Machine Learning for Health: Algorithm Auditing & Quality Control.

Developers proposing new machine learning for health (ML4H) tools often pledge to match or even surpass the performance of existing tools, yet the reality is usually more complicated. Reliable deployment of ML4H to the real world is challenging as examples from diabetic retinopathy or Covid-19 screening show. We envision an integrated framework of algorithm auditing and quality control that provides a path towards the effective and reliable application of ML systems in healthcare. In this editorial, we give a summary of ongoing work towards that vision and announce a call for participation to the special issue  Machine Learning for Health: Algorithm Auditing & Quality Control in this journal to advance the practice of ML4H auditing.

Piloting a Survey-Based Assessment of Transparency and Trustworthiness with Three Medical AI Tools.

Artificial intelligence (AI) offers the potential to support healthcare delivery, but poorly trained or validated algorithms bear risks of harm. Ethical guidelines stated transparency about model development and validation as a requirement for trustworthy AI. Abundant guidance exists to provide transparency through reporting, but poorly reported medical AI tools are common. To close this transparency gap, we developed and piloted a framework to quantify the transparency of medical AI tools with three use cases. Our framework comprises a survey to report on the intended use, training and validation data and processes, ethical considerations, and deployment recommendations. The transparency of each response was scored with either 0, 0.5, or 1 to reflect if the requested information was not, partially, or fully provided. Additionally, we assessed on an analogous three-point scale if the provided responses fulfilled the transparency requirement for a set of trustworthiness criteria from ethical guidelines. The degree of transparency and trustworthiness was calculated on a scale from 0% to 100%. Our assessment of three medical AI use cases pin-pointed reporting gaps and resulted in transparency scores of 67% for two use cases and one with 59%. We report anecdotal evidence that business constraints and limited information from external datasets were major obstacles to providing transparency for the three use cases. The observed transparency gaps also lowered the degree of trustworthiness, indicating compliance gaps with ethical guidelines. All three pilot use cases faced challenges to provide transparency about medical AI tools, but more studies are needed to investigate those in the wider medical AI sector. Applying this framework for an external assessment of transparency may be infeasible if business constraints prevent the disclosure of information. New strategies may be necessary to enable audits of medical AI tools while preserving business secrets.

A Functional Model for Unifying Brain Computer Interface Terminology.

Brain Computer Interface (BCI) technology is a critical area both for researchers and clinical practitioners. The IEEE P2731 working group is developing a comprehensive BCI lexicography and a functional model of BCI. The glossary and the functional model are inextricably intertwined. The functional model guides the development of the glossary. Terminology is developed from the basis of a BCI functional model. This paper provides the current status of the P2731 working group's progress towards developing a BCI terminology standard and functional model for the IEEE.

Bilateral renal cortical necrosis following acute pancreatitis - A rare complication of a common disease.

Acute renal cortical necrosis is a rare cause of intrinsic acute kidney injury (AKI) which is commonly associated with obstetric complications such as placental abruption and some serious systemic disorders such as hemolytic-uremic syndrome, sepsis, severe burns, and snake bite. Acute pancreatitis is an extremely rare cause of renal cortical necrosis, and only less than 10 cases are reported in the literature. Here, we present a 24-year-old male presented with features of acute pancreatitis and oliguric AKI. His pancreatic enzymes were above 1000 IU/mL at admission. He was initiated on hemodialysis. Percutaneous renal biopsy done at 4th week of illness showed features of diffuse renal cortical necrosis. Contrast-enhanced computed tomography demonstrated hypoattenuation of cortex compared to medulla consistent with renal cortical necrosis. He developed complications such as acute necrotic collection, pleural effusion and retinal detachment in addition to renal cortical necrosis which was managed conservatively. Since there was no improvement in the renal function now, he is being evaluated for renal transplantation.