An interventional study of Algorithmically informed randomization (taking into account phenotypes) and Physical Therapy (PT) and Exercise in Chronic Low-back Pain, sponsored by University of Michigan. Recruiting at 1 site in United States. Open to participants aged 25 Years and older. Per ClinicalTrials.gov, last updated 2026-09-15.
Sponsored by University of Michigan · Not applicable, Interventional, and Health services research
Researchers are exploring how certain personal factors, such as symptoms, health history, and lifestyle, may help predict which treatments will work best for someone.
The purpose of this study is to evaluate how well a study algorithm chooses the best treatments for a patient when considering their unique pain characteristics.
During the treatment stages participants may be placed into the following interventions:
After participants are placed in an initial assignment based on a combination of the use of the phenotype based algorithm and randomization, they have the option of continuing on that treatment, switching to another (to be assigned by another randomization combined with use of the algorithm) or adding a second treatment to the first (to be assigned by another randomization combined with use of the algorithm).
Analysis of results will not be a function of the arms listed here, but on whether those allocations were based on the algorithm assigning them initially to their presumed "most effective" treatment; or to a potentially less effective treatment (2nd, 3rd or 4th, choice). These "ranked phenotypic" assignments are masked from participants and researchers until after the trial is completed.
University of Michigan is the lead sponsor of 1,475 studies on the registry; 196 are open to participants now.
Of its 162 completed or terminated interventional studies of FDA-regulated products, 128 (79%) have results posted.
Counted across the registry records on this site, refreshed daily.
Exclusion Criteria:
Cancer
Device: Algorithmically informed randomization (taking into account phenotypes) · Behavioral: Physical Therapy (PT) and Exercise
Device: Algorithmically informed randomization (taking into account phenotypes) · Behavioral: Physical Therapy (PT) and Exercise · Drug: Duloxetine
Device: Algorithmically informed randomization (taking into account phenotypes) · Behavioral: Physical Therapy (PT) and Exercise
Device: Algorithmically informed randomization (taking into account phenotypes) · Behavioral: Physical Therapy (PT) and Exercise
Device: Algorithmically informed randomization (taking into account phenotypes) · Behavioral: Physical Therapy (PT) and Exercise · Drug: Duloxetine
Device: Algorithmically informed randomization (taking into account phenotypes) · Behavioral: Physical Therapy (PT) and Exercise
Device: Algorithmically informed randomization (taking into account phenotypes) · Behavioral: Physical Therapy (PT) and Exercise
Device: Algorithmically informed randomization (taking into account phenotypes) · Drug: Duloxetine
Device: Algorithmically informed randomization (taking into account phenotypes) · Drug: Duloxetine
Device: Algorithmically informed randomization (taking into account phenotypes) · Behavioral: Cognitive-Behavioral Therapy for Pain (PRISM-CBT) · Drug: Duloxetine
Device: Algorithmically informed randomization (taking into account phenotypes) · Behavioral: Physical Therapy (PT) and Exercise · Drug: Duloxetine
Device: Algorithmically informed randomization (taking into account phenotypes) · Behavioral: Cognitive-Behavioral Therapy for Pain (PRISM-CBT) · Drug: Duloxetine
Device: Algorithmically informed randomization (taking into account phenotypes) · Behavioral: mHealth Acupressure Self-Management: · Drug: Duloxetine
Device: Algorithmically informed randomization (taking into account phenotypes) · Behavioral: Cognitive-Behavioral Therapy for Pain (PRISM-CBT)
Device: Algorithmically informed randomization (taking into account phenotypes) · Behavioral: Physical Therapy (PT) and Exercise · Behavioral: Cognitive-Behavioral Therapy for Pain (PRISM-CBT)
Device: Algorithmically informed randomization (taking into account phenotypes) · Behavioral: Cognitive-Behavioral Therapy for Pain (PRISM-CBT) · Drug: Duloxetine
Device: Algorithmically informed randomization (taking into account phenotypes) · Behavioral: Cognitive-Behavioral Therapy for Pain (PRISM-CBT) · Behavioral: mHealth Acupressure Self-Management:
Device: Algorithmically informed randomization (taking into account phenotypes) · Behavioral: Physical Therapy (PT) and Exercise · Behavioral: Cognitive-Behavioral Therapy for Pain (PRISM-CBT)
Device: Algorithmically informed randomization (taking into account phenotypes) · Behavioral: Cognitive-Behavioral Therapy for Pain (PRISM-CBT) · Drug: Duloxetine
Device: Algorithmically informed randomization (taking into account phenotypes) · Behavioral: Cognitive-Behavioral Therapy for Pain (PRISM-CBT) · Behavioral: mHealth Acupressure Self-Management:
Device: Algorithmically informed randomization (taking into account phenotypes) · Behavioral: mHealth Acupressure Self-Management:
Device: Algorithmically informed randomization (taking into account phenotypes) · Behavioral: mHealth Acupressure Self-Management: · Drug: Duloxetine
Device: Algorithmically informed randomization (taking into account phenotypes) · Behavioral: Cognitive-Behavioral Therapy for Pain (PRISM-CBT) · Behavioral: mHealth Acupressure Self-Management:
Device: Algorithmically informed randomization (taking into account phenotypes) · Behavioral: Physical Therapy (PT) and Exercise · Behavioral: mHealth Acupressure Self-Management:
Device: Algorithmically informed randomization (taking into account phenotypes) · Behavioral: mHealth Acupressure Self-Management: · Drug: Duloxetine
Device: Algorithmically informed randomization (taking into account phenotypes) · Behavioral: Cognitive-Behavioral Therapy for Pain (PRISM-CBT) · Behavioral: mHealth Acupressure Self-Management:
Device: Algorithmically informed randomization (taking into account phenotypes) · Drug: Duloxetine
Device: Algorithmically informed randomization (taking into account phenotypes) · Behavioral: Physical Therapy (PT) and Exercise · Behavioral: mHealth Acupressure Self-Management:
After Phenotypic data is collected from participants, the algorithm will use that data to "rank" the likelihood of success of different treatments for an individual; it will then,randomize participants based on two patterns of assignment. And at visit 3, it will re-randomize those participants who wish to add an additional treatment modality or transfer from one modality to another.
