With the advent of artificial intelligence (AI), machines are increasingly being used to complete complicated tasks, yielding remarkable results. Machine learning (ML) is the most relevant subset of AI in medicine, which will soon become an integral part of our everyday practice. Therefore, physicians should acquaint themselves with ML and AI, and their role as an enabler rather than a competitor. Herein, we introduce basic concepts and terms used in AI and ML, and aim to demystify commonly used AI/ML algorithms such as learning methods including neural networks/deep learning, decision tree and application domain in computer vision and natural language processing through specific examples. We discuss how machines are already being used to augment the physician’s decision-making process, and postulate the potential impact of ML on medical practice and medical research based on its current capabilities and known limitations. Moreover, we discuss the feasibility of full machine autonomy in medicine.

Pneumonia is one of the most common treatable causes of death, and early diagnosis allows for early intervention. Automated diagnosis of pneumonia can therefore improve outcomes. However, it is challenging to develop high-performance deep learning models due to the lack of well-annotated data for training. This paper proposes a novel method, called Deep Supervised Domain Adaptation (DSDA), to automatically diagnose pneumonia from chest X-ray images. Specifically, we propose to transfer the knowledge from a publicly available large-scale source dataset (ChestX-ray14) to a well-annotated but small-scale target dataset (the TTSH dataset). DSDA aligns the distributions of the source domain and the target domain according to the underlying semantics of the training samples. It includes two task-specific sub-networks for the source domain and the target domain, respectively. These two sub-networks share the feature extraction layers and are trained in an end-to-end manner. Unlike most existing domain adaptation approaches that perform the same tasks in the source domain and the target domain, we attempt to transfer the knowledge from a multi-label classification task in the source domain to a binary classification task in the target domain. To evaluate the effectiveness of our method, we compare it with several existing peer methods. The experimental results show that our method can achieve promising performance for automated pneumonia diagnosis.

The efficacy, limitations, and methods of studying antidepressant treatment continued beyond initial weeks of acute major depression remain incompletely resolved. For subjects treated in controlled trials for acute depression, we analyzed the relationship of relapse risk within 12 months of rerandomizing to placebo versus duration of initial treatment and putative stabilization. With data from placebo arms of 45 relevant controlled trials identified in recent, systematic reviews were pooled and analyzed by regression modeling. There was a strong inverse correlation of shorter initial treatment and greater relapse risk after rerandomizing to placebo treatment, best fit to a power function (P ≤ 0.003); relapse risk differed by 11.4-fold, declining sharply as initial treatment continued for 16 to 20 weeks or more. Discontinuation of antidepressant treatment for major depressive episodes at times less than 6 months was associated with rising risks after randomization to continuation with placebo. This relationship requires critical consideration in both clinical management of depressed patients and the design and interpretation of treatment discontinuation trials.

Immune responses in allergic diseases begin with allergen sensitization, which usually occurs in childhood. Allergen sensitization involves a complex interplay of genetic and environmental factors, and sensitization patterns may change with age. To determine the predictors of allergen sensitization in the first 3 years of life in the growing up in Singapore towards healthy outcomes (GUSTO) prospective birth cohort study. Interviewers collected information on demographics, family history of allergy, social and lifestyle factors, and the child’s health. We analyzed data from 849 children who completed skin prick testing (SPT) to inhalant allergens (house dust mites: Dermatophagoides pteronyssinus, Dermatophagoides farinae, and Blomia tropicalis) and food allergens (egg, peanut and cow’s milk) to assess risk factors for allergen sensitization at 18 months. To ensure that clinical phenotypes preceded allergen sensitization, we also analyzed data from 649 children who had a negative skin prick test at 18 months and completed skin prick testing at 36 months. We observed a significant association between eczema reported before 18 months and a positive SPT at 18 months [aOR 4.5 (1.9–10.7)]. Ninety-five (14.6 %) children with negative SPTs at 18 months developed positive tests at 36 months. Onset of eczema before 18 months was associated with an increased risk of new allergen sensitization at 36 months among children non-sensitized at 18 months [aOR 3.4 (1.2–9.3)]. An association was seen between wheeze reported before 18 months and new allergen sensitization at 36 months [aOR 3.2 (1.1–9.1)]. We found no significant association, however, between rhinitis reported before 18 months and new allergen sensitization at 36 months. Early onset of eczema and wheeze are risk factors for later allergen sensitization, suggesting a possible increased susceptibility to allergen exposure through an impaired skin barrier or defective airway epithelium. Trial registration NCT01174875 Registered 1 July 2010, retrospectively registered

This review article serves to highlight radiological services as a major cost driver for the healthcare sector, and the potential improvements in productivity and cost savings that can be generated by incorporating artificial intelligence (AI) into the radiology workflow, referencing Singapore healthcare as an example. More specifically, we will discuss the opportunities for AI in lowering healthcare costs and supporting transformational shifts in our care model in the following domains: predictive analytics for optimising throughput and appropriate referrals, computer vision for image enhancement (to increase scanner efficiency and decrease radiation exposure) and pattern recognition (to aid human interpretation and worklist prioritisation), natural language processing and large language models for optimising reports and text data-mining. In the context of preventive health, we will discuss how AI can support population level screening for major disease burdens through opportunistic screening and democratise expertise to increase access to radiological services in primary and community care.

(1) Background: Chest radiographs are the mainstay of initial radiological investigation in this COVID-19 pandemic. A reliable and readily deployable artificial intelligence (AI) algorithm that detects pneumonia in COVID-19 suspects can be useful for screening or triage in a hospital setting. This study has a few objectives: first, to develop a model that accurately detects pneumonia in COVID-19 suspects; second, to assess its performance in a real-world clinical setting; and third, by integrating the model with the daily clinical workflow, to measure its impact on report turn-around time. (2) Methods: The model was developed from the NIH Chest-14 open-source dataset and fine-tuned using an internal dataset comprising more than 4000 CXRs acquired in our institution. Input from two senior radiologists provided the reference standard. The model was integrated into daily clinical workflow, prioritising abnormal CXRs for expedited reporting. Area under the receiver operating characteristic curve (AUC), F1 score, sensitivity, and specificity were calculated to characterise diagnostic performance. The average time taken by radiologists in reporting the CXRs was compared against the mean baseline time taken prior to implementation of the AI model. (3) Results: 9431 unique CXRs were included in the datasets, of which 1232 were ground truth-labelled positive for pneumonia. On the “live” dataset, the model achieved an AUC of 0.95 (95% confidence interval (CI): 0.92, 0.96) corresponding to a specificity of 97% (95% CI: 0.97, 0.98) and sensitivity of 79% (95% CI: 0.72, 0.84). No statistically significant degradation of diagnostic performance was encountered during clinical deployment, and report turn-around time was reduced by 22%. (4) Conclusion: In real-world clinical deployment, our model expedites reporting of pneumonia in COVID-19 suspects while preserving diagnostic performance without significant model drift.