Observed LAeq,10-min values ranged from 20.00 to 88.58 dB(A), with a mean of 48.88 ± 13.36 dB(A) and a median of 47.98 dB(A). Of all observations, 43.10% were below 45 dB(A), while 33.24% were at or above 55 dB(A). Comparisons among predefined time windows did not show statistically significant differences (p = 0.169). These results describe measurements collected during the specified short monitoring period rather than annual conditions.

The study’s measurement-driven workflow combined inverse-distance-weighted interpolation, leave-one-out cross-validation, descriptive comparisons, study-defined screening bands contextualized with reference to World Health Organization environmental-noise guidance, and false-discovery-rate-corrected Getis–Ord Gi* analysis. For the selected IDW configuration, with p = 2 and k = 12, cross-validation showed minimal average bias but only moderate point-level predictive performance: RMSE was 11.79 dB(A), MAE was 8.55 dB(A), mean error was −0.08 dB(A), and r was 0.52. The Gi* analysis identified 100 cold-spot and 57 hot-spot locations among 276 coordinate-unique site means, conditional on the specified spatial-weighting configuration.

As summarized in the article abstract, the findings provide a sample-supported empirical framework for identifying relative spatial patterns and follow-up monitoring priorities at the studied campus. The authors caution that the results represent short-term outdoor conditions and should not be interpreted as annual exposure, formal WHO compliance, indoor exposure, or high-precision prediction. The study is therefore a campus noise-screening investigation based on field observations and spatial modeling, not a review, protocol, simulation, or animal or cell study.

Subject of Research: Short-term outdoor campus noise screening and GIS spatial analysis at Batman University

Article Title: Measurement-driven GIS mapping of short-term outdoor campus noise at Batman University, Türkiye: A WHO-informed screening approach

Article References: Durmus, B. (2026). Measurement-driven GIS mapping of short-term outdoor campus noise at Batman University, Türkiye: A WHO-informed screening approach. Environmental Monitoring and Assessment, 198(9), Article 1000. https://doi.org/10.1007/s10661-026-15835-8

Image Credits: AI Generated

DOI: 10.1007/s10661-026-15835-8

Keywords: Batman University, campus noise, environmental noise, GIS mapping, acoustic measurements, LAeq, spatial hotspots, WHO guidance, Measurement-driven, mapping, short-term, outdoor

The technical case for AI in Bangladeshi medical imaging is compelling. Deep learning algorithms now achieve diagnostic performance comparable to expert clinicians in image-based tasks such as tumor detection, anomaly identification, and disease classification. Automated image segmentation and diagnostic prediction can compress reporting times that currently stretch for days in under-resourced facilities. For a country where the healthcare system faces pronounced urban–rural disparities, infrastructural constraints, and a thin supply of specialists, the technology offers a genuine opportunity to extend expert-level diagnostics to populations that have historically gone without. The World Health Organization has recognized this potential, defining AI in health as the use of algorithms and software to approximate human cognition in the analysis and interpretation of complex medical data.

Yet the study insists that this shift is not happening in a regulatory vacuum so much as in a regulatory void. Bangladesh’s principal digital legislation, including the Information and Communication Technology Act 2006 and the Digital Security Act 2018, was drafted for cybersecurity and digital offenses, not for the governance of algorithmic decision-making in clinical settings. The analysis identifies no clear statutory provisions governing how patient data may be used to train AI systems, how liability should be allocated when an algorithm-assisted misdiagnosis causes harm, or how transparency obligations can be enforced when diagnostic outputs emerge from opaque computational models. These are not marginal technicalities; they go to the heart of patient safety and legal recourse.

The ethical stakes are framed through the four classical principles of biomedical ethics: autonomy, beneficence, non-maleficence, and justice. Autonomy is tested when patients cannot know how their data are used or how algorithms contribute to their diagnosis. Beneficence demands that AI genuinely improve care while remaining under human oversight. Non-maleficence requires protection against algorithmic bias, data errors, and misdiagnosis, harms the study notes can be systemic and reproducible across entire populations. Justice requires that the benefits of AI not deepen existing inequalities between urban and rural, public and private healthcare. The authors argue that these principles provide both a moral compass and a practical lens through which Bangladesh’s legal instruments can be critically assessed.

