Li Weishan

Dr. Li Weishan

orcid

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
23 March 2025 in Nature Communications
Verified
Journal Article
Open access
PDF file
TLTau Ming Liew
Tau Ming Liew
JFJessica Yi Hui Foo
Jessica Yi Hui Foo
HYHoward Yang
Howard Yang
STSze Yan Tay
Sze Yan Tay
WKWay Inn Koay
Way Inn Koay
JTJulian Thumboo
Julian Thumboo
Undiagnosed cognitive impairment is a pervasive global issue, often due to subtle nature of early symptoms, necessitating the use of brief cognitive tests for early detection. However, most brief tests are not scalable (requiring trained professionals), and are not designed for lower literacy groups (e.g. in underserved communities). Here, we developed PENSIEVE-AITM, a drawing-based digital test that is less dependent on literacy, and can be self-administered in <5 min. In a prospective study involving 1758 community-dwelling individuals aged 65 and older from Singapore (education range = 0–23 years), our deep-learning model showed excellent performance in detecting clinically-adjudicated mild cognitive impairment and dementia (AUC = 93%), comparable to traditional neuropsychological assessments (AUC = 94%, Pcomparison = 1.000). Results were consistent even across education subgroups. Being less dependent on literacy, PENSIEVE-AI holds promise for broader deployment in literacy-diverse populations similar to Singapore (e.g. some Asian and lower- and middle-income countries), potentially improving early detection and intervention of cognitive impairment.

11 March 2026 in Journal of Neurology
Verified
Journal Article
Closed access
PDF file
STSimon Kang Seng Ting
Simon Kang Seng Ting
STSean Asahara Thio
Sean Asahara Thio
KCKe Cao
Ke Cao
SHShahul Hameed
Shahul Hameed
LWLi Weishan
Li Weishan
ANAdeline S. L. Ng
Adeline S. L. Ng

6 January 2026 in JMIR Aging
Verified
Journal Article
Open access
TLTau Ming Liew
Tau Ming Liew
KYKing Fan Yip
King Fan Yip
KNKaavya Narasimhalu
Kaavya Narasimhalu
STSimon Kang Seng Ting
Simon Kang Seng Ting
LWLi Weishan
Li Weishan
WKWay Inn Koay
Way Inn Koay
Background: Undiagnosed cognitive impairment poses a global challenge, prompting recent interest in ultra-brief screening questionnaires (comprising <2 to 3 items) to efficiently identify individuals needing further evaluation. However, evidence on ultra-brief questionnaires remains limited, particularly regarding their validity across diverse literacy levels. Objective: This study aimed to develop an ultra-brief questionnaire that performs well in detecting mild cognitive impairment or dementia (MCI/dementia) across diverse literacy levels and to compare its performance with an established questionnaire (the 8-item Informant Interview to Differentiate Aging and Dementia [AD8]). Methods: This diagnostic study involved 1856 participants aged ≥65 years (median education 10 y, range 0‐23 y), prospectively recruited from community settings in Singapore. Participants and informants completed 15 cognition-related questions. MCI/dementia was diagnosed via a comprehensive assessment and consensus conference. The sample was randomly split 70/30—the training sample (70%) was used to derive an ultra-brief questionnaire from the 15 cognition-related questions (using an exhaustive search approach), and the test sample (30%) evaluated the area under the receiver operating characteristic curve (AUC). Results: The new questionnaire comprised 2 informant questions (ie, assistance with medications and worry about cognition ), plus age and years of education. It demonstrated excellent performance in detecting MCI/dementia (AUC 85%, 95% CI 80%‐90%), significantly better ( P =.003) than a nested baseline model (comprising age and years of education; AUC 78%, 95% CI 73%‐83%). In contrast, the AD8 had an AUC of 76% (95% CI 70%‐83%), not significantly different ( P> .99) from the baseline model. The questionnaire’s performance was consistent across education subgroups and varying prevalence scenarios. Two optimal cutoffs were used—the lower cutoff provided 80% sensitivity and 96% negative predictive value, and the upper cutoff provided 99% specificity and 81% positive predictive value. A web-based calculator is available for public use. Conclusions: This ultra-brief questionnaire enables rapid screening for cognitive impairment (in <1 min) by family members or as part of community geriatric assessments. Its excellent performance across literacy levels supports its utility for case finding in diverse populations, including underserved communities and lower- and middle-income countries.

