Calibrating Mini-Mental State Examination Scores to Predict Misdiagnosed Dementia Patients

Mini-Mental State Examination (MMSE) is used as a diagnostic test for dementia to screen patient’s cognitive assessment and disease severity. However, these examinations are often inaccurate unreliable either due human error or patients’ physical disability correctly interpret the questions well motor deficit. Erroneous data may lead wrong of specific patient. Therefore, other clinical factors (e.g., gender comorbidities) existing in electronic health records, can also play significant role, while reporting her examination results. This work considers various attributes patients accurately determine their status terms Score. We employ machine learning models calibrate MMSE score classify correctness diagnosis among patients, order assist clinicians better understanding progression impairment subsequent treatment. For this purpose, we utilize curated real-world ageing study data. A random forest prediction model employed estimate score, related classification patients.This uses provide accurate predictions, succeeding correcting an important percentage cases that contain previously identified miscalculated scores our dataset. Furthermore, effective mechanism automatically identifying patient episodes with values high confidence. These tools be combined finding within medical records where probably estimating what correct value should be. provides valuable support decision making process diagnosing potential patients.