Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Skip to main content
Springer Nature Link
Log in

Obsolete personal information update system: towards the prevention of falls in the elderly

  • Published:
Applied Intelligence Aims and scope Submit manuscript

Abstract

Falls stand for a prevalent problem among the elderly and a significant public health concern. In recent years, a growing number of apps have been developed to assist in terms of the delivery of more effective and efficient falls prevention programs. All of these apps rely on a massive elderly personal database gathered from hospitals, mutual health groups, and other organizations that help the elderly. Information on an older adult is constantly changing, and it may become obsolete at any time, contradicting what we currently know about the same person. As a result, it needs to be checked and updated on a regular basis in order to maintain database consistency and hence provide a better service. This research work describes an Obsolete Personal Information Update System (OIUS) developed as part of the elderly-fall prevention project. Our OIUS intends to control and update the information gathered about each older adult in real-time, to provide consistent information on demand, and to provide tailored interventions to carers and fall-risk patients. The method discussed here is based upon a polynomial-time algorithm built on top of a causal Bayesian network that models the older adults data. The outcome is presented as an AND-OR recommendation Tree with a certain level of accuracy. On an aged personal information base, we perform an empirical study for such a model. Experiments corroborate our OIUS’s viability and effectiveness.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Algorithm 1
Fig. 10
Fig. 11

Similar content being viewed by others

Explore related subjects

Discover the latest articles, news and stories from top researchers in related subjects.

Notes

  1. https://www.cdc.gov

  2. https://www.who.int/news-room/fact-sheets/detail/ageing-and-health

  3. http://www.elsat2020.org/en

  4. https://agrum.gitlab.io/

References

  1. Alchourrón CE, Gärdenfors P, Makinson D (1985) On the logic of theory change: partial meet contraction and revision functions. J Symb Log 1:510–530

    Article  MathSciNet  MATH  Google Scholar 

  2. Basu P (2019) Bayesian updating rules and agm belief revision. J Econ Theory 179:455–475

    Article  MathSciNet  MATH  Google Scholar 

  3. Bosch J, Pearce LA, Sharma M, Mikulík R, Whiteley WN, Canavan M, Hart RG, O’Donnell MJ (2022) Functional abilities of an international post-stroke population: standard assessment of global everyday activities (sagea) scale. J Stroke Cerebrovasc Dis 31(4):106329

    Article  Google Scholar 

  4. Byrne RM, Walsh CR (2019) Contradictions and counterfactuals: Generating belief revisions in conditional inference. In: Proceedings of the twenty-fourth annual conference of the cognitive science society, routledge, pp. 160–165

  5. Carrara M, Fazio D, Pra Baldi M (2022) Paraconsistent belief revision: an algebraic investigation. Erkenntnis :1–29

  6. Chaieb S, Delcroix V, Mrad AB, Grislin-Le Strugeon E (2018) Réseau bayésien pour la gestion de l’obsolescence dans une base d’informations en vue de l’évaluation du risque de chute des personnes âgées. In: EGC, pp 359–364

  7. Chaieb S, Hnich B, Mrad AB (2022) Data obsolescence detection in the light of newly acquired valid observations. Appl Intell: 1–23

  8. Chaieb S, Mrad AB, Hnich B (2021) Probabilistic causal model for the detection of obsolete personal information to prevent falls in the elderly. Proc Comput Sci 192:1170–1179

    Article  Google Scholar 

  9. Choi Sh, Lim Cg (2020) Immediate effects of ankle non-elastic taping on balance and gait ability in patients with chronic stroke: a randomized, controlled trial. J Manip Physiol Ther 43(9):922–929

    Article  MathSciNet  Google Scholar 

  10. Cormode G, Tirthapura S, Xu B (2007) Time-decaying sketches for sensor data aggregation. In: Proceedings of the twenty-sixth annual ACM symposium on principles of distributed computing, pp 215–224

  11. Dean C, Clemson L, Ada L, Scrivener K, Lannin N, Mikolaizak S, Day S, Cusick A, Gardner B, Heller G, et al. (2021) Home-based, tailored intervention for reducing falls after stroke (fast): Protocol for a randomized trial. Int J Stroke 16(9):1053–1058

