset organ failure had the highest possible value of cumulative SIRSS. CONCLUSIONS: SIRSS of less than 2 on day 1 has a high negative predictive value for complications of AP. Eighty percent of the patients with persistent SIRSS on day 3 will develop at least 1 adverse outcome. A new variable "cumulative SIRSS" has the potential to reliably predict late-onset persistent organ failure.