Chiara Longo
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Chiara Longo has a total of 123 co-authors. Here are the top co-authors by number of shared publications:
Maria Chiara Malaguti
Department of Neurology, Azienda Sanitaria Universitaria Integrata del Trentino, ASUIT, Trento, Italy
5 shared publications- Maria Chiara Malaguti
Azienda Provinciale per i Servizi Sanitari (APSS) di Trento, Trento, Italy
5 shared publications Bruno Giometto
Neurology Unit Azienda Provinciale per i Servizi Sanitari (APSS) Trento Italy
4 shared publications- Costanza Papagno
Center for Mind/Brain Sciences (CIMeC), University of Trento, Trento, Italy
4 shared publications Donatella Ottaviani
Department of Neurology Santa Maria del Carmine Hospital Rovereto Italy
3 shared publications- Lorenzo Gios
Digital Health & Wellbeing Center, Fondazione Bruno Kessler, Trento, Italy
3 shared publications
Latest Publications
- Open Access
- 11 August 2026
- Published by SAGE Publications in Journal of Parkinson’s Disease
- Vol. 16 (7) , 1469-1500
Cognitive-behavioral therapy in people with Parkinson's disease and caregivers: A mixed method systematic review on clinical applications and therapeutic outcomes
Background: Cognitive behavioral therapy (CBT) has emerged as a promising intervention in Parkinson's disease (PD), although the available evidence remains heterogeneous in design and quality. Objective: The present mixed method systematic review aims to synthesize the evidence on CBT in people with PD (PwPD) and caregivers, focusing on clinical applications and therapeutic outcomes across symptom domains. Methods: A systematic search of PubMed, Web of Science, Scopus and Cochrane databases was conducted for studies published between 1980 and 2025, following PRISMA guidelines. Eligible studies evaluated clinical applications and therapeutic outcomes of CBT-based interventions in PwPD and/or caregivers and included randomized controlled trials, observational studies, case series and single-case reports. Findings were synthesized narratively, and certainty of evidence was assessed using a simplified GRADE approach. Results: Fifty-four studies met inclusion criteria. The most robust evidence was observed for depression, with several RCTs supporting the efficacy of CBT, resulting in moderate certainty of evidence. Evidence for anxiety and sleep disorders suggests potential benefit; however, certainty was low due to heterogeneity and small sample sizes. Evidence for impulse control disorders, cognitive outcomes, motor symptoms, and caregiver -related outcomes remain limited, with low to very low certainty, Effects on motor symptoms were inconsistent and likely indirect. Conclusions: CBT represents a flexible and transdiagnostic intervention for treating non-motor symptoms in PwPD and for caregivers. While moderate-certainty evidence supports CBT use for depression, evidence for other domains remains limited. These findings should be interpreted with caution, and further large-scale, well designed RCTs are needed to strengthen the evidence base and clarify optimal therapeutic targets and delivery format.
- 11 August 2026
- Published by SAGE Publications in Journal of Parkinson’s Disease
- Vol. 16 (7) , 1469-1500
Open AccessCognitive-behavioral therapy in people with Parkinson's disease and caregivers: A mixed method systematic review on clinical applications and therapeutic outcomes
Background: Cognitive behavioral therapy (CBT) has emerged as a promising intervention in Parkinson's disease (PD), although the available evidence remains heterogeneous in design and quality. Objective: The present mixed method systematic review aims to synthesize the evidence on CBT in people with PD (PwPD) and caregivers, focusing on clinical applications and therapeutic outcomes across symptom domains. Methods: A systematic search of PubMed, Web of Science, Scopus and Cochrane databases was conducted for studies published between 1980 and 2025, following PRISMA guidelines. Eligible studies evaluated clinical applications and therapeutic outcomes of CBT-based interventions in PwPD and/or caregivers and included randomized controlled trials, observational studies, case series and single-case reports. Findings were synthesized narratively, and certainty of evidence was assessed using a simplified GRADE approach. Results: Fifty-four studies met inclusion criteria. The most robust evidence was observed for depression, with several RCTs supporting the efficacy of CBT, resulting in moderate certainty of evidence. Evidence for anxiety and sleep disorders suggests potential benefit; however, certainty was low due to heterogeneity and small sample sizes. Evidence for impulse control disorders, cognitive outcomes, motor symptoms, and caregiver -related outcomes remain limited, with low to very low certainty, Effects on motor symptoms were inconsistent and likely indirect. Conclusions: CBT represents a flexible and transdiagnostic intervention for treating non-motor symptoms in PwPD and for caregivers. While moderate-certainty evidence supports CBT use for depression, evidence for other domains remains limited. These findings should be interpreted with caution, and further large-scale, well designed RCTs are needed to strengthen the evidence base and clarify optimal therapeutic targets and delivery format.