    Article  Google Scholar 

  12. Denissen S, Staring W, Kunkel D, Pickering RM, Lennon S, Geurts AC, Weerdesteyn V, Verheyden GS (2019) Interventions for preventing falls in people after stroke. Cochrane database of systematic reviews 10(10):CD008728

    Google Scholar 

  13. Early NK, Fairman KA, Hagarty JM, Sclar DA (2019) Joint effects of advancing age and number of potentially inappropriate medication classes on risk of falls in medicare enrollees. BMC Geriatr 19 (1):194

    Article  Google Scholar 

  14. Goyal J, Khandnor P, Aseri TC (2020) Classification, prediction, and monitoring of parkinson’s disease using computer assisted technologies: a comparative analysis. Eng Appl Artif Intell 96:103955

    Article  Google Scholar 

  15. Grichi Y, Beauregard Y, Dao TM (2019) An approach to obsolescence forecasting based on hidden markov model and compound poisson process. Int J Ind Eng 1(2):111–124

    Google Scholar 

  16. Gupta A Managing inventory obsolescence for improved retail performance. https://i.dell.com/sites/csdocuments/Business_smb_sb360_Documents/en/uk/wp-retail-r4-fa-uk.pdf. Accessed 22 Jan 2022

  17. de Jesus Chagas T, dos Santos Cravo IS, Bazan R, de Souza LAPS, Luvizutto GJ (2021) Effects of transcranial direct current stimulation on balance after ischemic stroke (sande trial): study protocol for a multicentric randomized controlled trial. Contemp Clin Trials 105:106396

    Article  Google Scholar 

  18. Kato Y, Kitamura S, Katoh M, Hirano A, Senjyu Y, Ogawa M, Maeda H, Mukaino M, Hirano S, Sakurai H et al (2022) Stroke patients with nearly independent transfer ability are at high risk of falling. J Stroke Cerebrovasc Dis 31(1):106169

    Article  Google Scholar 

  19. Kollerup A, Kjellberg J, Ibsen R (2022) Ageing and health care expenditures: the importance of age per se, steepening of the individual-level expenditure curve, and the role of morbidity. Eur J Health Econ 23:1121–1149

    Article  Google Scholar 

  20. Ling Y, Xu F, Xia X, Dai D, Xiong A, Sun R, Qiu L, Xie Z (2021) Vitamin d supplementation reduces the risk of fall in the vitamin d deficient elderly: an updated meta-analysis. Clin Nutr 40(11):5531–5537

    Article  Google Scholar 

  21. Liouane Z, Lemlouma T, Roose P, Weis F, Messaoud H (2018) An improved extreme learning machine model for the prediction of human scenarios in smart homes. Appl Intell 48(8):2017–2030

    Article  Google Scholar 

  22. Luo G, Zhao B, Du S (2019) Causal inference and bayesian network structure learning from nominal data. Appl Intell 49(1):253–264

    Article  Google Scholar 

  23. Malazi HT, Davari M (2018) Combining emerging patterns with random forest for complex activity recognition in smart homes. Appl Intell 48(2):315–330

    Article  Google Scholar 

  24. Mellal MA (2020) Obsolescence–a review of the literature. Technol Soc 63:101347

    Article  Google Scholar 

  25. Montero-Odasso M, Sarquis-Adamson Y, Song HY, Bray NW, Pieruccini-Faria F, Speechley M (2019) Polypharmacy, gait performance, and falls in community-dwelling older adults. results from the gait and brain study. J Am Geriatr Soc 67(6):1182–1188

    Article  Google Scholar 

  26. Montero-Odasso M, Van Der Velde N, Alexander NB, Becker C, Blain H, Camicioli R, Close J, Duan L, Duque G, Ganz DA et al (2021) New horizons in falls prevention and management for older adults: a global initiative. Age Ageing 50(5):1499–1507

    Article  Google Scholar 

  27. Nadia BA, Amrouch C, Boukhayatia F, Mahjoub F, Guamoudi A, Lahmar I, Berriche O, Jamoussi H (2021) Evaluation of quality of life and degree of autonomy among elderly subjects with type 2 diabetes NPG neurologie-psychiatrie-gériatrie

  28. Ortega-Bastidas P, Gómez B, Barriga K, Saavedra F, Aqueveque P (2022) Post-stroke balance impairments assessment: clinical scales and current technologies