A high-contact intervention (10 in-person sessions) involving individualized programs tailored to participant needs and guided by physical therapy best-practice guidelines. Treatment emphasizes home exercise, progressive low-intensity conditioning, and functional endurance.
A moderate-contact telehealth intervention (8 virtual sessions) integrating standard CBT techniques with positive activity modules to enhance engagement, mood, and self-efficacy. Weekly modules focus on pacing, cognitive reframing, relaxation, gratitude, and acts of kindness.
A low-contact, self-guided intervention delivered via the MeTime mobile application, supported by brief staff instruction. Participants practice daily self-acupressure at ten standardized points for approximately 30 minutes per day, stimulating key acupoints associated with pain modulation.
This is a serotonin-norepinephrine reuptake inhibitor (SNRI) FDA-approved for chronic pain. A low-contact pharmacologic intervention consisting of an 8-week dose escalation of 60 mg duloxetine, followed by taper as indicated. Participants initiate medication at home after a standardized orientation, with remote safety and adherence check-ins.
Change in Pain, Enjoyment and General Activity (PEG) scores
The PEG is a three-item survey measure used to assess pain by asking for ratings of Pain intensity, Enjoyment of life, and General activity on a scale of 0-10 over the past week. The final score is the average of the three ratings, with higher scores indicating greater pain severity or interference.
Time frame: T2 (approximately week 6) - T3 (approximately week 15)
Change in Patient-Reported Outcomes Measurement Information System (PROMIS) Pain Interference scores
Interference from pain is assessed using 6 items covering broad functional domains such as life enjoyment, concentration, daily activities, recreation, tasks, and socializing. The scale uses a recall period of 7 days and a response set ranging from 'Not at all" (1) to "Very much" (5). Total scores are between 4 and 20, with higher scores indicating increased pain interference.
Time frame: T2 (approximately week 6) - T3 (approximately week 15)
Patient Global Impression of Pain (PGIC)
Overall perceived benefit of treatment will be assessed using the Patient Global Impression of Change (PGIC).34 This single-item question asks "Overall, how do you feel since the beginning of this phase of the study", and participants respond on a 1 - 7 Likert scale where 1 = markedly improved, 2 = somewhat improved, 3 = mildly improved, 4 = the same, and 5 - 7 are correspondingly "worsened".
Time frame: T3 (approximately week 15)
Change in ecological momentary assessment (EMA)-derived mean Pain Interference
Real-time 7-day pain severity measure assessed using Qualtrics. In practice, participants initiate EMAs at wake, noon and bed-times. Momentary pain intensity will be assessed with the question: "What is your level of pain right now?" rated on a numerical rating scale from 0 = "no pain" to 10 = "worst pain imaginable."
Time frame: T2 (approximately week 6) - T3 (approximately week 15)
Change in Oswestry Disability Index (ODI) scores
This 10-section scale has good internal consistency, discriminative validity, and sensitivity to change in cLBP. Respondents check the box next to each statement that describes their pain or disability
Time frame: T2 (approximately week 6) - T3 (approximately week 15)
Plan to share: Yes — After the study is completed, the de-identified, archived data may also be transmitted to and stored in a data repository for use by other researchers including those outside of the study as per the cooperative agreement with the study sponsor, National Institute of Arthritis and Musculoskeletal and Skin Diseases (NIAMS).
Supporting information: Study protocol, Sap, Icf, Analytic code
No publications or documents are linked to this record.
Eligibility is decided by the study team. Share this record with your doctor or contact the team directly.
Contact study teamGet an email when the registry record changes — status, dates, results — or when someone posts here.
Sign in to followQuestions and observations about this study, from anyone following it. Not medical advice, and not a channel to the study team — their contact details are on the registry record.
Sign in to join the discussion. Reading takes no account; posting does. You choose a display name, and a pseudonym is the default.
Nothing here yet. If you are running this trial, taking part in it, or weighing whether to, this is the place to say so.
University of Michigan