- Open Access
- 11 July 2026
- Published by Springer Nature in Journal of NeuroEngineering and Rehabilitation
- Vol. 23 (1)
Technology-enabled telerehabilitation for Parkinson’s disease: a scoping review of digital rehabilitation systems, delivery architectures, and implementation challenges
Digital technologies are increasingly integrated into neurorehabilitation programs for Parkinson’s Disease (PD), enabling remote delivery of therapy,
- 11 July 2026
- Published by Springer Nature in Journal of NeuroEngineering and Rehabilitation
- Vol. 23 (1)
Open AccessTechnology-enabled telerehabilitation for Parkinson’s disease: a scoping review of digital rehabilitation systems, delivery architectures, and implementation challenges
Digital technologies are increasingly integrated into neurorehabilitation programs for Parkinson’s Disease (PD), enabling remote delivery of therapy,
- Open Access
- 28 November 2025
- Published by Wiley in European Journal of Neurology
- Vol. 32 (12) , e70417
Machine Learning Analysis Applied to Prediction of Early Progression Independent of Relapse Activity in Multiple Sclerosis Patients
Background: Predicting prognosis in people with multiple sclerosis (pwMS) at early disease stages still remains an unmet need. Machine learning (ML) strategies demonstrated good reliability when applied for prediction in medicine. This study aimed at developing a predictive algorithm comparing different ML approaches, by using routine demographic, clinical and radiological data from a large multicentric cohort of newly diagnosed pwMS. Methods: Demographic, clinical, radiological and biochemical data were retrospectively collected at three Italian MS centers at baseline and four timepoints thereafter (6, 12, 24, and 36 months). Data from the first evaluation and subsequent 2‐year follow‐up were analyzed, comparing different ML models (Random Forest, Extra Trees, XGBoost, Logistic Regression and Support Vector Classifier) to predict progression independent of relapse activity (PIRA) at year 3. To understand how features impacted the selected model's output, a ML explainability analysis was performed on the whole cohort and on specific subsets of patients, those aged under 45 and those NEDA‐3 at the 2‐year follow‐up. Results: Data from 719 pwMS (age 34.6 ± 11.2 years); female sex 501 (70%) were analyzed. Ninety‐two pwMS (13%) developed PIRA at year 3. Random Forest achieved the highest score, with a test set area under the ROC curve (AUC) of 0.75 ± 0.06. Features with the highest predictive impact were Expanded Disability Status Scale at 24 months, age at symptom onset and disease duration at baseline. Conclusion: Our results showed the feasibility of applying ML techniques to predict short‐term PIRA in newly diagnosed pwMS by using routine clinical practice data, paving the way for tailored and personalized approaches.
- 28 November 2025
- Published by Wiley in European Journal of Neurology
- Vol. 32 (12) , e70417
Open AccessMachine Learning Analysis Applied to Prediction of Early Progression Independent of Relapse Activity in Multiple Sclerosis Patients
Background: Predicting prognosis in people with multiple sclerosis (pwMS) at early disease stages still remains an unmet need. Machine learning (ML) strategies demonstrated good reliability when applied for prediction in medicine. This study aimed at developing a predictive algorithm comparing different ML approaches, by using routine demographic, clinical and radiological data from a large multicentric cohort of newly diagnosed pwMS. Methods: Demographic, clinical, radiological and biochemical data were retrospectively collected at three Italian MS centers at baseline and four timepoints thereafter (6, 12, 24, and 36 months). Data from the first evaluation and subsequent 2‐year follow‐up were analyzed, comparing different ML models (Random Forest, Extra Trees, XGBoost, Logistic Regression and Support Vector Classifier) to predict progression independent of relapse activity (PIRA) at year 3. To understand how features impacted the selected model's output, a ML explainability analysis was performed on the whole cohort and on specific subsets of patients, those aged under 45 and those NEDA‐3 at the 2‐year follow‐up. Results: Data from 719 pwMS (age 34.6 ± 11.2 years); female sex 501 (70%) were analyzed. Ninety‐two pwMS (13%) developed PIRA at year 3. Random Forest achieved the highest score, with a test set area under the ROC curve (AUC) of 0.75 ± 0.06. Features with the highest predictive impact were Expanded Disability Status Scale at 24 months, age at symptom onset and disease duration at baseline. Conclusion: Our results showed the feasibility of applying ML techniques to predict short‐term PIRA in newly diagnosed pwMS by using routine clinical practice data, paving the way for tailored and personalized approaches.
