Showing posts with label ChatGPT. Show all posts
Showing posts with label ChatGPT. Show all posts

Monday, June 30, 2025

ChatGPT, the shoulder arthritis blog, and me

Many of us are curious about the utility of ChatGPT. I decided to put it to the test. I was recently asked if there was a way to summarize the 3000 posts on the Shoulder Arthritis Blog. I wondered whether ChatGPT could help.  Below is our conversation word for word. The whole conversation took less than 60 seconds.

Me: I have over 3000 posts on http://shoulderarthritis.blogspot.com can you help me summarize them by key word

ChatGPT: Here are some high-level key themes (keywords/topics) that emerge when reviewing your Shoulder Arthritis blog (with over 3,000 posts!):

ðŸĶī Common Keywords / Topics

  1. Reverse Total Shoulder Arthroplasty (rTSA)
  2. Ream-and-Run Procedure
  3. Rotator Cuff Pathology & Repair
  4. Periprosthetic Joint Infections (PJI)
  5. Glenoid Component Types
  6. Long-Term Follow-up Challenges
  7. Rehabilitation & Exercise Post-Arthroplasty
  8. Patient-Centered Perspectives
  9. Risk Factors in Shoulder Surgery
  10. FDA & Implant Safety

Proposed Workflow for Summarization

Given the blog’s volume, here’s a scalable approach:

  1. Content Harvesting
    • Export all blog post titles, dates, labels (tags), and preferably the full text (via Blogger API or web scraping) into a structured dataset.
  2. Text Processing
    • Tokenization and keyword extraction (e.g., TF-IDF, RAKE).
    • Topic modeling (LDA or BERTopic) to cluster posts into these themes.
  3. Quantitative Analysis
    • Count posts per topic over time (trend analysis).
    • List most-used keywords and their co-occurrence networks.
  4. Summaries & Visualization
    • Generate concise summaries for each theme (e.g., top-5 posts, key clinical recommendations).
    • Visualize trends with charts (volume by year, topic distribution).
  5. User Presentation
    • Provide an executive summary, keyword cloud, topic-trend graphs, and a way to drill down into specific themes/posts.

How I Can Help

I can assist you with:

  • Designing the full pipeline (scraping, NLP, visualization).
  • Writing scripts (in Python, R, etc.) to implement it.
  • Suggesting tools you might use (e.g., Gensim, spaCy, BERTopic).
  • Demonstrating a sample on a subset of posts.
  • Generating summarized output, like an Excel or HTML summary.

Would you like to:

  • Start with extracting titles/metadata?
  • Dive into one theme in detail first (e.g., rTSA outcomes)?
  • Or get a working prototype pipeline?

Let me know your preferred next step and I’ll tailor the workflow accordingly!


Me: rTSA outcomes


ChatGPT: Here’s a focused summary on reverse total shoulder arthroplasty (rTSA) outcomes based on the latest evidence:

📈 Functional Outcomes & Range of Motion

⚠️ Complication & Revision Rates

  • Primary rTSA (≥2 yr follow-up):
  • Mid to long-term (≥5 yr):
  • Longer-term registry data:
    • Scapular notching (grades I–II: 15–59%; III–IV: up to ~47%)
    • Functional stability maintained in most, though some studies report deterioration or increased late revisions (up to 23% in select cohorts) pubmed.ncbi.nlm.nih.gov

🔁 Revision rTSA

🏃 Return to Work & Sport

ðŸ§Đ Key Takeaways

  1. Primary rTSA delivers strong pain relief and functional improvement, with sustained motion gains.
  2. Complication and revision rates are modest short-term (~10% and <3%), increasing modestly over time.
  3. Revisions are challenging, with higher complication risk but meaningful functional benefits.
  4. Most patients resume sport and work, but recovery timelines depend on job/sport demands and psychosocial factors.

🔍 What’s Worth Monitoring

  • High rates of scapular notching—does it influence long-term glenoid stability or implant survival?
  • Long-term (>10 years) outcomes in larger registries as current data is limited.
  • Predictors of successful return to activity beyond ROM—considering psychological and occupational factors.


I hope you found this response interesting.


