Neuroradiology Division, Massachusetts General Hospital, Harvard Medical School, Boston, MA, United States of America.
Mass General Brigham Data Science Office, Boston, MA, United States of America.
PLoS One. 2023 Mar 13;18(3):e0281900. doi: 10.1371/journal.pone.0281900. eCollection 2023.
Machine learning (ML) algorithms to detect critical findings on head CTs may expedite patient management. Most ML algorithms for diagnostic imaging analysis utilize dichotomous classifications to determine whether a specific abnormality is present. However, imaging findings may be indeterminate, and algorithmic inferences may have substantial uncertainty. We incorporated awareness of uncertainty into an ML algorithm that detects intracranial hemorrhage or other urgent intracranial abnormalities and evaluated prospectively identified, 1000 consecutive noncontrast head CTs assigned to Emergency Department Neuroradiology for interpretation. The algorithm classified the scans into high (IC+) and low (IC-) probabilities for intracranial hemorrhage or other urgent abnormalities. All other cases were designated as No Prediction (NP) by the algorithm. The positive predictive value for IC+ cases (N = 103) was 0.91 (CI: 0.84-0.96), and the negative predictive value for IC- cases (N = 729) was 0.94 (0.91-0.96). Admission, neurosurgical intervention, and 30-day mortality rates for IC+ was 75% (63-84), 35% (24-47), and 10% (4-20), compared to 43% (40-47), 4% (3-6), and 3% (2-5) for IC-. There were 168 NP cases, of which 32% had intracranial hemorrhage or other urgent abnormalities, 31% had artifacts and postoperative changes, and 29% had no abnormalities. An ML algorithm incorporating uncertainty classified most head CTs into clinically relevant groups with high predictive values and may help accelerate the management of patients with intracranial hemorrhage or other urgent intracranial abnormalities.
机器学习（ML）算法可用于检测头部 CT 上的关键发现，从而加快患者的管理速度。大多数用于诊断影像学分析的 ML 算法使用二分法分类来确定是否存在特定的异常。然而，影像学表现可能不确定，算法推断可能存在较大的不确定性。我们将不确定性意识纳入到一种 ML 算法中，该算法用于检测颅内出血或其他紧急颅内异常，并前瞻性地对 1000 例连续的非对比头部 CT 进行评估，这些 CT 被分配给急诊神经放射科进行解释。该算法将扫描结果分为高（IC+）和低（IC-）两种发生颅内出血或其他紧急异常的概率。算法将所有其他病例标记为无预测（NP）。IC+病例（N=103）的阳性预测值为 0.91（CI：0.84-0.96），IC-病例（N=729）的阴性预测值为 0.94（0.91-0.96）。IC+的入院、神经外科干预和 30 天死亡率分别为 75%（63-84）、35%（24-47）和 10%（4-20），而 IC-分别为 43%（40-47）、4%（3-6）和 3%（2-5）。NP 有 168 例，其中 32%有颅内出血或其他紧急异常，31%有伪影和术后改变，29%无异常。纳入不确定性的 ML 算法将大多数头部 CT 分类为具有高预测值的临床相关组，这可能有助于加快颅内出血或其他紧急颅内异常患者的管理。