- Open Access
- 16 October 2025
- Published by Wiley in Movement Disorders Clinical Practice
- Vol. 13 (4) , 1038-1043
A Short Version of Carers' Quality of Life Questionnaire for Parkinsonism: Data from Progressive Supranuclear Palsy Network
Background and objectives: Caregivers of progressive supranuclear palsy ( PSP) patients frequently show significant distress. The Parkinsonism Carers quality of life (QoL) (PQoL Carer) is a valid tool evaluating the effect of PSP on caregivers' QoL . Main aim of the present study was to develop a short version of the PQoL Carer, named PSP ‐ ShoQoL Carer. Methods: PQoL Carer was administered within the PSP ‐ NET . Participants underwent clinical, motor, cognitive, and behavioral evaluations. Results: Data from 344 participants were included. The final PSP ‐ ShoQoL Carer included eight items. The internal consistency was high (Cronbach's α = 0.867) and PSP ‐ ShoQoL Carer showed also good acceptability, reliability, and validity. The PSP ‐ ShoQoL Carer showed a significant correlation with caregivers' standard measures of QoL and with patients' motor, cognitive, and behavioral characteristics, such as neuropsychiatric symptoms. Finally, PSP ‐ ShoQoL Carer showed an appropriate sensitivity to change over 6‐month follow up. Conclusions: PSP ‐ ShoQoL Carer is a reliable and valid time‐saving tool for the assessment of caregivers' QoL in PSP .
- 16 October 2025
- Published by Wiley in Movement Disorders Clinical Practice
- Vol. 13 (4) , 1038-1043
Open AccessA Short Version of Carers' Quality of Life Questionnaire for Parkinsonism: Data from Progressive Supranuclear Palsy Network
Background and objectives: Caregivers of progressive supranuclear palsy ( PSP) patients frequently show significant distress. The Parkinsonism Carers quality of life (QoL) (PQoL Carer) is a valid tool evaluating the effect of PSP on caregivers' QoL . Main aim of the present study was to develop a short version of the PQoL Carer, named PSP ‐ ShoQoL Carer. Methods: PQoL Carer was administered within the PSP ‐ NET . Participants underwent clinical, motor, cognitive, and behavioral evaluations. Results: Data from 344 participants were included. The final PSP ‐ ShoQoL Carer included eight items. The internal consistency was high (Cronbach's α = 0.867) and PSP ‐ ShoQoL Carer showed also good acceptability, reliability, and validity. The PSP ‐ ShoQoL Carer showed a significant correlation with caregivers' standard measures of QoL and with patients' motor, cognitive, and behavioral characteristics, such as neuropsychiatric symptoms. Finally, PSP ‐ ShoQoL Carer showed an appropriate sensitivity to change over 6‐month follow up. Conclusions: PSP ‐ ShoQoL Carer is a reliable and valid time‐saving tool for the assessment of caregivers' QoL in PSP .
- Open Access
- 4 August 2025
- Published by Wiley in Brain and Behavior
- Vol. 15 (8) , e70737
When Sex Overcomes Motor Phenotype: New Evidence on Cognitive and Neurobehavioral Symptoms in Parkinson's Disease
Background: Sex‐based differences in cognitive and behavioral symptoms have been previously reported in Parkinson's disease (PD), as well as the effects of motor lateralization and phenotypes at onset. However, no studies investigated the interaction between these variables.Objective: We aimed to evaluate whether sex differences interact with motor phenotype and lateralization at the onset of cognitive and neurobehavioral symptoms.Methods: Data from 304 PD patients (119 women and 185 men) were retrospectively examined, including comprehensive neurologic, neuropsychological, and neurobehavioral assessments. MANCOVAs on tests divided based on the results of a principal component analysis were performed to compare cognitive and behavioral performance, considering sex, motor phenotype at onset, and onset lateralization as grouping variables. Analyses were also performed on a subsample of patients (n = 200) in which subgroups were balanced in terms of motor and demographic features.Results: Significant sex effects were found, with females showing higher performance compared to males in verbal long‐term memory (p = 0.00003), social cognition (p = 0.0001), and naming tasks (p = 0.03009). Significant interactions between motor phenotype and sex were found: rigid‐akinetic (RA) females showed higher performance than other groups in a verbal memory task (p = 0.0183), and tremor‐dominant (TD) females made more errors than the other groups in an inhibitory control task (p = 0.03853). Interestingly, RA females performed better on verbal learning than tremor‐dominant (TD) males (p = 0.00911), suggesting that sex effects overcome motor phenotype in this cognitive function. No significant interactions were found between sex and lateralization at onset concerning cognitive variables. However, patients with right‐sided onset, in particular females, self‐reported higher levels of behavioral symptoms.Conclusions: These results emphasize the complex relationship between demographic and PD motor features in delineating the clinical phenotype, which should be considered in designing patient‐tailored strategies for disease monitoring and intervention.