Keeping and eye on opportunity

 

Osprey 

Union Bay Natural Area

Seattle

June 2025


You can support cutting edge shoulder research that is leading to better care for patients with shoulder problems, click on this link

Follow on twitter/X: https://x.com/RickMatsen
Follow on facebook: https://www.facebook.com/shoulder.arthritis
Follow on LinkedIn: https://www.linkedin.com/in/rick-matsen-88b1a8133/

Here are some videos that are of shoulder interest
Shoulder arthritis - what you need to know (see this link).
How to x-ray the shoulder (see this link).
The ream and run procedure (see this link).
The total shoulder arthroplasty (see this link).
The cuff tear arthropathy arthroplasty (see this link).
The reverse total shoulder arthroplasty (see this link).
The smooth and move procedure for irreparable rotator cuff tears (see this link)
Shoulder rehabilitation exercises (see this link).





Posted by at
Labels: ,

Sunday, June 8, 2025

The Perils of Propensity Matching (post revised with the assistance of ChatGPT)

In a prior post, I discussed an article titled "Medicaid status is independently predictive of increased complications, readmission, and mortality following primary total shoulder arthroplasty." The authors claimed to show that Medicaid status was an independent predictor of adverse outcomes using a national administrative claims database. To interrogate that conclusion, I submitted the article and my blog comments to ChatGPT and asked for a refined critique. Here’s what we arrived at:

Is Medicaid Really the Risk? Are we asking the right question?

Recent work using national databases has reported that patients insured by Medicaid are at increased risk for complications, readmission, and mortality following elective total shoulder arthroplasty (TSA). These findings have led to the conclusion that "Medicaid status is independently predictive" of adverse outcomes. But is Medicaid status truly the cause of poorer outcomes, or is it a proxy for other, more fundamental patient characteristics and circumstances?

Let’s start with a thought experiment: Imagine a 63-year-old widow living alone with diabetes, osteoporosis, and shoulder arthritis. She qualifies for Medicaid due to low income and limited assets. Her shoulder arthroplasty is scheduled in two months. Now imagine she marries a childhood friend who provides her with different health insurance. Her comorbidities, living situation, and health literacy remain unchanged. Should we expect her surgical risk to suddenly drop?

Of course not. The administrative label of her insurer has changed, but her biological and social risk factors have not. Yet the implication of the aforementioned study is that the change in payer alone would significantly reduce her odds of a complication. This framing fails what I would call the "sniff test."

Propensity Matching Pitfalls

The study used propensity score matching (PSM) to compare outcomes between patients on Medicaid and those not on Medicaid. However, matching included only age, sex, and discharge weight. Critically, key confounders such as comorbidity burden (Charlson Comorbidity Index) were excluded from the matching algorithm. The groups remained imbalanced across multiple preoperative risk factors: congestive heart failure, chronic lung disease, anemia, renal failure, substance use, and more. These are not minor oversights—they are core determinants of perioperative risk.

More broadly, Medicaid enrollment is intertwined with social determinants of health: poverty, underemployment, poor nutrition, limited access to preventive care, and systemic racism. These powerful drivers of outcome often go unmeasured in administrative data. To ignore them is to risk mistaking correlation for causation.

This misattribution reflects a well-known cognitive bias: the fundamental attribution error. As Daniel Kahneman explains in Thinking, Fast and Slow, we often over-attribute outcomes to individual traits while neglecting situational forces. Medicaid status is being treated as a standalone risk factor, rather than a marker of cumulative disadvantage.

The authors did apply multivariate regression after matching, but residual differences in baseline health status suggest significant causes of confounding were unaddressed. The assertion that "Medicaid status was independently predictive" risks directing attention toward an insurance label—a variable that is neither biologically meaningful nor directly actionable for most patients—instead of toward modifiable drivers of inequity.

Instead, we should ask: Do patients insured by Medicaid fare worse after adjusting for what we can measure? If so, it tells us that we have incompletely identified the barriers these patients face in accessing and benefitting from coordinated, high-quality care.

Clinically speaking, we do not treat Medicaid status. We treat people. Let us not confuse an administrative variable with the medical and social factors that determine the outcome of treatment.

Revised Abstract (from ChatGPT)

Background: Prior studies report worse surgical outcomes in Medicaid-insured patients, but the extent to which these reflect insurance status versus underlying comorbidity and social disadvantage remains unclear. This study assessed the association between Medicaid insurance and short-term adverse outcomes after elective total shoulder arthroplasty (TSA) using a national administrative database.

