Deep learning algorithm reveals probabilities of stage‐specific time to conversion in individuals with neurodegenerative disease LATE

Wu, Xinxing; Peng, Chong; Nelson, Peter T.; Cheng, Qiang

doi:10.1002/trc2.12363

Cited by 2 publications

(2 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…, 2021; Srivastava and Eachempati, 2021) and deep learning (Du and Shu, 2022; Hou et al. , 2021; Wu et al. , 2022).…”

Section: Discussionmentioning

confidence: 99%

“…Therefore, future research could consider other contextual variables such as "environmental uncertainty" and "Government's Reward-Penalty Mechanism", which may influence SC dynamic capabilities. Besides, future research can also explore the impact of specific emerging technologies on SC innovation and SC dynamic capabilities, such as the Internet of Things (Almomani et al, 2021;Huang et al, 2021;Peng et al, 2021), machine learning (Cheng et al, 2021;Srivastava and Eachempati, 2021) and deep learning (Du and Shu, 2022;Hou et al, 2021;Wu et al, 2022). Third, this research uses cross-sectional data to test the relationship between variables.…”

Section: Limitations and Avenues For Future Researchmentioning

confidence: 99%

See 1 more Smart Citation

Linkage between digital supply chain, supply chain innovation and supply chain dynamic capabilities: an empirical study

Li,

Zhang,

Liu

et al. 2023

IJLM

View full text Add to dashboard Cite

PurposeThere has been limited research that has explored the connection between digital supply chain (DSC) and SC innovation and SC dynamic capabilities. This paper aims to examine the mediating effect of SC innovation on the relationship between DSC and SC dynamic capabilities.Design/methodology/approachThe research model and hypotheses were tested, employing (Statistical Package of Social Sciences) SPSS 25.0 and (Analysis of Moment Structures) AMOS 24.0 on data drawn from the Chinese manufacturing enterprises.FindingsThe study reveals that DSC has a significant positive effect on SC innovation and SC dynamic capabilities. SC innovation also has a significant positive effect on SC dynamic capabilities. Besides, the authors' research illustrates that SC innovation partially mediates the relationship between DSC and SC dynamic capabilities.Research limitations/implicationsSince the results are derived from the data collected from China, it may not, therefore, be generalized to other settings. Moreover, future research could consider other contextual variables such as “environmental uncertainty” and “Government's Reward-Penalty Mechanism,” which may influence SC dynamic capabilities.Practical implicationsThe study provides practical insights for senior executives and managers in the manufacturing industry. Managers should emphasize the investment of advanced digital technologies and tools (DTTs) and improvement of SC visibility and collaboration. In the digital age, companies should pay attention to the introduction of advanced technologies, tools and processes and focus on cultivating an innovative spirit to promote SC dynamic capabilities, thereby enhancing competitive advantages.Originality/valueThe paper illustrates that DSC is of great significance to improving SC dynamic capabilities. This study reveals compelling insights for firms to enhance SC innovation and dynamic capabilities by using DSC as an enabler.

show abstract

“…, 2021; Srivastava and Eachempati, 2021) and deep learning (Du and Shu, 2022; Hou et al. , 2021; Wu et al. , 2022).…”

Section: Discussionmentioning

confidence: 99%

Section: Limitations and Avenues For Future Researchmentioning

confidence: 99%

Linkage between digital supply chain, supply chain innovation and supply chain dynamic capabilities: an empirical study

Li,

Zhang,

Liu

et al. 2023

IJLM

View full text Add to dashboard Cite

show abstract

Identification of profiles associated with conversions between the Alzheimer’s disease stages, using a machine learning approach

Dauphinot,

Laurent,

Prodel

et al. 2024

Alz Res Therapy

View full text Add to dashboard Cite

Background The identification of factors involved in the conversion across the different Alzheimer’s disease (AD) stages is crucial to prevent or slow the disease progression. We aimed to assess the factors and their combination associated with the conversion across the AD stages, from mild cognitive impairment to dementia, at a mild, moderate or severe stage and to identify profiles associated with earliest/latest conversion across the AD stages. Methods In this study conducted on the real-life MEMORA cohort data collected from January 1, 2013, and December 31, 2019, three cohorts were selected depending on the baseline neurocognitive stage from a consecutive sample of patients attending a memory center, aged between 50 and 90 years old, with a diagnosis of AD during the follow-up, and with at least 2 visits at 6 months to 1 year of interval. A machine learning approach was used to assess the relationship between factors including socio-demographic characteristics, comorbidities and history of diseases, prescription of drugs, and geriatric hospitalizations, and the censored time to conversion from mild cognitive impairment to AD dementia, from the mild stage of dementia to the moderate or severe stages of AD dementia, and from the moderate stage of AD dementia to the severe stage. Profiles of earliest/latest conversion compared to median time to conversion across stages were identified. The median time to conversion was estimated with a Kaplan-Meier estimator. Results Overall, 2891 patients were included (mean age 77±9 years old, 65% women). The median time of follow-up was 28 months for mild cognitive impairment (MCI) patients, 33 months for mild AD dementia and 30 months for moderate AD dementia. Among the 1264 patients at MCI stage, 61% converted to AD dementia (median time to conversion: 25 months). Among the 1142 patients with mild AD dementia, 59% converted to moderate/severe stage (median time: 23 months) and among the 1332 patients with moderate AD dementia, 23% converted to severe stage (Q3 time to conversion: 22 months). Among the studied factors, cardiovascular comorbidities, anxiety, social isolation, osteoporosis, and hearing disorders were identified as being associated with earlier conversion across stages. Symptomatic treatment i.e. cholinesterase inhibitors for AD was associated with later conversion from mild stage of dementia to moderate/severe stages. Conclusion This study based on a machine learning approach allowed to identify potentially modifiable factors associated with conversion across AD stages for which timely interventions may be implemented to delay disease progression.

show abstract

Deep learning algorithm reveals probabilities of stage‐specific time to conversion in individuals with neurodegenerative disease LATE

Cited by 2 publications

References 40 publications

Linkage between digital supply chain, supply chain innovation and supply chain dynamic capabilities: an empirical study

Linkage between digital supply chain, supply chain innovation and supply chain dynamic capabilities: an empirical study

Identification of profiles associated with conversions between the Alzheimer’s disease stages, using a machine learning approach

Contact Info

Product

Resources

About