Sep 12, 2023
After diving into the murder trial of nurse Lucia de Berk, statistician Richard Gill became a leading expert on the statistics of medical murder cases. Together with colleagues, he now wrote a peer reviewed report about the statistical missteps in past medical murder trials. It gives recommendations for how legal systems can do better. ‘People’s intuition of an “impossible coincidence” sometimes falsely joins the dots in the evidence,’ he says in the Science Magazine.
Lucia de Berk was under trial for being present at a suspiciously high number of deaths and resuscitations. His wife told him about a “witch trial” and saying: ‘They’re using statistics; you should get involved, do something useful.’
At first Gill didn’t get involved, but years later the case would turn out to be the pinnacle of his career. He proved that the nurse went to jail based on bad statistics, tunnel visions and assumptions. ‘In a normal murder case, you actually have a body which has clearly been murdered,’ he says. ‘When there’s only a suspicious cluster of deaths, investigators may assume a murderer is at work and selectively focus on evidence that supports that assumption.’
Statistics to the rescue
When the court of appeals announced the acquittal of the nurse, Gill was there to celebrate. ‘It was one of the biggest events of my life,’ he says. ‘It was really joyful.’ And that became the start of lending his expertise as a statistician in medical murder cases.
With that expertise, Gill and his colleagues wrote a report published by the Royal Statistical Society (RSS) in September 2022. That report exposes the statistical missteps in past medical murder trials and makes recommendations for how legal systems can do better. One of the things that the report recommends is for investigators to be ‘blinded’. For example, having pathologists classify deaths as suspicious or not, without knowing which medical personnel were in attendance.
Gill hopes the report will help with new similar cases. The one of the British nurse Lucy Letby for expample, who is now on trial for the alleged murder of seven babies. Gill is retired, but still follows the case closely. As he will not be working much on forensic cases anymore, Gill hopes younger statisticians will feel compelled to help when bad statistics lead to injustice, as he did. ‘I sensed that in the Lucia case, I could make a difference. And that therefore I must.’
Read more about Richard Gill and his career in the article on the website of Science.