- 4 August 2025
- Published by Wiley in Brain and Behavior
- Vol. 15 (8) , e70737
Open AccessWhen Sex Overcomes Motor Phenotype: New Evidence on Cognitive and Neurobehavioral Symptoms in Parkinson's Disease
Background: Sex‐based differences in cognitive and behavioral symptoms have been previously reported in Parkinson's disease (PD), as well as the effects of motor lateralization and phenotypes at onset. However, no studies investigated the interaction between these variables.Objective: We aimed to evaluate whether sex differences interact with motor phenotype and lateralization at the onset of cognitive and neurobehavioral symptoms.Methods: Data from 304 PD patients (119 women and 185 men) were retrospectively examined, including comprehensive neurologic, neuropsychological, and neurobehavioral assessments. MANCOVAs on tests divided based on the results of a principal component analysis were performed to compare cognitive and behavioral performance, considering sex, motor phenotype at onset, and onset lateralization as grouping variables. Analyses were also performed on a subsample of patients (n = 200) in which subgroups were balanced in terms of motor and demographic features.Results: Significant sex effects were found, with females showing higher performance compared to males in verbal long‐term memory (p = 0.00003), social cognition (p = 0.0001), and naming tasks (p = 0.03009). Significant interactions between motor phenotype and sex were found: rigid‐akinetic (RA) females showed higher performance than other groups in a verbal memory task (p = 0.0183), and tremor‐dominant (TD) females made more errors than the other groups in an inhibitory control task (p = 0.03853). Interestingly, RA females performed better on verbal learning than tremor‐dominant (TD) males (p = 0.00911), suggesting that sex effects overcome motor phenotype in this cognitive function. No significant interactions were found between sex and lateralization at onset concerning cognitive variables. However, patients with right‐sided onset, in particular females, self‐reported higher levels of behavioral symptoms.Conclusions: These results emphasize the complex relationship between demographic and PD motor features in delineating the clinical phenotype, which should be considered in designing patient‐tailored strategies for disease monitoring and intervention.
- Open Access
- 4 July 2025
- Published by Elsevier in Clinical Parkinsonism & Related Disorders
- Vol. 13, 100365
Distinctive cognitive phenotypes in Parkinson’s disease patients with GBA mutations and without dementia: a multicentre cross-sectional retrospective study
- 4 July 2025
- Published by Elsevier in Clinical Parkinsonism & Related Disorders
- Vol. 13, 100365
Open AccessDistinctive cognitive phenotypes in Parkinson’s disease patients with GBA mutations and without dementia: a multicentre cross-sectional retrospective study
- Open Access
- 1 July 2025
- Vol. 32 (7) , e70281
Reply to Comments on the Article "Machine Learning Predicts Risk of Falls in Parkinson's Disease Patients in a Multicenter Observational Study".
- 1 July 2025
- Vol. 32 (7) , e70281
Open AccessReply to Comments on the Article "Machine Learning Predicts Risk of Falls in Parkinson's Disease Patients in a Multicenter Observational Study".
