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), a senior advisor at the Cancer Registry of Norway, 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: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.
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.
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.
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.
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.
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."
References
Feychting M, Schüz J, Toledano MB, Vermeulen R, Auvinen A, Poulsen AH, Deltour I, Smith RB, Heller J, Kromhout H, Huss A, Johansen C, Tettamanti G, Elliott P.
Mobile phone use and brain tumour risk – COSMOS, a prospective cohort
study. Environment International, Volume 185, 2024a, 108552, https://doi.org/10.1016/j.
Feychting M, Schüz J, Toledano MB, Vermeulen R, Auvinen A, Poulsen AH, Deltour I, Smith RB, Heller J, Kromhout H, Huss A, Johansen C, Tettamanti G, Elliott P. Response to the letter to the editor regarding “Mobile phone use and brain tumour risk − COSMOS, a prospective cohort study”. Environment International, Volume 189, 2024b, 108808, https://doi.org/10.1016/j.
Moskowitz JM,
Frank JW, Melnick RL, Hardell L, Belyaev I, Héroux P, Kelley E, Lai H,
Maisch D, Mallery-Blythe E, Philips A. COSMOS. A
methodologically-flawed cohort study of the health effects from exposure
to radiofrequency radiation from mobile phone use. Environment
International, Volume 190, 2024, 108807, https://doi.org/10.1016/j.--
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.
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.
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.
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.
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.
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."
References
Feychting M, Schüz J, Toledano MB, Vermeulen R, Auvinen A, Poulsen AH, Deltour I, Smith RB, Heller J, Kromhout H, Huss A, Johansen C, Tettamanti G, Elliott P.
Mobile phone use and brain tumour risk – COSMOS, a prospective cohort
study. Environment International, Volume 185, 2024a, 108552, https://doi.org/10.1016/j.
Feychting M, Schüz J, Toledano MB, Vermeulen R, Auvinen A, Poulsen AH, Deltour I, Smith RB, Heller J, Kromhout H, Huss A, Johansen C, Tettamanti G, Elliott P. Response to the letter to the editor regarding “Mobile phone use and brain tumour risk − COSMOS, a prospective cohort study”. Environment International, Volume 189, 2024b, 108808, https://doi.org/10.1016/j.
Moskowitz JM,
Frank JW, Melnick RL, Hardell L, Belyaev I, Héroux P, Kelley E, Lai H,
Maisch D, Mallery-Blythe E, Philips A. COSMOS. A
methodologically-flawed cohort study of the health effects from exposure
to radiofrequency radiation from mobile phone use. Environment
International, Volume 190, 2024, 108807, https://doi.org/10.1016/j.
--
June 26, 2024
ICBE-EMF exposes major flaws in COSMOS cell phone brain tumor risk study in journal letter published today
Contacts:
Joel M. Moskowitz, PhD, jmm@berkeley.edu
Ronald Melnick, PhD, ronmelnick@gmail.com
New peer-reviewed letter presents
scientific case for retraction of conclusions
of COSMOS brain tumor risk study.
TUCSON, AZ – June 26, 2024 – The International Commission on the Biological Effects of Electromagnetic Fields (ICBE-EMF) exposed major flaws with the COSMOS study of brain tumor risk from cell phone use in a letter to the editor published today in the journal Environment International, "COSMOS: A methodologically-flawed cohort study of the health effects from exposure to radiofrequency radiation from mobile phone use."
The letter discusses serious problems with a recent COSMOS paper that provided interim results about brain tumor risk from mobile phone use. The letter calls for a retraction of the paper's conclusions and demands that the data set be made available to independent investigators who have no industry ties. Excerpts from the letter appear below.
The response to our letter by the authors of the COSMOS paper failed to adequately address our concerns.
COSMOS (“Cohort Study on Mobile Phone Use and Health”) is a 20-30-year cohort study investigating the possible health effects of long-term use of mobile phones and other wireless technologies. The study enrolled over 290,000 mobile phone users from six European countries (Denmark, Finland, France, Sweden, the Netherlands, and the United Kingdom).
The ICBE-EMF is made up of a multidisciplinary consortium of scientists, doctors and related professionals who are involved with research related to the biological and health effects of electromagnetic frequencies up to and including 300 GHz. The organization makes recommendations that include and go beyond establishing numerical exposure guidelines based on the best peer-reviewed scientific research publications.