The methodological approach is doctrinal, sometimes called black-letter legal research, involving the systematic identification, interpretation, and evaluation of authoritative sources: statutes, regulations, professional codes, and policy documents. The descriptive dimension maps Bangladesh’s existing legal landscape; the normative dimension asks whether that landscape aligns with international standards. The study draws on primary legal materials, secondary interpretive sources, and ethical frameworks including the WHO’s 2021 Guidance on Ethics and Governance of Artificial Intelligence for Health, the UNESCO Recommendation on the Ethics of Artificial Intelligence adopted by all 193 member states, and the European Union’s AI Act, which classifies medical diagnostic imaging systems as high-risk and imposes stringent obligations on data quality, transparency, human oversight, and post-market monitoring.

Against these benchmarks, Bangladesh’s domestic frameworks fall short in instructive ways. The Bangladesh Medical and Dental Council’s Code of Medical Ethics, while emphasizing physician competence and confidentiality, presupposes direct human decision-making and does not address algorithmic opacity, data-intensive diagnostics, or the allocation of responsibility in AI-assisted errors. The Draft Bangladesh National AI Policy 2026–2030 represents progress, acknowledging transparency, accountability, human oversight, and safeguards against fully autonomous clinical decision-making. But the study finds these provisions remain largely programmatic rather than enforceable: the policy establishes no binding liability regime, no independent oversight body, and no detailed compliance mechanisms for high-risk applications such as medical imaging.

The comparative analysis adds an important caution against simple imitation. The EU’s risk-based model works because it rests on strong institutional infrastructure, including independent supervisory authorities and robust data protection under the GDPR. The United Kingdom’s principle-based approach depends on the integrated structure of the National Health Service, which allows coordinated implementation of AI standards. The United States relies on a market-oriented FDA framework for AI and machine-learning-based Software as a Medical Device, emphasizing pre-market approval and lifecycle monitoring. Each model presupposes institutional capacity, regulatory expertise, and technological maturity that Bangladesh cannot simply import. The authors warn that uncritical transplantation of Global North frameworks risks becoming symbolic rather than functional, and may even reinforce what they describe as techno-colonialism, where standards and technologies are externally imposed without contextual adaptation.

The study’s most distinctive contribution is its insistence on explaining why regulatory gaps persist rather than merely cataloging them. It identifies structural factors: limited regulatory capacity, fragmented legal frameworks, competing political priorities that privilege digital expansion over rights-based governance, and heavy reliance on externally developed technologies trained on datasets from high-income countries. That last point carries direct clinical consequences. Imaging algorithms trained on foreign demographic and epidemiological data may embed systematic biases that produce diagnostic inaccuracies disproportionately affecting vulnerable Bangladeshi populations, particularly where local data infrastructure and dataset representativeness requirements are absent.

Informed consent emerges as a particularly thorny problem. The draft policy’s prohibition on AI independently making life-altering decisions addresses only a narrow slice of autonomy. The deeper difficulty is algorithmic opacity: when clinicians themselves cannot fully explain how diagnostic outputs were generated, meaningful patient consent becomes difficult to uphold. The challenge is compounded in Bangladesh by limited digital literacy and hierarchical physician–patient relationships, conditions under which consent risks degenerating into a procedural formality rather than a substantive safeguard. Similarly, the draft policy’s data protection commitments, including calls for strict safeguards against leakage of sensitive health information, are not backed by a comprehensive, sector-specific data protection regime covering anonymization, secondary use, and cross-border transfers.

The study closes with a reform agenda that links ethical principles to operational governance. It calls for comprehensive health data legislation that codifies patient rights, consent, and transparency; AI-specific ethical guidelines updating professional codes to address algorithmic accountability; a sector-specific regulatory authority to oversee validation, certification, and post-deployment monitoring of clinical AI; clearly defined liability frameworks spanning developers, deployers, and clinicians; and sustained investment in regulatory capacity and AI literacy among healthcare professionals. The authors argue that without this shift from aspirational policy-making to enforceable, institutionally grounded regulation, AI adoption in Bangladesh risks exacerbating existing inequalities rather than curing them. Their message to policymakers is ultimately optimistic but firm: the country can harness AI to transform diagnostic medicine, but only if its legal and ethical infrastructure evolves as fast as the technology it is meant to govern.

