New ADHD Screening Tool Disorder Matches DSM 5 Criteria

Adult ADHD can be accurately identified by a brief new screening tool designed using a machine-learning algorithm.

A brief new screening tool designed using a machine-learning algorithm can accurately identify attention deficit hyperactivity disorder (ADHD) in adults according to the American Psychiatric Association’s Diagnostic and Statistical Manual 5 (DSM-5) criteria with a high degree of specificity and sensitivity, according to a recent study published in JAMA Psychiatry.1

The screening tests currently in use are based on diagnostic criteria from DSM-IV12, which was significantly modified to include fewer required symptoms with later onset for the DSM-5 update in 2013, changes that are likely to identify greater numbers of individuals with ADHD.

In 2016, investigators applied the Risk-Calibrated Supersparse Linear Integer Model (RiskSLIM) to a pooled database of responses from 2 population surveys using the World Health Organization’s 29-question Adult ADHD Self-Reporting Scale (ASRS)3 to create an updated scale to match DSM-5 diagnostic criteria. The RiskSLIM machine-learning algorithm identified 6 key questions relative to the DSM5 criteria for use in a new screening scale for ADHD.3,4

The new ADHD screening scale for DSM-5 criteria was then independently evaluated in a clinical sample of patients seeking evaluation at the New York University (NYU) Langone Medical Center Adult ADHD program, as well as a general population sample of 300 individuals who completed household surveys. The scale was highly accurate in identifying 37% of household respondents and 57.7% of NYU Langone respondents who met DSM-5 criteria in clinical interviews. The confirmation rate of individuals who screened positive was 67.3% in the general population sample and 80% in the NYU Langone cohort, at a threshold of >90% sensitivity, with few false-positives.

The investigators from the department of healthcare policy at Harvard Medical School in Boston, Massachusetts, found the new screening scale to be a highly practical tool for use in primary care as well as psychiatry to identify adults with ADHD. “The scale is short, easily scored, and detects the vast majority of general population cases at a threshold that also has high specificity and PPV [positive predictive value], and could be used as a screening tool in specialty treatment settings,” they concluded.

Psychiatry Advisor contacted corresponding investigator Ronald C. Kessler, PhD to find out how practitioners can obtain access to the new screening tool. “We are working on a website that individuals can go to and self-administer the scale to get feedback on [the] likelihood of meeting criteria,” Dr. Kessler responded. “This site will include the caution that a definitive diagnosis can only be provided by a clinician and that the screening scale is being offered only as an aid to help individuals estimate whether their symptoms are persistent and severe enough to be in the range typically found among individuals who meet [the] criteria.”

In the interim, Dr. Kessler invited clinicians interested in using the scale to contact: [email protected].

Related Articles


  1. Ustun B, Adler LA, Rudin C, et al.  The world health organization adult attention-deficit/hyperactivity disorder self-report screening scale for DSM-5. JAMA Psychiatry 2017;74:520-526. doi:10.1001/jamapsychiatry.2017.0298
  2. Adler LA, Shaw DM, Alperin S. ADHD diagnostic and symptom assessment scales for adults. In: Adler LA, Spencer TJ, Wilens T, eds. Attention-Deficit Hyperactivity Disorder in Adults and Children. New York, NY: Cambridge University Press; 2014:224-232.
  3. Kessler RC, Adler LA, Gruber MJ, et al. Validity of the World Health Organization Adult ADHD Self-Report Scale (ASRS) screener in a representative sample of health plan members. Int J Methods Psychiatr Res 2007;16:52-65.
  4. Kessler RC, Adler L, Ames M, et al. The World Health Organization Adult ADHD Self-Report Scale (ASRS): a short screening scale for use in the general population. Psychol Med 2005;35:245-256.