Excerpts from the ICBE-EMF letter:
Moskowitz JM, Frank JW, Melnick RL, Hardell L, Belyaev I, Héroux P, Kelley E, Lai H, Maisch D, Mallery-Blythe E, Philips A. COSMOS: A methodologically-flawed cohort study of the health effects from exposure to radiofrequency radiation from mobile phone use. Environ Int. 2024;190;108807, doi: 10.1016/j.envint.2024.108807. Open access paper: https://www.sciencedirect.com/
We write to point out serious methodological problems with the Cohort Study on Mobile Phones and Health (COSMOS) brain tumor risk paper (Feychting et al., 2024). Because of these flaws, the study does not provide reliable estimates of the risks of tumors associated with exposure to mobile phone radio frequency radiation (RFR). This paper which summarizes interim results from this 25-plus year cohort study (Schüz et al., 2011) demonstrates many of the overall study’s shortcomings....
1. Problems with exposure assessment
... Misclassification of RFR exposure was substantial because the amount of exposure from a mobile phone varies by up to four orders of magnitude depending on the cellular network technology and the strength of the signal from the cell tower (Wall et al., 2019). COSMOS did not account for this variability. The study also did not control for other sources of RFR exposure, including cordless phones, personal wireless devices, Wi-Fi routers, and cell towers....
Since almost everyone in this cohort study regularly used mobile phones at baseline (including two-thirds who used mobile phones for 10 or more years) and many were exposed to others sources of RFR (e.g., cordless DECT phones, cell towers, Wi-Fi), there was no unexposed group. That the authors chose to use the bottom 50 % of the mobile phone use distribution as the reference group instead of a more extreme percentile cutoff (e.g., the bottom decile of mobile phone use) does not seem defensible....
2. Problems with outcome assessment
The incidence of brain tumors may be under-reported in the five national cancer registries that this study relied upon to assess outcomes....
3. Latency, type and location of tumors
Most human cancers have long latencies, requiring many years to decades after exposure to carcinogens before clinical presentation and diagnosis (Armenian, 1987, Nadler and Zurbenko, 2022). Accordingly, it is critical in cohort studies like COSMOS to stratify on the total length of time between initiation of any given level of exposure – in this case to RFR – and the date of cancer diagnosis, especially since so many members of the COSMOS cohort already had many years of substantial RFR exposure when recruited....
This interim study by Feychting et al. (2024) does not have a sufficient number of subjects followed for more than a decade after RFR exposure began to rule out elevated risks of these two tumors after the most relevant latent periods for carcinogenesis....
4. Statistical issues
Although the authors acknowledged that “Statistical power was limited for meningioma and acoustic neuroma,” we contend that glioma with only 149 incident cases in this study of 1.836 million person years also had limited statistical power. The confidence intervals for the hazard ratios were large. Moreover, the power analysis in the COSMOS design paper (Table 2, Schüz et al., 2011) assumed an annual incidence rate of 15 per 100,000 for brain tumors, whereas the glioma annual incidence rate in the current study was 8.11 per 100,000. Thus, no analysis of tumor risk in this paper had adequate statistical power.
We question whether the study adequately addressed the heterogeneity among countries....
The Data Availability section of the paper states, “The data that has been used is confidential.” If the authors are using this as the reason not to share their data, then the results cannot be confirmed by independent investigators. Since these data have potentially important policy implications, the data set must be accessible to other researchers....
5. Industry research funding
Funding bias is well-recognized in biomedical research (Bekelman et al., 2003). Industry-funded studies were less likely to report statistically significant health-related effects associated with mobile phone use than non-industry funded studies (Huss et al., 2007, Moskowitz et al., 2020). For example, a review of experimental studies concluded, “industry-sponsored studies were least likely to report results suggesting effects… The source of funding and conflicts of interest are important to consider in this area of research (van Nierop et al., 2010).
COSMOS was partially funded by the telecommunications industry in three countries, Finland, Sweden, and the United Kingdom (Feychting et al., 2024)....
1. Problems with exposure assessment
... Misclassification of RFR exposure was substantial because the amount of exposure from a mobile phone varies by up to four orders of magnitude depending on the cellular network technology and the strength of the signal from the cell tower (Wall et al., 2019). COSMOS did not account for this variability. The study also did not control for other sources of RFR exposure, including cordless phones, personal wireless devices, Wi-Fi routers, and cell towers....
Since almost everyone in this cohort study regularly used mobile phones at baseline (including two-thirds who used mobile phones for 10 or more years) and many were exposed to others sources of RFR (e.g., cordless DECT phones, cell towers, Wi-Fi), there was no unexposed group. That the authors chose to use the bottom 50 % of the mobile phone use distribution as the reference group instead of a more extreme percentile cutoff (e.g., the bottom decile of mobile phone use) does not seem defensible....
2. Problems with outcome assessment
The incidence of brain tumors may be under-reported in the five national cancer registries that this study relied upon to assess outcomes....
