July 1, 2024

The authors of COSMOS mobile phone-brain tumor study (Feychting et al., 2024a) failed to address numerous issues in their response (Feychting et al., 2024b) to the ICBE-EMF letter (Moskowitz et al., 2024) critiquing their study.

ICBE-EMF stands by its call for a retraction of the study’s conclusions and demands that the data set be made available to independent investigators who have no industry ties.

Mads Rohde (MR), an advisor to the Norwegian cancer registry, input the text from the ICBE-EMF letter into ChatGPT followed by the response to the letter. Then MR submitted the following queries to ChatGPT:

MR: so u see the first was a critique and the next was a reply?

ChatGPT: “Yes, I see that the first document was a critique of the COSMOS study on mobile phone use and brain tumor risk, pointing out several methodological flaws and issues with exposure and outcome assessment, latency periods, statistical power, and potential funding bias. The second document was a reply from the authors of the COSMOS study, addressing the criticisms, defending their methodology, explaining their exposure assessment and outcome ascertainment, and emphasizing the independence and rigor of their research process.”

MR: ok, tell me what the response did not adequately address (which limitations that still apply even if we take their reply for being true)

ChatGPT: “Here are the limitations that the response from the COSMOS study authors did not adequately address, even if we take their reply at face value:

1. Exposure Assessment Limitations:
   • Lack of Updated Exposure Information: The reply acknowledges that the study did not update exposure information during the follow-up period (median 7.12 years), which is crucial as mobile phone technology and usage patterns evolved significantly during this time.
   • Variability in RF-EMF Exposure: The reply did not adequately address the substantial variability in RF-EMF exposure due to different cellular technologies and signal strengths. While they mention that newer technologies emit lower levels of RF-EMF, the exposure from earlier technologies was not comprehensively accounted for.
2. Confounding Factors and Other RF-EMF Sources:
   • Other RF-EMF Sources: The response did not fully address the critique that the study did not control for other sources of RF-EMF exposure such as cordless phones, Wi-Fi routers, and cell towers.
   • Unexposed Group: The lack of a completely unexposed group remains a limitation. The authors argue that non-users would be an unsuitable comparison group due to confounding factors, but this does not mitigate the critique that without an unexposed group, the ability to detect risk differences is compromised.
3. Outcome Assessment Issues:
   • Under-Reporting of Brain Tumors: While the authors refuted the claim of under-reporting based on administrative changes, the potential under-reporting in cancer registries remains a concern, especially for benign tumors like meningioma. The response did not convincingly dismiss the possibility of under-reporting affecting the study’s results.
4. Statistical Power:
   • Insufficient Number of Cases: The response acknowledges limited statistical power, especially for acoustic neuroma and meningioma. Despite their defense, the critique that the study had fewer cases than expected and thus limited power to detect significant associations stands valid.
5. Latency Periods:
   • Insufficient Long-Term Data: The response did not adequately address the critique about insufficient long-term follow-up data. For cancers with long latency periods, the study’s follow-up duration may not be sufficient to detect potential risks associated with long-term mobile phone use.
6. Funding and Potential Bias:
   • Industry Funding Influence: The reply defends the independence of the study despite industry funding. However, the critique about potential funding bias due to partial industry funding and its influence on research outcomes remains a point of concern that was not fully mitigated by the authors’ response.

In summary, while the COSMOS study authors addressed many points raised in the critique, significant limitations regarding exposure assessment, confounding factors, outcome assessment, statistical power, latency periods, and potential funding bias still apply and were not completely resolved by their reply.”