DeCare
DeCare is an Android application built to support in-home caregivers in improving dementia patients' quality of life. Born from a deeply personal experience with a family member's undiagnosed dementia, the project addresses the lack of accessible early-detection tools — especially in low-to-middle income households where 68% of cases go untreated. Built as a capstone project for Bangkit Academy 2021, DeCare combines MMSE screening with cloud-based ML prediction, daily exercise guidance, activity reminders, health articles, and progress tracking.
01 / The_Problem
Dementia affects over 50 million people globally, with nearly 10 million new cases every year. In Indonesia alone, 1.2 million cases were recorded in 2016 — a number that doubles every 20 years. 68% of cases come from low-to-middle income families, and 61% of patients stay at home without proper treatment due to the high cost of care. The core issue is a lack of knowledge — families and caregivers often dismiss early symptoms like forgetfulness and mood swings as normal aging, delaying diagnosis until it's too late.
“My grandma went missing for three days. When a neighbor found her far from home, she couldn't remember where she lived or her family's names. That's when we knew it was dementia.”
02 / The_Solution
MMSE_SCREENING
Guided Mini-Mental State Examination flow that scores cognitive function and flags early signs of dementia.
ML_PREDICTION
Cloud-based machine learning model analyzes screening results and patient data to predict dementia likelihood.
DAILY_CARE
Exercise guidance, scheduled activity reminders, and curated health articles to support ongoing patient wellbeing.
PROGRESS_TRACKING
Recapitulation dashboard for caregivers to monitor patient progress over time and share with professionals.
DeCare provides an accessible, in-home tool for early dementia detection and ongoing patient care. The app walks caregivers through MMSE screening, sends patient data to a cloud ML model for prediction, and offers daily tools to maintain and improve quality of life.
03 / Technical_Recap
Built natively in Kotlin with Android Jetpack components. The ML pipeline runs on Google Cloud — patient data is sent via REST API to a TensorFlow model that returns a dementia probability score. Firebase handles authentication, real-time database for patient records, and Cloud Messaging for activity reminders.
class ScreeningViewModel(
private val repository: ScreeningRepository
) : ViewModel() {
private val _result = MutableLiveData<PredictionResult>()
val result: LiveData<PredictionResult> = _result
fun submitScreening(patient: Patient, answers: List<Answer>) {
viewModelScope.launch {
val score = MMSECalculator.calculate(answers)
val prediction = repository.predict(
patientData = patient,
mmseScore = score
)
_result.value = prediction
}
}
}