Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
Review
. 2025 Jun 2;5(1):29.
doi: 10.1186/s44158-025-00249-8.

Expert consensus on feasibility and application of automatic pain assessment in routine clinical use

Marco Cascella  1 , Alfonso Maria Ponsiglione  2 , Vittorio Santoriello  2 , Maria Romano  2 , Valentina Cerrone  1 , Dalila Esposito  1 , Mario Montedoro  1 , Roberta Pellecchia  2 , Gennaro Savoia  3 , Giuliano Lo Bianco  4 , Massimo Innamorato  5 , Silvia Natoli  6   7 , Jonathan Montomoli  8 , Federico Semeraro  9 , Elena Giovanna Bignami  10 , Valentina Bellini  10 , Matteo Luigi Giuseppe Leoni  11 , Felice Occhigrossi  12 , Alessandro Vittori  13 , Maria Caterina Pace  14 , Pasquale Buonanno  3 , Mauro Forte  14 , Elisabetta Chinè  15 , Roberta Carpenedo  15 , Alessandro De Cassai  16   17 , Alfonso Papa  18 , Maurizio Marchesini  19 , Gaetano Terranova  20 , Fabrizio Micheli  21 , Laura Demartini  22 , Franco Marinangeli  23 , William Raffaeli  24 , Flaminia Coluzzi  25 , Andrea Tinnirello  26 , Roberto Arcioni  27 , Angelo Marra  28 , Mohammed Naveed Shariff  29 , Federica Monaco  30 , Gabriele Finco  31 , Alessia Bramanti  32 , Ornella Piazza  1
Affiliations
Review

Expert consensus on feasibility and application of automatic pain assessment in routine clinical use

Marco Cascella et al. J Anesth Analg Crit Care. .

Abstract

Background: Pain is often difficult to assess, particularly in non-communicative patients. While artificial intelligence (AI)-based objective Automatic Pain Assessment (APA) systems are a promising solution, their clinical implementation raises essential questions, primarily regarding clinician acceptance.

Methods: We conducted a survey-to-consensus investigation on the feasibility and application of APA for clinical use. Firstly, the steering committee implemented the CHERRIES guidelines and designed a questionnaire for healthcare professionals. Given the survey results, 26 experts in pain medicine were asked to participate in a two-round consensus by rating 10 statements through a 7-point Likert scale. Consensus was defined as ≥ 75% agreement ("agree" or "completely agree"). For both phases, data was collected through online questionnaires and analyzed quantitatively.

Results: For the survey, we collected responses from 628 healthcare professionals. The output highlighted excellent acceptance of the technology and a preference for multidimensional techniques. After two rounds, consensus was achieved on 8 out of 10 statements. Experts agreed on APA utility in supporting healthcare professionals and real-time pain monitoring. A strong consensus (96.2%) supported the need to inform patients about the use and limitations of AI systems. Adequate staff training is mandatory. Moreover, 92.3% agreed on the importance of implementing risk management, data quality control, and AI governance throughout the APA lifecycle. The experts stressed the need for internal and external validation processes and periodic updates, even for research purposes. Consensus was also reached about the importance of involving interdisciplinary stakeholders and addressing regulatory, ethical, and social implications. Multimodal inputs (e.g., physiological signals, facial expressions, speech, and clinical data) in APA systems are recommended. Additionally, APA systems should be capable of grading pain levels (e.g., via NRS), not just detecting the presence of pain. On the other hand, two statements did not reach consensus: the applicability of APA systems for acute and chronic pain conditions and their potential to improve therapeutic strategies.

Conclusion: APA is viewed as a promising and potentially feasible technology for clinical pain assessment, particularly in vulnerable populations. Further research is needed to validate the dedicated tools, define applications in different clinical conditions (e.g., acute and chronic pain), and demonstrate their impact on routine clinical practice for pain management.

Keywords: Artificial intelligence; Automatic pain assessment; Opioid; Pain; Pain medicine; Pain therapy; Pediatric pain.

PubMed Disclaimer

Conflict of interest statement

Declarations. Ethics approval and consent to participate: Not applicable. Consent for publication: Not applicable. Competing interests: Competing interests: FS is the Chair of the European Resuscitation Council, an Emeritus member of the ILCOR BLS Working Group, and a member of the Italian Resuscitation Council Foundation. JM is a co-founder and shareholder of Callisia srl University Spin-off at Università Politecnica delle Marche, developing a smart bracelet collecting patient data intelligently for real-time visualization and data analysis. EGB is the Chair of SIAARTI, the Italian Society of Anesthesia, Analgesia, Resuscitation, and Intensive Care. The other authors declare no competing interests.

Figures

Fig. 1
Fig. 1
Study framework
Fig. 2
Fig. 2
Potential advantages of Automatic Pain Assessment in different settings. Legend: Boxplots from Q1 to Q4 (Q1 “intensive care settings”, Q2 “complications detection”, Q3 “analgesic dosage”, Q4 “inpatients management at night”)
Fig. 3
Fig. 3
Different settings for Automatic Pain Assessment implementation. Legend: Boxplots Likert scale scores from Q1 to Q4 of the questionnaire grouped by gender (A) and age (B) (Q1 “intensive care settings”, Q2 “complications detection”, Q3 “analgesic dosage”, Q4 “inpatients management at night”)
Fig. 4
Fig. 4
Different approaches to Automatic Pain Assessment. Legend: Boxplots Likert scale scores to questions Q5 and Q6 of the questionnaire (Q5 “unimodal approaches”, Q6 “multimodal approaches”)
Fig. 5
Fig. 5
Different modalities for Automatic Pain Assessment implementation. Legend: Boxplots Likert scale scores from Q1 to Q4 of the questionnaire grouped by gender (A) and age (B) (Q5 “unimodal approaches”, Q6 “multimodal approaches”)
Fig. 6
Fig. 6
Different modalities for Automatic Pain Assessment implementation. Legend: Boxplots Likert scale scores from Q5 to Q6 of the questionnaire grouped by healthcare profession (MD, Nurse, Other) (Q5 “unimodal approaches”, Q6 “multimodal approaches”)
Fig. 7
Fig. 7
Propensity to use Automatic Pain Assessment tools in clinical practice. Legend: Bar chart of Likert scale scores to question Q7 grouped by healthcare profession
See this image and copyright information in PMC

References

    1. Cohen SP, Vase L, Hooten WM (2021) Chronic pain: an update on burden, best practices, and new advances. Lancet 397:2082–2097 - DOI - PubMed
    1. Cascella M, Bimonte S, Saettini F, Muzio MR (2019) The challenge of pain assessment in children with cognitive disabilities: features and clinical applicability of different observational tools. J Paediatr Child Health 55:129–135 - DOI - PubMed
    1. Marchetti G, Vittori A, Tortora V, Bishop M, Lofino G, Pardi V et al (2016) Prevalence of pain in the departments of surgery and oncohematology of a paediatric hospital that has joined the project “Towards pain free hospital.” Clin Ter 167:156–160 - PubMed
    1. Marchetti G, Vittori A, Cascella M, Mascilini I, Piga S, Petrucci E et al (2023) Pain prevalence and pain management in children and adolescents in an italian third level pediatric hospital: a cross-sectional study. Ital J Pediatr 49:41 - DOI - PMC - PubMed
    1. Rababa M, Al-Sabbah S, Hayajneh AA (2021) Nurses’ perceived barriers to and facilitators of pain assessment and management in critical care patients: a systematic review. J Pain Res 14:3475–3491 - DOI - PMC - PubMed

LinkOut - more resources