3. Latency, type and location of tumors
Most human cancers have long latencies, requiring many years to decades after exposure to carcinogens before clinical presentation and diagnosis (Armenian, 1987, Nadler and Zurbenko, 2022). Accordingly, it is critical in cohort studies like COSMOS to stratify on the total length of time between initiation of any given level of exposure – in this case to RFR – and the date of cancer diagnosis, especially since so many members of the COSMOS cohort already had many years of substantial RFR exposure when recruited....
This interim study by Feychting et al. (2024) does not have a sufficient number of subjects followed for more than a decade after RFR exposure began to rule out elevated risks of these two tumors after the most relevant latent periods for carcinogenesis....
4. Statistical issues
Although the authors acknowledged that “Statistical power was limited for meningioma and acoustic neuroma,” we contend that glioma with only 149 incident cases in this study of 1.836 million person years also had limited statistical power. The confidence intervals for the hazard ratios were large. Moreover, the power analysis in the COSMOS design paper (Table 2, Schüz et al., 2011) assumed an annual incidence rate of 15 per 100,000 for brain tumors, whereas the glioma annual incidence rate in the current study was 8.11 per 100,000. Thus, no analysis of tumor risk in this paper had adequate statistical power.
We question whether the study adequately addressed the heterogeneity among countries....
The Data Availability section of the paper states, “The data that has been used is confidential.” If the authors are using this as the reason not to share their data, then the results cannot be confirmed by independent investigators. Since these data have potentially important policy implications, the data set must be accessible to other researchers....
5. Industry research funding
Funding bias is well-recognized in biomedical research (Bekelman et al., 2003). Industry-funded studies were less likely to report statistically significant health-related effects associated with mobile phone use than non-industry funded studies (Huss et al., 2007, Moskowitz et al., 2020). For example, a review of experimental studies concluded, “industry-sponsored studies were least likely to report results suggesting effects… The source of funding and conflicts of interest are important to consider in this area of research (van Nierop et al., 2010).
COSMOS was partially funded by the telecommunications industry in three countries, Finland, Sweden, and the United Kingdom (Feychting et al., 2024)....
6. Conclusions
Given the serious methodologic problems with this interim COSMOS paper discussed above, we recommend that the authors retract their conclusion: “Our findings to date, together with other available scientific evidence, suggest that mobile phone use is not associated with increased risk of developing these tumours.”.
To support this assertion the authors relied on evidence from three cohort studies (Feychting et al., 2024, Schüz et al., 2006, Schüz, 2022) with weak methodology (Ahlbom et al., 2007, Birnbaum et al., 2022, Moskowitz, 2022, Söderqvist et al., 2012). For example, IARC concluded, “reliance on subscription to a mobile phone provider, as a surrogate for mobile phone use, could have resulted in considerable misclassification in exposure assessment” (Baan et al., 2011). Schüz et al. (2022) did not provide data on cumulative phone use. To support their “no association” conclusion, the COSMOS authors also cited time-trend studies; yet, these studies reported significant increases in brain tumor incidence in age-specific subgroups (e.g., de Vocht, 2021, Deltour et al., 2022, Elwood et al., 2022: Ostrom et al., 2022). Finally, the COSMOS authors cited a review of case-control studies that dismissed the results of the cumulative call time analysis by relegating it to the appendix (i.e., Supplemental Figure 2, Röösli et al., 2019).
In contrast to Röösli et al., 2019, Choi et al., 2020 systematic review and meta-analysis of 46 case-control studies”found significant evidence linking cellular phone use to increased tumor risk, especially among cell phone users with cumulative cell phone use of 1000 or more hours in their lifetime,” and called for high quality, prospective cohort studies to confirm the results of the case-control research.
Given the serious methodologic problems with this interim COSMOS paper discussed above, we recommend that the authors retract their conclusion: “Our findings to date, together with other available scientific evidence, suggest that mobile phone use is not associated with increased risk of developing these tumours.”.
To support this assertion the authors relied on evidence from three cohort studies (Feychting et al., 2024, Schüz et al., 2006, Schüz, 2022) with weak methodology (Ahlbom et al., 2007, Birnbaum et al., 2022, Moskowitz, 2022, Söderqvist et al., 2012). For example, IARC concluded, “reliance on subscription to a mobile phone provider, as a surrogate for mobile phone use, could have resulted in considerable misclassification in exposure assessment” (Baan et al., 2011). Schüz et al. (2022) did not provide data on cumulative phone use. To support their “no association” conclusion, the COSMOS authors also cited time-trend studies; yet, these studies reported significant increases in brain tumor incidence in age-specific subgroups (e.g., de Vocht, 2021, Deltour et al., 2022, Elwood et al., 2022: Ostrom et al., 2022). Finally, the COSMOS authors cited a review of case-control studies that dismissed the results of the cumulative call time analysis by relegating it to the appendix (i.e., Supplemental Figure 2, Röösli et al., 2019).