Subject of Research: Ethical and legal governance of artificial intelligence in medical imaging and diagnostics in Bangladesh

Article Title: Regulating AI in medical imaging and diagnostics in Bangladesh through ethical and legal doctrinal analysis

Article References: Basu, B. K., Sarker, M. F. R., Akter, R., Amin, M. B., Hassan, M. S., Debnath, G. C., & Sony, M. M. A. A. M. (2026). Regulating AI in medical imaging and diagnostics in Bangladesh through ethical and legal doctrinal analysis. Discover Artificial Intelligence, 6(1), Article 1324. https://doi.org/10.1007/s44163-026-02197-w

Image Credits: AI Generated

DOI: 10.1007/s44163-026-02197-w

Keywords: artificial intelligence, medical imaging, Bangladesh, health law, medical ethics, data protection, informed consent, algorithmic bias, EU AI Act, WHO guidance, regulatory policy, digital health

The review, led by Ornella Gonzato with contributions from patient advocates Denise Reinke and Roger Wilson, oncologist Bernd Kasper and regulatory expert Maria Josefina Ruiz Alvarez, examines how two landmark frameworks can be operationalised in rare cancer research: the 2024 World Health Organization Guidance for best practices for clinical trials and the International Council for Harmonisation’s ICH E6(R3) Good Clinical Practice guideline. The WHO guidance articulates scientific validity, efficiency, ethical acceptability, social value, feasibility, equity and patient engagement as interdependent components of trial quality. ICH E6(R3) complements this by reframing Good Clinical Practice around quality by design and risk-proportionate oversight, emphasising critical-to-quality factors rather than box-ticking procedural compliance. Together, the authors argue, these documents shift trial governance toward principled flexibility.

The central problem is one of proportionality. When patient populations are intrinsically small and biologically fragmented, conventional fixed-sample randomised trials may impose disproportionate burdens on participants while offering only a slim probability of generating actionable knowledge. The WHO guidance explicitly ties ethical acceptability to proportionality between risk, burden and anticipated social value. Adaptive and Bayesian designs can improve efficiency while preserving methodological rigour, and the sarcoma field has become a proving ground for them. The biomarker-driven MULTISARC umbrella trial used centralised molecular profiling to allocate patients across treatment cohorts, showing how molecular stratification can enhance feasibility and interpretability even in highly fragmented populations. IMMUNOSARC employed a multicohort, single-arm design spanning multiple rare subtypes, illustrating how flexible, risk-proportionate approaches can support evidence generation when conventional randomisation is simply impractical.

But methodological innovation alone is not enough. The review emphasises that rare cancer research depends on collaborative infrastructure that often matters as much as the trial design itself. Cross-border networks such as the European Reference Network EURACAN and international sarcoma consortia enable accrual, harmonise standards and safeguard data quality. Multinational trials such as RAIN-3201, an international randomised phase III study, and rEECur, an international multi-arm seamless phase II/III trial in relapsed and refractory Ewing sarcoma, relied on coordinated governance, harmonised data collection and cross-border recruitment to maintain scientific validity while maximising the number of patients enrolled. In populations fragmented across dozens of subtypes, such infrastructures are frequently a prerequisite for adequately powered studies rather than a mere facilitator of research activity.

Equity emerges as a persistent tension throughout the analysis. Centralising expertise improves diagnostic accuracy and outcomes, but it can raise barriers to research participation. Travel burdens, financial costs and logistical complexity fall disproportionately on patients in rural regions, lower socioeconomic groups and older populations. Regulatory heterogeneity compounds the problem: in multinational rare cancer studies, variation in approval timelines, submission requirements and local governance procedures delays site activation and creates unequal opportunities for participation across countries. These asymmetries fall hardest on academic and investigator-initiated studies, which typically lack dedicated regulatory affairs departments. The authors point to ECRIN’s Regulatory and Ethical Database, which catalogues country-specific requirements across more than 750 searchable fields, as a practical tool for navigating this fragmentation, but they stress that differences in ethics committee composition, review timelines and national procedures persist alongside the EU’s Clinical Trials Information System harmonisation.

Decentralised and hybrid trial models offer a partial remedy. Remote informed consent, telemedicine visits, electronic patient-reported outcomes, local clinical assessments, remote monitoring and digital data capture can reduce the burden of participation for geographically dispersed patients, improving recruitment and retention. Registry-based initiatives such as RESAR, a prospective multicentre sarcoma registry, and ICONIC, a registry-based osteosarcoma platform with strong patient involvement, demonstrate how longitudinal real-world data collection can complement interventional studies, support external control arms when randomisation is infeasible and give researchers contextual evidence grounded in patient experience. The authors caution, however, that decentralisation should extend rather than replace specialist centres, and that digital-first approaches require infrastructure, regulatory alignment, data protection safeguards and explicit attention to digital inclusion so that efforts to improve accessibility do not unintentionally exclude under-resourced populations.

