Can artificial intelligence simplify the screening of muscle mass loss?
Background: Sarcopenia is a risk factor for morbidity and preventable mortality in old age, with consequent high costs for the national health system. Its diagnosis requires costly radiological examinations, such as the DEXA, which complicate screening in medical centers with a high prevalence of sa...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-05-01
|
| Series: | Heliyon |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2405844023035302 |
| _version_ | 1827937288506572800 |
|---|---|
| author | Enrico Buccheri Daniele Dell’Aquila Marco Russo Rita Chiaramonte Giuseppe Musumeci Michele Vecchio |
| author_facet | Enrico Buccheri Daniele Dell’Aquila Marco Russo Rita Chiaramonte Giuseppe Musumeci Michele Vecchio |
| author_sort | Enrico Buccheri |
| collection | DOAJ |
| description | Background: Sarcopenia is a risk factor for morbidity and preventable mortality in old age, with consequent high costs for the national health system. Its diagnosis requires costly radiological examinations, such as the DEXA, which complicate screening in medical centers with a high prevalence of sarcopenia. Objectives: Developing a nearly zero-cost screening tool to emulate the performance of DEXA in identifying patients with muscle mass loss. This can crucially help the early diagnosis of sarcopenia at large-scale, contributing to reduce its prevalence and related complications with timely treatments. Methods: We exploit cross-sectional data for about 14,500 patients and 38 non-laboratory variables from successive NHANES over 7 years (1999–2006). Data are analyzed through a state-of-the-art artificial intelligence approach based on decision trees. Results: A reduced number of anthropometric parameters allows to predict the outcome of DEXA with AUC between 0.92 and 0.94. The most complex model derived in this paper exploits 6 variables, related to the circumference of key corporal segments and to the evaluation of body fat. It achieves an optimal trade-off sensitivity of 0.89 and a specificity of 0.82. Restricting exclusively to variables related to lower limb, we obtain an even simpler tool with only slightly lower accuracy (AUC 0.88–0.90). Conclusions: Anthropometric data seem to contain the entire informative content of a more complex set of non-laboratory variables, including anamnestic and/or morbidity factors. Compared to previously published screening tools for muscle mass loss, the newly developed models are less complex and achieve a better accuracy. The new results might suggest a possible inversion of the standard diagnostic algorithm of sarcopenia. We conjecture a new diagnostic scheme, which requires a dedicated clinical validation that goes beyond the scope of the present study. |
| first_indexed | 2024-03-13T08:23:22Z |
| format | Article |
| id | doaj.art-0b51656095d64a46adbfe7b5858100c3 |
| institution | Directory Open Access Journal |
| issn | 2405-8440 |
| language | English |
| last_indexed | 2024-03-13T08:23:22Z |
| publishDate | 2023-05-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Heliyon |
| spelling | doaj.art-0b51656095d64a46adbfe7b5858100c32023-05-31T04:47:12ZengElsevierHeliyon2405-84402023-05-0195e16323Can artificial intelligence simplify the screening of muscle mass loss?Enrico Buccheri0Daniele Dell’Aquila1Marco Russo2Rita Chiaramonte3Giuseppe Musumeci4Michele Vecchio5Department of Biomedical and Biotechnological Sciences, Section of Pharmacology, University of Catania, 95123 Catania, Italy; Corresponding author. Via Santa Sofia 89, Torre Biologica, University of Catania, 95123, Catania, Italy.Dipartimento di Fisica “Ettore Pancini”, University of Naples “Federico II”, Napoli, Italy; INFN – Sezione di Napoli, Napoli, Italy; Corresponding author. Via Cinthia 21, Complesso Universitario di Monte S. Angelo, Dipartimento di Fisica “Ettore Pancini”, University of Naples “Federico II”, 80126, Napoli, Italy.Department of Physics and Astronomy, University of Catania, Catania, Italy; INFN – Sezione di Catania, Catania, ItalyDepartment of Biomedical and Biotechnological Sciences, University of Catania, 95123 Catania, ItalyDepartment of Biomedical and Biotechnological Sciences, Human, Histology and Movement Science Section, University of Catania, 95123, Catania, ItalyDepartment of Biomedical and Biotechnological Sciences, Section of Pharmacology, University of Catania, 95123 Catania, Italy; Rehabilitation Unit, “AOU Policlinico G. Rodolico-San Marco”, 95123 Catania, ItalyBackground: Sarcopenia is a risk factor for morbidity and preventable mortality in old age, with consequent high costs for the national health system. Its diagnosis requires costly radiological examinations, such as the DEXA, which complicate screening in medical centers with a high prevalence of sarcopenia. Objectives: Developing a nearly zero-cost screening tool to emulate the performance of DEXA in identifying patients with muscle mass loss. This can crucially help the early diagnosis of sarcopenia at large-scale, contributing to reduce its prevalence and related complications with timely treatments. Methods: We exploit cross-sectional data for about 14,500 patients and 38 non-laboratory variables from successive NHANES over 7 years (1999–2006). Data are analyzed through a state-of-the-art artificial intelligence approach based on decision trees. Results: A reduced number of anthropometric parameters allows to predict the outcome of DEXA with AUC between 0.92 and 0.94. The most complex model derived in this paper exploits 6 variables, related to the circumference of key corporal segments and to the evaluation of body fat. It achieves an optimal trade-off sensitivity of 0.89 and a specificity of 0.82. Restricting exclusively to variables related to lower limb, we obtain an even simpler tool with only slightly lower accuracy (AUC 0.88–0.90). Conclusions: Anthropometric data seem to contain the entire informative content of a more complex set of non-laboratory variables, including anamnestic and/or morbidity factors. Compared to previously published screening tools for muscle mass loss, the newly developed models are less complex and achieve a better accuracy. The new results might suggest a possible inversion of the standard diagnostic algorithm of sarcopenia. We conjecture a new diagnostic scheme, which requires a dedicated clinical validation that goes beyond the scope of the present study.http://www.sciencedirect.com/science/article/pii/S2405844023035302Muscle mass lossSarcopeniaArtificial intelligenceBoost decision trees |
| spellingShingle | Enrico Buccheri Daniele Dell’Aquila Marco Russo Rita Chiaramonte Giuseppe Musumeci Michele Vecchio Can artificial intelligence simplify the screening of muscle mass loss? Heliyon Muscle mass loss Sarcopenia Artificial intelligence Boost decision trees |
| title | Can artificial intelligence simplify the screening of muscle mass loss? |
| title_full | Can artificial intelligence simplify the screening of muscle mass loss? |
| title_fullStr | Can artificial intelligence simplify the screening of muscle mass loss? |
| title_full_unstemmed | Can artificial intelligence simplify the screening of muscle mass loss? |
| title_short | Can artificial intelligence simplify the screening of muscle mass loss? |
| title_sort | can artificial intelligence simplify the screening of muscle mass loss |
| topic | Muscle mass loss Sarcopenia Artificial intelligence Boost decision trees |
| url | http://www.sciencedirect.com/science/article/pii/S2405844023035302 |
| work_keys_str_mv | AT enricobuccheri canartificialintelligencesimplifythescreeningofmusclemassloss AT danieledellaquila canartificialintelligencesimplifythescreeningofmusclemassloss AT marcorusso canartificialintelligencesimplifythescreeningofmusclemassloss AT ritachiaramonte canartificialintelligencesimplifythescreeningofmusclemassloss AT giuseppemusumeci canartificialintelligencesimplifythescreeningofmusclemassloss AT michelevecchio canartificialintelligencesimplifythescreeningofmusclemassloss |