Published By: Newsweek, 2/27/2017
>> View the Article <<
Summary
Human clinicians are known not to be very accurate at predicting suicides, so researchers are developing machine-learning algorithms that use multiple factors to identify short-term suicide risk. Data scientists trained the algorithm on data from thousands of clinical records, from both non-fatal suicide cases and random patients. Accuracy was significantly better than studying only one risk factor at a time. Using such a system could aid clinicians in targeting at-risk patients and treating them early.
Flesch-Kincaid Grade Level of Article: 10.5
Extended Discussion Questions
- The article mentions that convincing clinicians to trust a machine-learning algorithm instead of their instincts could be challenging.
- What do you think it would take for clinicians to trust this machine-learning algorithm?
- What questions might they have?
- Do you think the mental healthcare field should begin to use machine-learning algorithms to predict patients’ suicide risk?
- Under what circumstances would you expect such a system to be used?
- What questions and concerns do you think health insurance companies might have about treatments being recommended based on an algorithm’s prediction of suicide risk?
- Do you think this research has the potential to spur progress in mental health care in general? Why or why not?
- Moving beyond suicide risk, as a patient, what would you think if your doctor or healthcare provider told you they were recommending a treatment (for any condition) based on the risk predictions of a machine-learning algorithm?
- Based on what you’ve learned in this class, what questions would you have before deciding whether to go through with the treatment?
- If medical researchers wanted to do a similar study using social media, would you allow them to access your online feeds to obtain data to train their algorithms? Why or why not?
- How do you think other people your age would respond? People in different age groups?
- Could any ethical issues arise from such research?
Relating This Story to the CSP Curriculum Framework
Global Impact Learning Objectives:
- LO 7.3.1 Analyze the beneficial and harmful effects of computing.
- LO 7.4.1 Explain the connections between computing and real-world contexts, including economic, social, and cultural contexts.
Global Impact Essential Knowledge:
- EK 7.2.1B Scientific computing has enabled innovation in science and business.
- EK 7.3.1A Innovations enabled by computing raise legal and ethical concerns.
Other CSP Big Ideas:
- Idea 3 Data and Information
- Idea 4 Algorithms
Banner Image: “Network Visualization – Violet – Offset Crop“, derivative work by ICSI. New license: CC BY-SA 4.0. Based on “Social Network Analysis Visualization” by Martin Grandjean. Original license: CC BY-SA 3.0.
Home › Forums › Machine-Learning Algorithms Can Predict Suicide Risk More Readily Than Clinicians, Study Finds
Tagged: 3 Data & Info, 4 Algorithms, 7.2.1B Scientific computing, 7.3.1 Benefits and harm, 7.3.1A Law and ethics, 7.4.1 Real-world contexts