In contrast to Röösli et al., 2019, Choi et al., 2020 systematic review and meta-analysis of 46 case-control studies”found significant evidence linking cellular phone use to increased tumor risk, especially among cell phone users with cumulative cell phone use of 1000 or more hours in their lifetime,” and called for high quality, prospective cohort studies to confirm the results of the case-control research.
The COSMOS paper on brain tumor risk:
Feychting M, Schüz J, Toledano MB, Vermeulen R, Auvinen A, Poulsen AH, Deltour I, Smith RB, Heller J, Kromhout H, Huss A, Johansen C, Tettamanti G, Elliott P. Mobile phone use and brain tumour risk – COSMOS, a prospective cohort study. Environ Int. 2024;185; 108552, doi: org/10.1016/j.envint.2024.
Abstract
Background Each new generation of mobile phone technology has triggered discussions about potential carcinogenicity from exposure to radiofrequency electromagnetic fields (RF-EMF). Available evidence has been insufficient to conclude about long-term and heavy mobile phone use, limited by differential recall and selection bias, or crude exposure assessment. The Cohort Study on Mobile Phones and Health (COSMOS) was specifically designed to overcome these shortcomings.
Methods We recruited participants in Denmark, Finland, the Netherlands, Sweden, and the UK 2007–2012. The baseline questionnaire assessed lifetime history of mobile phone use. Participants were followed through population-based cancer registers to identify glioma, meningioma, and acoustic neuroma cases during follow-up. Non-differential exposure misclassification was reduced by adjusting estimates of mobile phone call-time through regression calibration methods based on self-reported data and objective operator-recorded information at baseline. Hazard ratios (HR) and 95% confidence intervals (CI) for glioma, meningioma, and acoustic neuroma in relation to lifetime history of mobile phone use were estimated with Cox regression models with attained age as the underlying time-scale, adjusted for country, sex, educational level, and marital status.
Results 264,574 participants accrued 1,836,479 person-years. During a median follow-up of 7.12 years, 149 glioma, 89 meningioma, and 29 incident cases of acoustic neuroma were diagnosed. The adjusted HR per 100 regression-calibrated cumulative hours of mobile phone call-time was 1.00 (95 % CI 0.98–1.02) for glioma, 1.01 (95 % CI 0.96–1.06) for meningioma, and 1.02 (95 % CI 0.99–1.06) for acoustic neuroma. For glioma, the HR for ≥ 1908 regression-calibrated cumulative hours (90th percentile cut-point) was 1.07 (95 % CI 0.62–1.86). Over 15 years of mobile phone use was not associated with an increased tumour risk; for glioma the HR was 0.97 (95 % CI 0.62–1.52).
Conclusions Our findings suggest that the cumulative amount of mobile phone use is not associated with the risk of developing glioma, meningioma, or acoustic neuroma.
References (in chronological order; all papers are open access)
Feychting M, Schüz J, Toledano MB, Vermeulen R, Auvinen A, Poulsen AH, Deltour I, Smith RB, Heller J, Kromhout H, Huss A, Johansen C, Tettamanti G, Elliott P. Mobile phone use and brain tumour risk – COSMOS, a prospective cohort study. Environ Int. 2024;185; 108552, doi: org/10.1016/j.envint.2024.
Kundi M. Letter to the editor. Environ Int. 2024 May;187:108665. doi: 10.1016/j.envint.2024.108665.
Feychting M, Schüz J, Toledano MB, Vermeulen R, Auvinen A, Poulsen AH, Deltour I, Smith RB, Heller J, Kromhout H, Huss A, Johansen C, Tettamanti G, Elliott P. Response to the Letter to the Editor regarding "Mobile phone use and brain tumour risk - COSMOS, a prospective cohort study". Environ Int. 2024 May;187:108664. doi: 10.1016/j.envint.2024.108664.
Moskowitz JM, Frank JW, Melnick RL, Hardell L, Belyaev I, Héroux P, Kelley E, Lai H, Maisch D, Mallery-Blythe E, Philips A. COSMOS: A methodologically-flawed cohort study of the health effects from exposure to radiofrequency radiation from mobile phone use. Environ Int. 2024;190;108807, doi: 10.1016/j.envint.2024.108807.
Feychting M, Schüz J, Toledano MB, Vermeulen R, Auvinen A, Poulsen AH, Deltour I, Smith RB, Heller J, Kromhout H, Huss A, Johansen C, Tettamanti G, Elliott P. Response to the letter to the editor regarding “Mobile phone use and brain tumour risk − COSMOS, a prospective cohort study”. Environ Int. 2024;189;108808, doi: 10.1016/j.envint.2024.108808. https://www.sciencedirect.com/