  29. Paik JH (2016) Parameterized decay model for information retrieval. ACM Trans Intell Syst Technol (TIST) 7(3):1–21

    Article  Google Scholar 

  30. Pearl J (1987) Evidential reasoning using stochastic simulation of causal models. Artif Intell 32 (2):245–257

    Article  MathSciNet  MATH  Google Scholar 

  31. Pearl J (1988) Bayesian inference. Probabilistic reasoning in intelligent systems: networks of plausible inference, 2nd edn. Morgan Kaufmann Publisher, San Francisco, pp 29–75

    Google Scholar 

  32. Pearl J (1995) Causal diagrams for empirical research. Biometrika 82(4):669–688

    Article  MathSciNet  MATH  Google Scholar 

  33. Pearl J (2012) The do-calculus revisited. In: Proceedings of the twenty-eighth conference on uncertainty in artificial intelligence, UAI’12. AUAI Press, Arlington, Virginia, pp 3–11

  34. Pearl J (2014) Probabilistic reasoning in intelligent systems: networks of plausible inference. Elsevier

  35. Pearl J, Mackenzie D (2018) The book of why: the new science of cause and effect. Basic books

  36. Pradhan M, Henrion M, Provan G, Del Favero B, Huang K (1996) The sensitivity of belief networks to imprecise probabilities: an experimental investigation. Artif Intell 85(1–2):363–397

    Article  Google Scholar 

  37. Raeiszadeh M, Tahayori H, Visconti A (2019) Discovering varying patterns of normal and interleaved adls in smart homes. Appl Intell 49(12):4175–4188

    Article  Google Scholar 

  38. Rodrigues F, Domingos C, Monteiro D, Morouċo P (2022) A review on aging, sarcopenia, falls, and resistance training in community-dwelling older adults. Int J Environ Res Public Health 19(2):874

    Article  Google Scholar 

  39. Ropero RF, Renooij S, Van der Gaag LC (2018) Discretizing environmental data for learning bayesian-network classifiers. Ecol Model 368:391–403

    Article  Google Scholar 

  40. Samuel M, Tardif JC, Bouabdallaoui N, Khairy P, Dubé MP, Blondeau L, Guertin MC (2021) Colchicine for secondary prevention of cardiovascular disease: a systematic review and meta-analysis of randomized controlled trials. Can J Cardiol 37(5):776–785

    Article  Google Scholar 

  41. Sanguri K, Mukherjee K (2021) Forecasting of intermittent demands under the risk of inventory obsolescence. J Forecast 40:1054–1069

    Article  MathSciNet  Google Scholar 

  42. Sharif SI, Al-Harbi AB, Al-Shihabi AM, Al-Daour DS, Sharif RS (2018) Falls in the elderly: assessment of prevalence and risk factors. Pharm Pract (Granada) 16(3):00

    Article  Google Scholar 

  43. Shear T, Fitelson B (2019) Two approaches to belief revision. Erkenntnis 84(3):487–518

    Article  MathSciNet  MATH  Google Scholar 

  44. Sicouri S, Antzelevitch C (2018) Mechanisms underlying the actions of antidepressant and antipsychotic drugs that cause sudden cardiac arrest. Arrhythmia Electrophysiol Rev 7(3):199

    Article  Google Scholar 

  45. Sorrentino G, Sale P, Solaro C, Rabini A, Cerri CG, Ferriero G (2018) Clinical measurement tools to assess trunk performance after stroke: a systematic review. Eur J Phys Rehab Med 54(5):772–784

    Google Scholar 

  46. Strößner C (2020) Compositionality meets belief revision: a bayesian model of modification. Rev Philos Psychol 11:859–880

    Article  Google Scholar 

  47. Torchio A, Corrini C, Anastasi D, Parelli R, Meotti M, Spedicato A, Groppo E, D’Arma A, Grosso C, Montesano A, et al. (2022) Identification of modified dynamic gait index cutoff scores for assessing fall risk in people with parkinson disease, stroke and multiple sclerosis. Gait Posture 91:1–6

    Article  Google Scholar 

  48. Tsai CF, Chen YC (2019) The optimal combination of feature selection and data discretization: an empirical study. Inf Sci 505:282–293