Patient-centredness, the review argues, is not merely an ethical nicety but a structural determinant of what the authors call operational validity—the ability of a trial to generate interpretable evidence under the real-world constraints of population size, feasibility and participation. In sarcomas, endpoints such as functional preservation and long-term toxicity may matter more to patients than short-term tumour response. The randomised multicentre surgical trial SarcoSIGHT shows that integrating functional and quality-of-life endpoints early in trial design is feasible while maintaining scientific rigour. Structured involvement of advocacy organisations such as the Sarcoma Patient Advocacy Global Network in protocol development, consent processes and dissemination enhances both feasibility and interpretability in very small populations, and patient-led initiatives like ICONIC demonstrate how engaged communities can shape research agendas and sustain engagement over time.

Digital and artificial intelligence-enabled tools extend this agenda further. Applications under active exploration include AI-assisted patient identification from electronic health records, wearable-based remote monitoring and digital twins as synthetic control alternatives—particularly relevant where randomising patients to a control arm is statistically or ethically constrained in ultra-rare populations. The WHO’s Global Action Plan for Clinical Trial Services calls for adopting such innovative designs and technologies to improve recruitment, data collection, analysis and oversight, while the Global Clinical Trials Forum provides the institutional architecture for aligning digital governance standards across jurisdictions. Yet the authors insist the governance risks demand equal attention: algorithmic bias can reproduce geographic and socioeconomic inequities in participant selection, unequal digital access can exclude vulnerable groups, and opaque AI-assisted decisions in eligibility or safety monitoring require audit trails and human oversight embedded by design.

The cross-cutting lessons are strikingly consistent. Methodological flexibility succeeds when linked to clear biological rationale, not innovation for its own sake. Feasibility and scientific validity are inseparable, because recruitment failure and attrition can render even a methodologically sound trial inconclusive. International collaborative infrastructure is an enabling condition, not a luxury. Patient-centred approaches improve operational performance, not just ethical acceptability. And despite all this progress, regulatory fragmentation remains the stubborn barrier that governance frameworks must address with greater specificity. The WHO Global Action Plan’s sixth action on streamlining regulatory and ethics review will need teeth if equitable, multinational rare cancer trials are to become routine rather than exceptional.

The implications reach well beyond sarcomas. As molecular stratification carves common cancers into progressively smaller and more dispersed subsets, the governance lessons forged in rare cancer research are increasingly relevant to precision oncology at large. The authors identify outstanding questions that will define the next decade: how to translate principles into proportionate governance across diverse regulatory systems, how to combine adaptive designs, registries, real-world data and decentralised models optimally, how to integrate patient involvement into regulatory decision-making, how to deploy digital tools equitably and transparently, and what sustainable funding models can maintain international research infrastructures. The review is candid about its limitations—it is a structured narrative synthesis, examples are illustrative rather than exhaustive, most evidence comes from high-income settings, and direct causal evidence linking patient engagement practices to trial outcomes remains limited. But its core message is clear: in rare cancers, operational validity depends on the interaction of methodological innovation, collaborative infrastructure, patient-centred governance and proportional regulation, and sarcoma research has shown the way.

Subject of Research: Patient-centred clinical trial design and governance for rare cancers, using sarcomas as a model for applying 2024 WHO guidance and ICH E6(R3)

Article Title: Patient-centred and fit-for-purpose clinical trials in rare cancers: lessons from sarcomas for operationalising 2024 WHO Guidance and ICH E6(R3)

Article References: Gonzato, O., Reinke, D., Wilson, R., Kasper, B., & Ruiz Alvarez, M. J. (2026). Patient-centred and fit-for-purpose clinical trials in rare cancers: lessons from sarcomas for operationalising 2024 WHO Guidance and ICH E6(R3). eClinicalMedicine, 100, Article 104192. https://doi.org/10.1016/j.eclinm.2026.104192

Image Credits: AI Generated

DOI: 10.1016/j.eclinm.2026.104192

Keywords: rare cancers, sarcoma, clinical trials, WHO guidance, ICH E6(R3), adaptive trial design, patient engagement, decentralised trials, real-world data, regulatory harmonisation, operational validity, precision oncology