28 July 2026 in Neurology
Verified
Journal Article
Closed access
STSimon Kang Seng Ting
Simon Kang Seng Ting
Seyed Ehsan SaffariSeyed Ehsan Saffari
Seyed Ehsan Saffari
JZJinran Zhan
Jinran Zhan
TGTushar Divikar Gosavi
Tushar Divikar Gosavi
SHShahul Hameed
Shahul Hameed
ANAdeline S.L. Ng
Adeline S.L. Ng
Seizures are a recognized comorbidity in dementia, with varying prevalence across Alzheimer disease (AD) and dementia with Lewy bodies (DLBs). Although previous studies have demonstrated an increased seizure risk in AD, the neuropathologic substrates underlying seizure susceptibility-particularly across dementia subtypes-remain incompletely understood. We aimed to identify distinct clinicopathologic correlates of clinically active seizures in AD and DLB using a large autopsy-confirmed cohort. We conducted a retrospective cohort study using data from the National Alzheimer's Coordinating Center (2005-December 2022). Autopsy-confirmed AD and DLB cases were included. Individuals with a history of stroke or traumatic brain injury were excluded. The primary outcome was clinically active seizures, defined as seizures occurring within 3 years before or after the diagnosis of dementia. Neuropathologic exposures included Braak stage, cerebral amyloid angiopathy (CAA), frontotemporal lobar degeneration, and vascular pathologies. Multivariable logistic regression models were used to examine associations between pathologic features and seizure occurrence, adjusting for relevant demographic covariates. A total of 3,498 participants were included, comprising 3,040 with AD (mean age, 73.4 years; 48.5% female) and 458 with DLB (mean age, 75.1 years; 31.4% female). Active seizures were identified in 174 participants with AD (5.7%) and 13 with DLB (2.8%). In AD, Braak stage VI (vs V) was associated with higher odds of active seizures (adjusted odds ratio [OR], 1.81; 95% CI 1.20-2.82; p = 0.007), as was moderate to severe CAA (adjusted OR, 1.38; 95% CI 1.01-1.90; p = 0.045). In DLB, AD-related pathologic features were not associated with seizures. By contrast, vascular pathology was significantly associated with seizure occurrence, including microinfarcts (adjusted OR, 5.11; 95% CI 1.64-16.4; p = 0.005) and infarcts (adjusted OR, 4.11; 95% CI 1.27-12.9; p = 0.015). In this autopsy-confirmed cohort, seizure susceptibility was associated with advanced tau pathology and CAA in AD. In DLB, exploratory analyses suggested a possible association between vascular pathology and seizures; however, these findings should be interpreted cautiously. Overall, the results support potentially distinct pathologic contributions to seizure susceptibility across dementia subtypes. Limitations include the use of advanced-stage pathologic samples, which may limit generalizability to earlier disease stages.

18 February 2025 in Reports
Verified
Journal Article
Open access
PDF file
SLSiew Fai Liew
Siew Fai Liew
LWLi Weishan
Li Weishan
Background and Clinical Significance: In our case study, the patient experienced approximately a year-long delay in her diagnosis, where her initial diagnosis was mistakenly a primary psychiatric disorder, resulting in undue stress on her family. The aim of this case study is to raise awareness of frontal variant Alzheimer’s dementia (fvAD) and to increase knowledge amongst clinicians about this disorder, its management and the need for long-term follow up in specialized clinics. Case Presentation: In January 2023, a 56-year-old woman first presented with a 4-month history of worsening cognitive symptoms with considerable overlapping mood symptoms. Her Mini-Mental State Examination (MMSE) score was 20/28, whereas her Frontal Assessment Battery (FAB) score was 6/18. Upon neuropsychological evaluation, she demonstrated multidomain cognitive deficits, where impairments were most prominent in executive dysfunction, learning, memory and semantic fluency. There was evidence of progressive neurodegenerative changes, with brain MRI (April 2024) showing predominant bilateral frontal and parietal volume loss, sparing the occipital and temporal lobes. Amyloid positron emission tomography (PET) was diffusely positive. A diagnosis of fvAD (frontal variant Alzheimer’s dementia) with BPSD was made. Other differential diagnoses included a major neurocognitive disorder due to multiple etiologies (AD and dementia with Lewy bodies (DLB)), frontotemporal dementia (bvFTD), primary progressive aphasia (PPA) and the psychiatric disorder of pseudodementia secondary to a mood disorder. Conclusions: This case presented significant challenges given the atypical neuropsychological profile and the complexity of the symptom presentation with significant neuropsychiatric overlay. The preliminary research findings underscore the complexity of fvAD, warranting future research using fundamental approaches.