A new study shows that an artificial intelligence (AI) method that fuses medically relevant information enables critical circulatory failure to be predicted in the intensive care unit (ICU) several hours before it occurs. Developed at the Swiss Federal Institute of Technology (ETH; Zurich, Switzerland) and Bern University Hospital (Inselspital; Switzerland), the early-warning platform integrates measurements from multiple systems using a high-resolution database that holds 240 patient-years of data. For the study, the researchers used anonymized data from 36,000 admissions to ICUs, and were able to show that just 20 of these variables, including blood pressure, pulse, various blood values, the patient's age, and medications administered were sufficient to make accurate predictions. In a trial run of the algorithms developed, they were able to predict 90% of circulatory-failure events, with 82% of them identified more than two hours in advance. On average, the system raised 0.05 alarms per patient and hour.

-- A deep learning network was used to predict future blood glucose levels, as this can permit diabetes patients to take action before imminent hyperglycaemia and hypoglycaemia. A sequential model with one long-short-term memory (LSTM) layer, one bidirectional LSTM layer and several fully connected layers was used to predict blood glucose levels for different prediction horizons. The method was trained and tested on 26 datasets from 20 real patients. The proposed network outperforms the baseline methods in terms of all evaluation criteria. Diabetes can be mainly classified into Type 1 diabetes (T1D) and Type 2 diabetes (T2D), where the former is caused by destruction of the pancreatic beta cells resulting in insulin deficiency, while the latter due to the ineffective use of insulin.

Early diagnosis of interstitial lung diseases is crucial for their treatment, but even experienced physicians find it difficult, as their clinical manifestations are similar. In order to assist with the diagnosis, computer-aided diagnosis (CAD) systems have been developed. These commonly rely on a fixed scale classifier that scans CT images, recognizes textural lung patterns and generates a map of pathologies. In a previous study, we proposed a method for classifying lung tissue patterns using a deep convolutional neural network (CNN), with an architecture designed for the specific problem. In this study, we present an improved method for training the proposed network by transferring knowledge from the similar domain of general texture classification. Six publicly available texture databases are used to pretrain networks with the proposed architecture, which are then fine-tuned on the lung tissue data. The resulting CNNs are combined in an ensemble and their fused knowledge is compressed back to a network with the original architecture. The proposed approach resulted in an absolute increase of about 2% in the performance of the proposed CNN. The results demonstrate the potential of transfer learning in the field of medical image analysis, indicate the textural nature of the problem and show that the method used for training a network can be as important as designing its architecture.