- 9 June 2025
- Published by Wiley in Movement Disorders Clinical Practice
- Vol. 12 (11) , 1873-1881
Digital Inclusion in Parkinson's Disease: A Case–Control Study
Background: People with Parkinson's disease (pwPD) are a candidate population to regularly use telemedicine services. However, their implementation into clinical practice can be limited by the so‐called “digital exclusion” of the target population. Objective: We aimed to (1) explore the level of digital inclusion in a cohort of pwPD as compared to sex‐ and age‐matched healthy controls (HC), and (2) to determine the possible influence of both socio‐demographic factors and disease features on the level of digital exclusion. Methods: Four hundred and ninety pwPD and 140 HC completed the Digital Inclusion Questionnaire (DIQUEST), which measures two barriers related to digital access and skills; demographic data (age, sex, education and economic status) and clinical characteristics (Hoeh & Yahr stage, MDS‐UPDRSIII, presence of depression/apathy, and/or mild cognitive decline) were also collected. Nonparametric tests were used for comparative analyses; multivariate linear regression models were performed to establish the predictive value of demographics and disease‐related variables on the DIQUEST scores. Results: pwPD had a higher level of digital exclusion than HC especially due to poorer digital skills. Both depression/apathy and mild cognitive decline were associated with a more pronounced digital exclusion. Beyond demographic variables, the presence of PD as well as its severity independently predicted the level of digital exclusion. Conclusions: PwPD suffer from a significant digital exclusion. Our results further highlight the paradox whereby subjects with more advanced PD are more prone to be digitally excluded, despite being the population that would most need telemedicine services.
- 9 June 2025
- Published by Wiley in Movement Disorders Clinical Practice
- Vol. 12 (11) , 1873-1881
Digital Inclusion in Parkinson's Disease: A Case–Control Study
Background: People with Parkinson's disease (pwPD) are a candidate population to regularly use telemedicine services. However, their implementation into clinical practice can be limited by the so‐called “digital exclusion” of the target population. Objective: We aimed to (1) explore the level of digital inclusion in a cohort of pwPD as compared to sex‐ and age‐matched healthy controls (HC), and (2) to determine the possible influence of both socio‐demographic factors and disease features on the level of digital exclusion. Methods: Four hundred and ninety pwPD and 140 HC completed the Digital Inclusion Questionnaire (DIQUEST), which measures two barriers related to digital access and skills; demographic data (age, sex, education and economic status) and clinical characteristics (Hoeh & Yahr stage, MDS‐UPDRSIII, presence of depression/apathy, and/or mild cognitive decline) were also collected. Nonparametric tests were used for comparative analyses; multivariate linear regression models were performed to establish the predictive value of demographics and disease‐related variables on the DIQUEST scores. Results: pwPD had a higher level of digital exclusion than HC especially due to poorer digital skills. Both depression/apathy and mild cognitive decline were associated with a more pronounced digital exclusion. Beyond demographic variables, the presence of PD as well as its severity independently predicted the level of digital exclusion. Conclusions: PwPD suffer from a significant digital exclusion. Our results further highlight the paradox whereby subjects with more advanced PD are more prone to be digitally excluded, despite being the population that would most need telemedicine services.
- Open Access
- 30 April 2025
- Published by Wiley in European Journal of Neurology
- Vol. 32 (5) , e70118
Machine Learning Predicts Risk of Falls in Parkison's Disease Patients in a Multicenter Observational Study
Background: Postural instability and gait difficulties are key symptoms of Parkinson's disease (PD), elevating the risk of falls substantially. Falls afflict 35% to 90% of PD patients, representing a major challenge in managing the condition. Accurate prediction of fall risk and identification of contributing factors are essential for timely interventions.Objectives: Our objective was to develop and validate a machine learning (ML) algorithm across multiple centers in Italy to accurately forecast fall risk and identify related factors using routinely collected clinical data.Methods: Patient data from two Italian centers (N = 251) were divided into a training cohort (N = 164) for ML model development and a validation cohort (N = 87). External validation was conducted on a subset of PPMI study patients (N = 65). We compared the performance of logistic regression (LR) and Support Vector Classifier (SVC) models trained on clinical data. The Shapley Additive exPlanations (SHAP) method was employed to examine the predictive power of individual variables.Results: In the training set, SVC outperformed LR slightly (AUC: LR = 0.779 ± 0.054, SVC = 0.792 ± 0.056). However, LR demonstrated better prediction accuracy in both internal (AUC: LR = 0.753, SVC = 0.733) and external validation cohorts (AUC: LR = 0.714, SVC = 0.676). SHAP analysis on the LR model revealed associations between fall risk and both motor and non‐motor variables.Conclusions: ML‐based models effectively estimate fall risk across different clinical centers, enabling tailored interventions to enhance PD patients' quality of life. Challenges persist in predicting falls in US‐based patients due to demographic and healthcare system differences.
