Collaboration between explainable artificial intelligence and pulmonologists improves the accuracy of pulmonary function test interpretation.

BACKGROUND: Few studies have investigated the collaborative potential between artificial intelligence (AI) and pulmonologists for diagnosing pulmonary disease. We hypothesised that the collaboration between a pulmonologist and AI with explanations (explainable AI (XAI)) is superior in diagnostic interpretation of pulmonary function tests (PFTs) than the pulmonologist without support. METHODS: The study was conducted in two phases, a monocentre study (phase 1) and a multicentre intervention study (phase 2). Each phase utilised two different sets of 24 PFT reports of patients with a clinically validated gold standard diagnosis. Each PFT was interpreted without (control) and with XAI's suggestions (intervention). Pulmonologists provided a differential diagnosis consisting of a preferential diagnosis and optionally up to three additional diagnoses. The primary end-point compared accuracy of preferential and additional diagnoses between control and intervention. Secondary end-points were the number of diagnoses in differential diagnosis, diagnostic confidence and inter-rater agreement. We also analysed how XAI influenced pulmonologists' decisions. RESULTS: In phase 1 (n=16 pulmonologists), mean preferential and differential diagnostic accuracy significantly increased by 10.4% and 9.4%, respectively, between control and intervention (p<0.001). Improvements were somewhat lower but highly significant (p<0.0001) in phase 2 (5.4% and 8.7%, respectively; n=62 pulmonologists). In both phases, the number of diagnoses in the differential diagnosis did not reduce, but diagnostic confidence and inter-rater agreement significantly increased during intervention. Pulmonologists updated their decisions with XAI's feedback and consistently improved their baseline performance if AI provided correct predictions. CONCLUSION: A collaboration between a pulmonologist and XAI is better at interpreting PFTs than individual pulmonologists reading without XAI support or XAI alone.

Azole-Induced Myositis after Combined Lung-Liver Transplantation.

Lung transplant recipients experience a high rate of invasive pulmonary aspergillosis infections, for which voriconazole is the treatment of choice. We report a patient who developed voriconazole-induced myositis that relapsed after one dose of isavuconazole. Our patient was a 38-year-old man who received a single sequential lung transplantation and liver transplantation because of end-stage cystic fibrosis. He presented to our emergency room with acute pain in both forearms at 3 weeks after voriconazole was initiated for invasive pulmonary aspergillosis infection. Levels of voriconazole were normal during the course of therapy. After stopping voriconazole, the symptoms decreased but relapsed after one dose of isavuconazole. Other causes of muscle pain and inflammation were excluded. Magnetic resonance imaging of both arms showed muscle edema in both arms, including involvement of the fascia, consistent with myositis. There were no signs of necrosis. Isavuconazole was discontinued, and the corticosteroid dose was temporarily increased, with rapid resolution of all complaints. Our patient is the fourth reported case of voriconazole-induced myositis, and the first whose symptoms relapsed after initiating isavuconazole.

Combined hepatocellular-cholangiocarcinoma in a patient with Abernethy malformation and tetralogy of Fallot: A case report.

Abernethy malformation is a rare congenital anomaly of the portal vein where the portal blood bypasses the liver. We report the first case of a patient with Abernethy malformation and tetralogy of Fallot associated with nodular regenerative hyperplasia and focal nodular hyperplasia (FNH), which finally evolved to a giant hepatocellular-cholangiocarcinoma (HCC-CC) of the liver, successfully resected. (Hepatology 2016;64:1800-1802).