# 牙周保險
###### tags: `intern`
## 關於牙周病

## 關於保險
牙周理賠主要是在實支實付醫療險中，轉嫁自費項目
e.g. [國泰人壽真安順手術醫療終身保險](https://www.cathaylife.com.tw/ts/B2CStatic/fileUpload/download/L6.pdf)、紐約人壽、南山人壽
| 可理賠項目 | 不可理賠項目 |
| -------- | -------- |
| 自費麻醉藥費, ==再生膜, 骨粉==, 齒槽骨, 膠原蛋白貼片 | 牙釘, 牙根, 牙冠, 牙套, 其他牙體 |

#### 哪些醫療險有理賠牙科門診手術？
* 對於「手術」沒有特別定義（因為多數保險只理賠健保列舉的手術，但牙齒手術不包含在內）

[圖片來源](https://wewe333we.pixnet.net/blog/post/227466467-%E3%80%90%E4%BB%80%E9%BA%BC%E6%98%AF%E5%81%A5%E4%BF%9D227%E6%89%8B%E8%A1%93%EF%BC%9F%E4%BB%80%E9%BA%BC%E5%8F%88%E6%98%AF226%E8%99%95%E7%BD%AE%E3%80%91)

#### 理賠條件
* **屬必要性醫療**
1. 植牙診斷證明書，上面清楚記錄手術日期、手術項目，包括麻醉、補骨、植牙等；
2. 植牙前的X光片，證實植牙屬於「必要性醫療行為」，實支醫療險就會啟動理賠機制。
3. 通常 **拔牙、翻瓣清創、再生手術** 較有機會給付，但如植牙、美觀相關手術絕大部分是不給付。
> 手術診斷證明書的理賠認定關鍵字：**牙齒齒位、麻醉、翻瓣、補骨粉、再生膜**
因為需要是「必要性醫療行為」，所以證明書需要有 **嚴重、切開、縫合** 等關鍵字。
>
> 可以參考 [這個人的理賠經驗](https://akanana.pixnet.net/blog/post/466670675)

* **符合保單保障項目**
1. 住院病房費保險金每日2,500元
2. 醫院各項雜費最高理賠5萬元
3. 外科手術限額6萬2,500元
(雖然植牙手術屬於門診手術，但因為有麻醉、補骨、植入牙根植體等耗材，所以還是會理賠手術費與雜費。)


> ### 參考
> * [治療牙周病好貴，但有保險能賠你知道嗎？快翻開你的保單！](http://smart.businessweekly.com.tw/Reading/IndepArticle.aspx?id=6000630)
> [自己的權益自己顧！牙周手術保險理賠你應該知道的事](http://www.kmuh.org.tw/www/kmcj/data/10807/23.htm)
> * [牙周病翻瓣手術，賠還是不賠？](https://miffycares.com/2020/10/14/%E7%89%99%E5%91%A8%E7%97%85%E7%BF%BB%E7%93%A3%E6%89%8B%E8%A1%93%E9%8C%A2%E5%8C%85%E7%97%9B%E5%95%8A/)
> * [治牙錢坑大，靠實支醫療險幫大忙，植牙花費75萬，理賠金買單70萬！](https://www.moneynet.com.tw/article/10051)
> * [牙齒理賠，關於醫療實支實付](https://wewe333we.pixnet.net/blog/post/199927428)

### 康健牙保
* 已裝設義齒、植牙之部位再次處置：不理賠
* 因為牙周病或是蛀牙導致缺齒時，依保單年度給付：

| | 活動、固定義齒 | 植牙 |
| -------- | -------- | -------- |
| 第一保單年度 | 30% | 80% |
| 第二保單年度 | 75% | 200% |
| >= 第三保單年度 | 150% | 400% |

> ### 參考
> * [保險商品分析-康健人壽"從齒健康"-加值型](https://blog.xuite.net/jvailly/twblog/179443580)
> * [有人評估過康健的牙齒保險划算嗎??](https://www.mobile01.com/topicdetail.php?f=330&t=3424510)

## 關於技術
### 1. [Diagnosis and prediction of periodontally compromised teeth using a deep learning-based convolutional neural network algorithm](https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5944222/)
**Purpose :** develop a computer-assisted detection system to predict periodontally compromised teeth (PCT) into "Healthy, Moderate, Severe" classes.
**Data :** periapical radiographic dataset was split into training (n=1,044), validation (n=348), and test (n=348)
**Result :** diagnostic accuracy for PCT was 81.0% for premolars and 76.7% for molars(臼齒).


### 2. [Deep Learning for the Radiographic Detection of Periodontal Bone Loss](https://www.nature.com/articles/s41598-019-44839-3)
**Purpose :** measure % of Periodontal Bone Loss (PBL)
**Data :** 2001 image segments from panoramic radiographs.
**Result :** Mean accuracy = 0.81. Our findings also highlight the limited agreement between the dentists.

### 3. [Automatic detection of periodontal compromised teeth in digital panoramic radiographs using faster regional convolutional neural networks](https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7314603/)

**Purpose :** use a deep learning-based object detection method to identify periodontally compromised teeth on digital panoramic radiographs.

**Data :** The dataset consisted of 100 anonymized digital panoramic radiographs collected using an Orthophos XG (Sirona, Bensheim, Germany). The mean age of the patients, who consisted of 42 men and 58 women, at the time of the oral examinations was 51.24±12.61 years.

**Result :** Average Percision Rate = 0.81; Average Recall Rate = 0.80


### 4. [Deep Learning Hybrid Method to Automatically Diagnose Periodontal Bone Loss and Stage Periodontitis](https://www.nature.com/articles/s41598-020-64509-z)

`Scientific Reports volume 10, Article number: 7531 (2020)`

**Purpose :** We developed an automatic method for staging periodontitis on dental panoramic radiographs, detecting and classifying the periodontal bone loss of each individual tooth.

**Methods:** Using the percentage rate, we could automatically classify the periodontal bone loss. This classification was used for periodontitis staging according to the new criteria proposed at the 2017 World Workshop on the Classification of Periodontal and Peri-Implant Diseases and Conditions.

**Data :** 340 panoramic radiographs excluding the images of patients with primary or mixed dentition.

**Result :**