    Article  Google Scholar 

  49. Wang H, Ding X, Li J, Gao H (2018) Rule-based entity resolution on database with hidden temporal information. IEEE Trans Knowl Data Eng 30(11):2199–2212

    Google Scholar 

  50. Ward KM, Citrome L (2018) Antipsychotic-related movement disorders: drug-induced parkinsonism vs. tardive dyskinesia—key differences in pathophysiology and clinical management. Neurol Ther 7(2):233–248

    Article  Google Scholar 

  51. Xiong X, Min W, Zheng WS, Liao P, Yang H, Wang S (2020) S3d-cnn: skeleton-based 3d consecutive-low-pooling neural network for fall detection. Appl Intell 50(10):3521–3534

    Article  Google Scholar 

  52. Zar JH (1972) Significance testing of the spearman rank correlation coefficient. J Am Stat Assoc 67(339):578–580

    Article  MATH  Google Scholar 

Download references

Acknowledgements

The present work is part of the ELSAT2020Footnote 3 project, which is co-financed by the European Union with the European Regional Development Fund, the French state and the Hauts de France Region Council. It is also supported by the PEJC project (20PEJC 08-03) fund from the Tunisian ministry of higher education and scientific research. A tiny part of the data used for the simulation has been invested in previous work and may be found in https://doi.org/10.1016/j.procs.2021.08.120 and https://doi.org/10.1016/j.procs.2021.08.020. The experts who provided the estimates for the used causal Bayesian model and the University Hospital physicians who validated our scenarios are sincerely thanked for their active participation.

Author information

Authors and Affiliations

  1. ISITCom, University of Sousse, Sousse, 4011, Tunisia

    Salma Chaieb

  2. CES Lab, ENIS, University of Sfax, Sfax, 3038, Tunisia

    Salma Chaieb, Ali Ben Mrad & Brahim Hnich

  3. ISAAS, University of Sfax, Sfax, 1013, Tunisia

    Ali Ben Mrad

  4. FSM, University of Monastir, Monastir, 5000, Tunisia

    Brahim Hnich

Authors
  1. Salma Chaieb
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Ali Ben Mrad
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Brahim Hnich
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Salma Chaieb.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

An early version of this paper appeared on the quant-ph arXiv as arxiv:2101.10132

Appendices

Appendix A: Variables description

Table 6 CBN variables for elderly fall
Full size table

Appendix B: User interface

We designed a first test application in the form of a desktop interface, as demonstrated in Fig. 12, to allow users (e.g., physicians) to manipulate our system and show the effects of the user’s manipulation. Our application was implemented under the Windows environment, with the pyAgrum libraryFootnote 4. As displayed in Fig. 12, the designed interface includes the different variables of the RB. Thus, when entering observations, a drop-down list containing all the possible values of each variable is displayed to the user. The latter selects the appropriate one.

Fig. 12
figure 12

User interface 1

Full size image

We simulate scenario 3 given in Table 4, which is related to a particular elderly patient. Once the user enters the new observation (Numberoffalls = f3 :≥ 5) in the treated scenario), the other old observations on the same older adult will be filled in automatically. Once the observations are validated, the new observation will be recorded in the database row reserved for the concerned patient. Then, our system checks if there is a contradiction between onew = f3 and the other observations. In case of contradiction on one or more observations, the system displays an alert message (see Fig. 13) highlighting the variables likely to be a direct or indirect cause of this contradiction.

Fig. 13
figure 13

User interface 2

Full size image

The physicians reacted positively to the first trial version of our system, and some of them stated that working with it is advantageous to a great extend. Furthermore, our system had no detrimental impact on users; none of the doctors’ good decisions were influenced, even when the algorithm supplied an inaccurate answer. It has led us to assert that our system could be valuable in terms of supporting physicians and other users at the level of detecting abnormal behaviors, exploring and identifying all possible reasons, and deciding how to handle these situations as early as possible to avoid any potential risk.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Chaieb, S., Mrad, A.B. & Hnich, B. Obsolete personal information update system: towards the prevention of falls in the elderly. Appl Intell 53, 18061–18084 (2023). https://doi.org/10.1007/s10489-022-04289-3

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10489-022-04289-3

Keywords

Search

Navigation