- 30 April 2025
- Published by Wiley in European Journal of Neurology
- Vol. 32 (5) , e70118
Open AccessMachine Learning Predicts Risk of Falls in Parkison's Disease Patients in a Multicenter Observational Study
Background: Postural instability and gait difficulties are key symptoms of Parkinson's disease (PD), elevating the risk of falls substantially. Falls afflict 35% to 90% of PD patients, representing a major challenge in managing the condition. Accurate prediction of fall risk and identification of contributing factors are essential for timely interventions.Objectives: Our objective was to develop and validate a machine learning (ML) algorithm across multiple centers in Italy to accurately forecast fall risk and identify related factors using routinely collected clinical data.Methods: Patient data from two Italian centers (N = 251) were divided into a training cohort (N = 164) for ML model development and a validation cohort (N = 87). External validation was conducted on a subset of PPMI study patients (N = 65). We compared the performance of logistic regression (LR) and Support Vector Classifier (SVC) models trained on clinical data. The Shapley Additive exPlanations (SHAP) method was employed to examine the predictive power of individual variables.Results: In the training set, SVC outperformed LR slightly (AUC: LR = 0.779 ± 0.054, SVC = 0.792 ± 0.056). However, LR demonstrated better prediction accuracy in both internal (AUC: LR = 0.753, SVC = 0.733) and external validation cohorts (AUC: LR = 0.714, SVC = 0.676). SHAP analysis on the LR model revealed associations between fall risk and both motor and non‐motor variables.Conclusions: ML‐based models effectively estimate fall risk across different clinical centers, enabling tailored interventions to enhance PD patients' quality of life. Challenges persist in predicting falls in US‐based patients due to demographic and healthcare system differences.
- Open Access
- 11 February 2025
- Published by Wiley in European Journal of Neurology
- Vol. 32 (2) , e70077
Cognitive Outcomes of Advanced Therapies in Parkinson's Disease: A Systematic Review of Apomorphine and Levodopa–Carbidopa Intestinal Gel Therapies
Background: Parkinson's disease (PD) treatments, such as apomorphine (APO) and levodopa–carbidopa intestinal gel (LCIG), represent advanced therapeutic options for managing motor symptoms. However, clear selection criteria and well‐defined cognitive outcomes are lacking. This systematic review specifically aimed to address these gaps by assessing the cognitive impact of APO and LCIG in PD patients.Methods: A systematic review was conducted following PRISMA guidelines, with searches in PubMed, Web of Science, Scopus, and Embase. Two authors screened studies based on key inclusion criteria, including at least two cognitive tests, and a follow‐up of 6 months or more. The risk of bias was evaluated using the Newcastle–Ottawa Scale (NOS).Results: Fifteen studies were identified (7 APO and 8 LCIG). APO generally preserved cognitive function over a 12‐month follow‐up, with some decreases in visuospatial memory and executive functions. LCIG, with a 28‐month follow‐up, showed more extensive cognitive decline, particularly in patients with pre‐existing impairments. Variability in cognitive tests made direct comparisons difficult.Discussion: APO may have a more favorable cognitive profile than LCIG. However, differences in follow‐up duration, moderate risk of bias, and inconsistent cognitive assessments warrant cautious interpretation. Improved patient selection and comprehensive cognitive evaluations are recommended for future practice.
- 11 February 2025
- Published by Wiley in European Journal of Neurology
- Vol. 32 (2) , e70077
Open AccessCognitive Outcomes of Advanced Therapies in Parkinson's Disease: A Systematic Review of Apomorphine and Levodopa–Carbidopa Intestinal Gel Therapies
Background: Parkinson's disease (PD) treatments, such as apomorphine (APO) and levodopa–carbidopa intestinal gel (LCIG), represent advanced therapeutic options for managing motor symptoms. However, clear selection criteria and well‐defined cognitive outcomes are lacking. This systematic review specifically aimed to address these gaps by assessing the cognitive impact of APO and LCIG in PD patients.Methods: A systematic review was conducted following PRISMA guidelines, with searches in PubMed, Web of Science, Scopus, and Embase. Two authors screened studies based on key inclusion criteria, including at least two cognitive tests, and a follow‐up of 6 months or more. The risk of bias was evaluated using the Newcastle–Ottawa Scale (NOS).Results: Fifteen studies were identified (7 APO and 8 LCIG). APO generally preserved cognitive function over a 12‐month follow‐up, with some decreases in visuospatial memory and executive functions. LCIG, with a 28‐month follow‐up, showed more extensive cognitive decline, particularly in patients with pre‐existing impairments. Variability in cognitive tests made direct comparisons difficult.Discussion: APO may have a more favorable cognitive profile than LCIG. However, differences in follow‐up duration, moderate risk of bias, and inconsistent cognitive assessments warrant cautious interpretation. Improved patient selection and comprehensive cognitive evaluations are recommended for future practice.