Methods: We conducted a retrospective cohort study using the Nationwide Readmissions Database (NRD) from 2016 to 2020. Patients undergoing elective primary TSA were identified by ICD-10-PCS codes. Medicaid patients were matched 1:1 to non-Medicaid patients on age, sex, and discharge weight using nearest-neighbor propensity score matching. Covariate balance was assessed descriptively but not using standardized mean differences. Logistic regression adjusted for residual covariates including the Charlson-Deyo Comorbidity Index (CCI), select diagnoses, and geographic factors. Outcomes included 180-day complications, readmissions, mortality, and other surgical and medical complications.

Results: 15,448 patients on Medicaid and 15,374 patients not on Medicaid were analyzed. Patients on Medicaid had higher CCI scores, greater comorbidity burden, and lower income. Adjusted analyses showed increased odds of any complication (OR 1.2), readmission (OR 1.2), and mortality (OR 1.4) in the Medicaid group. Significant associations also emerged for dislocation, pneumonia, sepsis, and other events.

Conclusion: Medicaid insurance was associated with increased adverse outcomes after TSA, even after adjustment for the variables that were identified. These differences must be due to social and clinical risks that were not identified in this study. Medicaid should be viewed not as an intrinsic risk factor, but as a proxy for structural disadvantage. Policy and care improvements must focus on optimizing comorbidity management, care access, and coordination for all patients, independent of insurance status, i.e. patients on other insurance programs are subject to the same risk factors as those covered by Medicaid. We should focus on identifying and managing these social, economic and medical risk factors rather than the type of insurance.

I'd like to illuminate this last point with a chart from the paper


When looking at this chart our eyes are drawn to the two right hand columns. However, if we look at the second and third columns we see that very similar complications and rates of complications occur both in patients not covered by Medicaid (Control) and those that are (Medicaid). Non-Medicaid insurance is not protective against complications any more than Medicaid insurance causes complications.
 


Simple Guidelines for Propensity Score Matching (PSM)

  1. Define the Exposure Clearly

    • Must be binary (e.g., Medicaid vs. non-Medicaid insurance).

    • Clearly identify the treated and comparison groups.

  2. Choose Confounders Thoughtfully

    • Include only variables measured before treatment.

    • Choose variables that affect both treatment and outcomes.

    • Avoid variables on the causal pathway (e.g., complications).

  3. Estimate the Propensity Score

    • Use logistic regression.

    • Include relevant confounders.

  4. Match Patients

    • Use 1:1 nearest neighbor with a caliper (e.g., 0.2 × SD of logit).

    • Prefer matching without replacement.

    • Exclude unmatched cases.

  5. Check Balance

    • Use standardized mean differences (SMD < 0.1 ideal).

    • Visualize using Love plots.



  6. Analyze Outcomes Appropriately

    • Use matched methods (e.g., conditional logistic regression).

    • Don’t assume matched pairs are independent.

  7. Report Transparently

    • Describe covariates used.

    • State matching method and caliper.

    • Report group sizes pre/post-matching.

    • Show covariate balance.

    • Detail outcome analysis.

A Fun Illustration: Osprey vs. Bald Eagle



If we were to use PSM to compare the hunting success of an osprey and a bald eagle:

  • Outcome: Hunting success rate = successful captures / attempts

  • Exposure: Species (osprey vs. eagle)

  • Confounders to Match:

    • Habitat (river, lake, ocean)

    • Wind/weather

    • Time of day/season

    • Prey density

    • Flight altitude

    • Visibility conditions

Not Confounders:

  • Bird color

  • Vocalization

  • Rarity or popularity

  • Endangered status

As with surgery, outcomes depend not just on species — or insurance — but on context, environment, and opportunity.

Let us not confuse administrative categories for biological truths. Statistical adjustment is no substitute for structural insight.



You can support cutting edge shoulder research that is leading to better care for patients with shoulder problems, click on this link

Follow on twitter/X: https://x.com/RickMatsen
Follow on facebook: https://www.facebook.com/shoulder.arthritis
Follow on LinkedIn: https://www.linkedin.com/in/rick-matsen-88b1a8133/

Here are some videos that are of shoulder interest
Shoulder arthritis - what you need to know (see this link).
How to x-ray the shoulder (see this link).
The ream and run procedure (see this link).
The total shoulder arthroplasty (see this link).
The cuff tear arthropathy arthroplasty (see this link).
The reverse total shoulder arthroplasty (see this link).
The smooth and move procedure for irreparable rotator cuff tears (see this link)
Shoulder rehabilitation exercises (see this link).


Posted by at
Labels: ,

Friday, June 16, 2023

How long does it take to recover after shoulder joint replacement?

"How long will it take my shoulder to recover after joint replacement?" This important topic has been explored by the authors of Speed of recovery after shoulder arthroplasty: a comparison of reverse and anatomic total shoulder arthroplasty. They found that anatomic total shoulder (TSA) patients reached a consistent plateau for pain and function by 6 months and for shoulder elevation by 1 year. Reverse total shoulder (RSA) patients demonstrated variability with multiple false plateau points. By 6 months, TSA patients had achieved 90% to 100% of functional improvement, whereas RSA patients reached 72% to 91%. The effectiveness of TSA was greater than that of RSA for all measures with the exception of elevation and abduction.






A recent post considered the questions patients most frequently asked about shoulder arthroplasty:  Information that patients want to know about shoulder joint replacement arthroplasty for arthritis. One of the commonly asked questions was about recovery: How long does it take to recover from a shoulder joint replacement? When this question was posed to ChatGPT, the response was "Full recovery (6-12 months): While the majority of recovery is typically achieved within the first six months, it can take up to a year or longer to fully regain strength, range of motion, and function."

The authors of recent article sought to answer this question in their practice: Rate of improvement in shoulder strength after anatomic and reverse total shoulder arthroplasty, a study of 374 shoulders having primary anatomic TSA (aTSA) and 601 shoulders having primary reverse TSA (rTSA).

A handheld dynamometer was used to assess 
(1) external rotator (ER) strength  with the involved shoulder in 0  degrees of external rotation, 0 degrees of abduction, and the elbow in 90 degrees offlexion and
(2) forward elevation (FE) strength with the involved shoulder in the scapular plane at 30 degrees of flexion and 30 degrees of abduction.

 aTSA patients had the greatest gains in strength in the first year postoperatively. Strength increased the most between 3 and 6 months. At two year followup patients having aTSA had a 32% improvement in ER and 38% improvement in FE. 

       



rTSA patients also had the greatest gains in strength in the first year postoperatively. ER strength improved the most between 6 months and 1 year; FE strength increased the most between baseline and 3 months. At two year followup patients  patients having rTSA had a 51% improvement in ER and 90% improvement in FE.  


                               


These data on the recovery of strength are consistent with the recovery in measures of comfort and function as reported by the authors of Rate of Improvement in Clinical Outcomes with Anatomic and Reverse Total Shoulder Arthroplasty who studied 505 anatomic total shoulders and 678 reverse total shoulder arthroplasty.

Full improvement was typically achieved by 24 months, although the majority of improvement was achieved in the first 6 months.






Comment: These two studies help answer patients' questions about the typical recovery of strength, comfort and function after shoulder arthroplasty, It is worth emphasizing that 
(1) shoulder arthroplasty (aTSA or rTSA) is most commonly performed on shoulders that have been disabled for years during which time the joint typically becomes weak and stiff - limitations that can only be overcome by a gentle, persistent postoperative rehabilitation program extending for months after surgery
(2) post-arthroplasty recovery is variable among patients because of differences in diagnoses, procedures, co-morbidities, resilience and effort, so "average" recovery may not pertain to each individual patient.
(3) it is useful for surgeons to monitor recovery for the first year after surgery using a convenient patient reported outcome measure to be sure that the patient is on track and, if not, to investigate the possible reasons why not.
(4) early identification of patients who are "off track" may indicate the need for interventions to optimize the opportunity for a good longer term outcome as emphasized in Which patients have poorer early results from total shoulder arthroplasty and how do these patients fare at two years after surgery?

You can support cutting edge shoulder research that is leading to better care for patients with shoulder problems, click on this link.

Follow on twitter: https://twitter.com/shoulderarth
Follow on facebook: click on this link
Follow on facebook: https://www.facebook.com/frederick.matsen
Follow on LinkedIn: https://www.linkedin.com/in/rick-matsen-88b1a8133/

Here are some videos that are of shoulder interest
Shoulder arthritis - what you need to know (see this link).
How to x-ray the shoulder (see this link).
The ream and run procedure (see this link).
The total shoulder arthroplasty (see this link).
The cuff tear arthropathy arthroplasty (see this link).
The reverse total shoulder arthroplasty (see this link).
The smooth and move procedure for irreparable rotator cuff tears (see this link).
Shoulder rehabilitation exercises (see this link).
Posted by at
Labels: , , , ,
Subscribe to: Posts (Atom)